From 925734b784c03fcdfb8c649528a6abea613b1ed8 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Wed, 1 Oct 2025 00:13:26 +0000 Subject: [PATCH] bot: update monthly RSS feed --- feed_monthly.xml | 1052 +++++++++++++++++++++++----------------------- 1 file changed, 526 insertions(+), 526 deletions(-) diff --git a/feed_monthly.xml b/feed_monthly.xml index 86ef88d..6694097 100644 --- a/feed_monthly.xml +++ b/feed_monthly.xml @@ -7,741 +7,741 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 01 Sep 2025 00:14:08 +0000 + Wed, 01 Oct 2025 00:13:26 +0000 - Efficient Agents: Building Effective Agents While Reducing Cost - https://arxiv.org/abs/2508.02694 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.02694.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ningning Wang, Xavier Hu, Pai Liu, He Zhu, Yue Hou, Heyuan Huang, Shengyu Zhang, Jian Yang, Jiaheng Liu, Ge Zhang, Changwang Zhang, Jun Wang, Yuchen Eleanor Jiang, Wangchunshu Zhou</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten scalability and accessibility. This work presents the first systematic study of the efficiency-effectiveness trade-off in modern agent systems, addressing the critical need for cost-effective designs without sacrificing performance. We investigate three key questions: (1) How much complexity do agentic tasks inherently require? (2) When do additional modules yield diminishing returns? (3) How much efficiency can be gained through the design of efficient agent frameworks? Through an empirical analysis on the GAIA benchmark, we evaluate the impact of LLM backbone selection, agent framework designs, and test-time scaling strategies. Using the cost-of-pass metric, we quantify the efficiency-performance trade-off across these dimensions. Our findings inform the development of Efficient Agents , a novel agent framework that has an optimal complexity to task requirements. Efficient Agents retains 96.7% of the performance of OWL, one leading open-source agent framework, while reducing operational costs from 0.398 to 0.228, resulting in a 28.4% improvement in cost-of-pass. Our work provides actionable insights for designing efficient, high-performing agent systems, advancing the accessibility and sustainability of AI-driven solutions.</p> - https://arxiv.org/abs/2508.02694 - Thu, 24 Jul 2025 17:56:51 +0000 + A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code + https://arxiv.org/abs/2508.18106 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keke Lian, Bin Wang, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Jiazheng Quan, Yilu Zhong, Chenhao He, Zichuan Chen, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui Li, Dong Zhang</p><p><b>Upvotes:</b> 342</p><p><b>Summary:</b> The increasing adoption of large language models (LLMs) in software engineering necessitates rigorous security evaluation of their generated code. However, existing benchmarks often lack relevance to real-world AI programming scenarios, making them inadequate for assessing the practical security risks associated with AI-generated code in production environments. To address this gap, we introduce A.S.E (AI Code Generation Security Evaluation), a repository-level evaluation benchmark designed to closely mirror real-world AI programming tasks, offering a comprehensive and reliable framework for assessing the security of AI-generated code. Our evaluation of leading LLMs on A.S.E reveals several key findings. In particular, current LLMs still struggle with secure coding. The complexity in repository-level scenarios presents challenges for LLMs that typically perform well on snippet-level tasks. Morever, a larger reasoning budget does not necessarily lead to better code generation. These observations offer valuable insights into the current state of AI code generation, assisting developers in selecting the most appropriate models for practical tasks, while laying the foundation for refining LLMs to generate secure and efficient code in real-world applications.</p> + https://arxiv.org/abs/2508.18106 + Mon, 25 Aug 2025 15:11:11 +0000 - RecGPT Technical Report - https://arxiv.org/abs/2507.22879 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.22879.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chao Yi, Dian Chen, Gaoyang Guo, Jiakai Tang, Jian Wu, Jing Yu, Sunhao Dai, Wen Chen, Wenjun Yang, Yuning Jiang, Zhujin Gao, Bo Zheng, Chi Li, Dimin Wang, Dixuan Wang, Fan Li, Fan Zhang, Haibin Chen, Haozhuang Liu, Jialin Zhu, Jiamang Wang, Jiawei Wu, Jin Cui, Ju Huang, Kai Zhang, Kan Liu, Lang Tian, Liang Rao, Longbin Li, Lulu Zhao, Mao Zhang, Na He, Peiyang Wang, Qiqi Huang, Tao Luo, Wenbo Su, Xiaoxiao He, Xin Tong, Xu Chen, Xunke Xi, Yang Li, Yaxuan Wu, Yeqiu Yang, Yi Hu, Yinnan Song, Yuchen Li, Yujie Luo, Yujin Yuan, Yuliang Yan, Zhengyang Wang, Zhibo Xiao, Zhixin Ma, Zile Zhou</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most current industrial systems remain heavily reliant on historical co-occurrence patterns and log-fitting objectives, i.e., optimizing for past user interactions without explicitly modeling user intent. This log-fitting approach often leads to overfitting to narrow historical preferences, failing to capture users' evolving and latent interests. As a result, it reinforces filter bubbles and long-tail phenomena, ultimately harming user experience and threatening the sustainability of the whole recommendation ecosystem. To address these challenges, we rethink the overall design paradigm of recommender systems and propose RecGPT, a next-generation framework that places user intent at the center of the recommendation pipeline. By integrating large language models (LLMs) into key stages of user interest mining, item retrieval, and explanation generation, RecGPT transforms log-fitting recommendation into an intent-centric process. To effectively align general-purpose LLMs to the above domain-specific recommendation tasks at scale, RecGPT incorporates a multi-stage training paradigm, which integrates reasoning-enhanced pre-alignment and self-training evolution, guided by a Human-LLM cooperative judge system. Currently, RecGPT has been fully deployed on the Taobao App. Online experiments demonstrate that RecGPT achieves consistent performance gains across stakeholders: users benefit from increased content diversity and satisfaction, merchants and the platform gain greater exposure and conversions. These comprehensive improvement results across all stakeholders validates that LLM-driven, intent-centric design can foster a more sustainable and mutually beneficial recommendation ecosystem.</p> - https://arxiv.org/abs/2507.22879 - Wed, 30 Jul 2025 17:55:06 +0000 + Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation + https://arxiv.org/abs/2508.20470 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20470.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaochuan Li, Guoguang Du, Runze Zhang, Liang Jin, Qi Jia, Lihua Lu, Zhenhua Guo, Yaqian Zhao, Haiyang Liu, Tianqi Wang, Changsheng Li, Xiaoli Gong, Rengang Li, Baoyu Fan</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Scaling laws have validated the success and promise of large-data-trained models in creative generation across text, image, and video domains. However, this paradigm faces data scarcity in the 3D domain, as there is far less of it available on the internet compared to the aforementioned modalities. Fortunately, there exist adequate videos that inherently contain commonsense priors, offering an alternative supervisory signal to mitigate the generalization bottleneck caused by limited native 3D data. On the one hand, videos capturing multiple views of an object or scene provide a spatial consistency prior for 3D generation. On the other hand, the rich semantic information contained within the videos enables the generated content to be more faithful to the text prompts and semantically plausible. This paper explores how to apply the video modality in 3D asset generation, spanning datasets to models. We introduce Droplet3D-4M, the first large-scale video dataset with multi-view level annotations, and train Droplet3D, a generative model supporting both image and dense text input. Extensive experiments validate the effectiveness of our approach, demonstrating its ability to produce spatially consistent and semantically plausible content. Moreover, in contrast to the prevailing 3D solutions, our approach exhibits the potential for extension to scene-level applications. This indicates that the commonsense priors from the videos significantly facilitate 3D creation. We have open-sourced all resources including the dataset, code, technical framework, and model weights: https://dropletx.github.io/.</p> + https://arxiv.org/abs/2508.20470 + Thu, 28 Aug 2025 06:39:41 +0000 - PixNerd: Pixel Neural Field Diffusion - https://arxiv.org/abs/2507.23268 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.23268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuai Wang, Ziteng Gao, Chenhui Zhu, Weilin Huang, Limin Wang</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> The current success of diffusion transformers heavily depends on the compressed latent space shaped by the pre-trained variational autoencoder(VAE). However, this two-stage training paradigm inevitably introduces accumulated errors and decoding artifacts. To address the aforementioned problems, researchers return to pixel space at the cost of complicated cascade pipelines and increased token complexity. In contrast to their efforts, we propose to model the patch-wise decoding with neural field and present a single-scale, single-stage, efficient, end-to-end solution, coined as pixel neural field diffusion~(PixelNerd). Thanks to the efficient neural field representation in PixNerd, we directly achieved 2.15 FID on ImageNet 256times256 and 2.84 FID on ImageNet 512times512 without any complex cascade pipeline or VAE. We also extend our PixNerd framework to text-to-image applications. Our PixNerd-XXL/16 achieved a competitive 0.73 overall score on the GenEval benchmark and 80.9 overall score on the DPG benchmark.</p> - https://arxiv.org/abs/2507.23268 - Thu, 31 Jul 2025 06:07:20 +0000 + EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control + https://arxiv.org/abs/2508.21112 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.21112.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Delin Qu, Haoming Song, Qizhi Chen, Zhaoqing Chen, Xianqiang Gao, Xinyi Ye, Qi Lv, Modi Shi, Guanghui Ren, Cheng Ruan, Maoqing Yao, Haoran Yang, Jiacheng Bao, Bin Zhao, Dong Wang</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> The human ability to seamlessly perform multimodal reasoning and physical interaction in the open world is a core goal for general-purpose embodied intelligent systems. Recent vision-language-action (VLA) models, which are co-trained on large-scale robot and visual-text data, have demonstrated notable progress in general robot control. However, they still fail to achieve human-level flexibility in interleaved reasoning and interaction. In this work, introduce EO-Robotics, consists of EO-1 model and EO-Data1.5M dataset. EO-1 is a unified embodied foundation model that achieves superior performance in multimodal embodied reasoning and robot control through interleaved vision-text-action pre-training. The development of EO-1 is based on two key pillars: (i) a unified architecture that processes multimodal inputs indiscriminately (image, text, video, and action), and (ii) a massive, high-quality multimodal embodied reasoning dataset, EO-Data1.5M, which contains over 1.5 million samples with emphasis on interleaved vision-text-action comprehension. EO-1 is trained through synergies between auto-regressive decoding and flow matching denoising on EO-Data1.5M, enabling seamless robot action generation and multimodal embodied reasoning. Extensive experiments demonstrate the effectiveness of interleaved vision-text-action learning for open-world understanding and generalization, validated through a variety of long-horizon, dexterous manipulation tasks across multiple embodiments. This paper details the architecture of EO-1, the data construction strategy of EO-Data1.5M, and the training methodology, offering valuable insights for developing advanced embodied foundation models.</p> + https://arxiv.org/abs/2508.21112 + Thu, 28 Aug 2025 17:26:15 +0000 - iLRM: An Iterative Large 3D Reconstruction Model - https://arxiv.org/abs/2507.23277 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.23277.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gyeongjin Kang, Seungtae Nam, Xiangyu Sun, Sameh Khamis, Abdelrahman Mohamed, Eunbyung Park</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Feed-forward 3D modeling has emerged as a promising approach for rapid and high-quality 3D reconstruction. In particular, directly generating explicit 3D representations, such as 3D Gaussian splatting, has attracted significant attention due to its fast and high-quality rendering, as well as numerous applications. However, many state-of-the-art methods, primarily based on transformer architectures, suffer from severe scalability issues because they rely on full attention across image tokens from multiple input views, resulting in prohibitive computational costs as the number of views or image resolution increases. Toward a scalable and efficient feed-forward 3D reconstruction, we introduce an iterative Large 3D Reconstruction Model (iLRM) that generates 3D Gaussian representations through an iterative refinement mechanism, guided by three core principles: (1) decoupling the scene representation from input-view images to enable compact 3D representations; (2) decomposing fully-attentional multi-view interactions into a two-stage attention scheme to reduce computational costs; and (3) injecting high-resolution information at every layer to achieve high-fidelity reconstruction. Experimental results on widely used datasets, such as RE10K and DL3DV, demonstrate that iLRM outperforms existing methods in both reconstruction quality and speed. Notably, iLRM exhibits superior scalability, delivering significantly higher reconstruction quality under comparable computational cost by efficiently leveraging a larger number of input views.</p> - https://arxiv.org/abs/2507.23277 - Thu, 31 Jul 2025 06:33:07 +0000 + R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning + https://arxiv.org/abs/2508.21113 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.21113.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Jiang, Qi Yang, Bolin Ni, Shiming Xiang, Han Hu, Houwen Peng</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) equipped with step-by-step thinking capabilities have demonstrated remarkable performance on complex reasoning problems. However, this thinking process is redundant for simple problems solvable without complex reasoning. To address this inefficiency, we propose R-4B, an auto-thinking MLLM, which can adaptively decide when to think based on problem complexity. The central idea of R-4B is to empower the model with both thinking and non-thinking capabilities using bi-mode annealing, and apply Bi-mode Policy Optimization~(BPO) to improve the model's accuracy in determining whether to activate the thinking process. Specifically, we first train the model on a carefully curated dataset spanning various topics, which contains samples from both thinking and non-thinking modes. Then it undergoes a second phase of training under an improved GRPO framework, where the policy model is forced to generate responses from both modes for each input query. Experimental results show that R-4B achieves state-of-the-art performance across 25 challenging benchmarks. It outperforms Qwen2.5-VL-7B in most tasks and achieves performance comparable to larger models such as Kimi-VL-A3B-Thinking-2506 (16B) on reasoning-intensive benchmarks with lower computational cost.</p> + https://arxiv.org/abs/2508.21113 + Thu, 28 Aug 2025 17:48:19 +0000 - Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving - https://arxiv.org/abs/2507.23726 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.23726.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Luoxin Chen, Jinming Gu, Liankai Huang, Wenhao Huang, Zhicheng Jiang, Allan Jie, Xiaoran Jin, Xing Jin, Chenggang Li, Kaijing Ma, Cheng Ren, Jiawei Shen, Wenlei Shi, Tong Sun, He Sun, Jiahui Wang, Siran Wang, Zhihong Wang, Chenrui Wei, Shufa Wei, Yonghui Wu, Yuchen Wu, Yihang Xia, Huajian Xin, Fan Yang, Huaiyuan Ying, Hongyi Yuan, Zheng Yuan, Tianyang Zhan, Chi Zhang, Yue Zhang, Ge Zhang, Tianyun Zhao, Jianqiu Zhao, Yichi Zhou, Thomas Hanwen Zhu</p><p><b>Upvotes:</b> 112</p><p><b>Summary:</b> LLMs have demonstrated strong mathematical reasoning abilities by leveraging reinforcement learning with long chain-of-thought, yet they continue to struggle with theorem proving due to the lack of clear supervision signals when solely using natural language. Dedicated domain-specific languages like Lean provide clear supervision via formal verification of proofs, enabling effective training through reinforcement learning. In this work, we propose Seed-Prover, a lemma-style whole-proof reasoning model. Seed-Prover can iteratively refine its proof based on Lean feedback, proved lemmas, and self-summarization. To solve IMO-level contest problems, we design three test-time inference strategies that enable both deep and broad reasoning. Seed-Prover proves 78.1% of formalized past IMO problems, saturates MiniF2F, and achieves over 50\% on PutnamBench, outperforming the previous state-of-the-art by a large margin. To address the lack of geometry support in Lean, we introduce a geometry reasoning engine Seed-Geometry, which outperforms previous formal geometry engines. We use these two systems to participate in IMO 2025 and fully prove 5 out of 6 problems. This work represents a significant advancement in automated mathematical reasoning, demonstrating the effectiveness of formal verification with long chain-of-thought reasoning.</p> - https://arxiv.org/abs/2507.23726 - Thu, 31 Jul 2025 17:00:30 +0000 + A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers + https://arxiv.org/abs/2508.21148 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.21148.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Hu, Chenglong Ma, Wei Li, Wanghan Xu, Jiamin Wu, Jucheng Hu, Tianbin Li, Guohang Zhuang, Jiaqi Liu, Yingzhou Lu, Ying Chen, Chaoyang Zhang, Cheng Tan, Jie Ying, Guocheng Wu, Shujian Gao, Pengcheng Chen, Jiashi Lin, Haitao Wu, Lulu Chen, Fengxiang Wang, Yuanyuan Zhang, Xiangyu Zhao, Feilong Tang, Encheng Su, Junzhi Ning, Xinyao Liu, Ye Du, Changkai Ji, Cheng Tang, Huihui Xu, Ziyang Chen, Ziyan Huang, Jiyao Liu, Pengfei Jiang, Yizhou Wang, Chen Tang, Jianyu Wu, Yuchen Ren, Siyuan Yan, Zhonghua Wang, Zhongxing Xu, Shiyan Su, Shangquan Sun, Runkai Zhao, Zhisheng Zhang, Yu Liu, Fudi Wang, Yuanfeng Ji, Yanzhou Su, Hongming Shan, Chunmei Feng, Jiahao Xu, Jiangtao Yan, Wenhao Tang, Diping Song, Lihao Liu, Yanyan Huang, Lequan Yu, Bin Fu, Shujun Wang, Xiaomeng Li, Xiaowei Hu, Yun Gu, Ben Fei, Zhongying Deng, Benyou Wang, Yuewen Cao, Minjie Shen, Haodong Duan, Jie Xu, Yirong Chen, Fang Yan, Hongxia Hao, Jielan Li, Jiajun Du, Yanbo Wang, Imran Razzak, Chi Zhang, Lijun Wu, Conghui He, Zhaohui Lu, Jinhai Huang, Yihao Liu, Fenghua Ling, Yuqiang Li, Aoran Wang, Qihao Zheng, Nanqing Dong, Tianfan Fu, Dongzhan Zhou, Yan Lu, Wenlong Zhang, Jin Ye, Jianfei Cai, Wanli Ouyang, Yu Qiao, Zongyuan Ge, Shixiang Tang, Junjun He, Chunfeng Song, Lei Bai, Bowen Zhou</p><p><b>Upvotes:</b> 141</p><p><b>Summary:</b> Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate. We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge, emphasizing the multimodal, cross-scale, and domain-specific challenges that differentiate scientific corpora from general natural language processing datasets. We systematically review recent Sci-LLMs, from general-purpose foundations to specialized models across diverse scientific disciplines, alongside an extensive analysis of over 270 pre-/post-training datasets, showing why Sci-LLMs pose distinct demands -- heterogeneous, multi-scale, uncertainty-laden corpora that require representations preserving domain invariance and enabling cross-modal reasoning. On evaluation, we examine over 190 benchmark datasets and trace a shift from static exams toward process- and discovery-oriented assessments with advanced evaluation protocols. These data-centric analyses highlight persistent issues in scientific data development and discuss emerging solutions involving semi-automated annotation pipelines and expert validation. Finally, we outline a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base. Collectively, this work provides a roadmap for building trustworthy, continually evolving artificial intelligence (AI) systems that function as a true partner in accelerating scientific discovery.</p> + https://arxiv.org/abs/2508.21148 + Thu, 28 Aug 2025 18:30:52 +0000 - Phi-Ground Tech Report: Advancing Perception in GUI Grounding - https://arxiv.org/abs/2507.23779 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.23779.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Miaosen Zhang, Ziqiang Xu, Jialiang Zhu, Qi Dai, Kai Qiu, Yifan Yang, Chong Luo, Tianyi Chen, Justin Wagle, Tim Franklin, Baining Guo</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> With the development of multimodal reasoning models, Computer Use Agents (CUAs), akin to Jarvis from "Iron Man", are becoming a reality. GUI grounding is a core component for CUAs to execute actual actions, similar to mechanical control in robotics, and it directly leads to the success or failure of the system. It determines actions such as clicking and typing, as well as related parameters like the coordinates for clicks. Current end-to-end grounding models still achieve less than 65\% accuracy on challenging benchmarks like ScreenSpot-pro and UI-Vision, indicating they are far from being ready for deployment. % , as a single misclick can result in unacceptable consequences. In this work, we conduct an empirical study on the training of grounding models, examining details from data collection to model training. Ultimately, we developed the Phi-Ground model family, which achieves state-of-the-art performance across all five grounding benchmarks for models under 10B parameters in agent settings. In the end-to-end model setting, our model still achieves SOTA results with scores of \textbf{43.2} on ScreenSpot-pro and \textbf{27.2} on UI-Vision. We believe that the various details discussed in this paper, along with our successes and failures, not only clarify the construction of grounding models but also benefit other perception tasks. Project homepage: https://zhangmiaosen2000.github.io/Phi-Ground/{https://zhangmiaosen2000.github.io/Phi-Ground/}</p> - https://arxiv.org/abs/2507.23779 - Thu, 31 Jul 2025 17:59:09 +0000 + Open Data Synthesis For Deep Research + https://arxiv.org/abs/2509.00375 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.00375.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyi Xia, Kun Luo, Hongjin Qian, Zheng Liu</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Large language models (LLMs) are increasingly expected to go beyond simple factual queries toward Deep Research-tasks that require decomposing questions into sub-problems, coordinating multi-step reasoning, and synthesizing evidence from diverse sources. We formalize Deep Research tasks with verifiable answers as Hierarchical Constraint Satisfaction Problems (HCSPs), which are fundamentally different from single-constraint, multi-hop, or flat CSP formulations. However, existing benchmarks (e.g., Natural Questions, HotpotQA) fail to capture this complexity, while recent synthetic datasets often introduce shortcut reasoning, knowledge leakage, or lack sufficient structural depth. To address this gap, we introduce InfoSeek, a scalable framework for synthesizing complex Deep Research tasks. InfoSeek uses a dual-agent system to recursively build a Research Tree from large-scale webpages, blurring intermediate nodes into valid sub-problems, and converting these trees into natural language questions that require traversing the full hierarchy. It also enables rapid scaling, yielding over 50K training examples, a curated test set, and reasoning trajectories generated via reject sampling. Experiments show that models trained on InfoSeek consistently outperform strong baselines. On a challenging benchmark BrowseComp-Plus, 3B LLMs optimized with InfoSeek surpass much larger 32B models and lightweight commercial APIs (e.g., Gemini2.5-Flash), while achieving performance comparable to stronger APIs (e.g., Gemini2.5-Pro). By preserving meta-information such as intermediate steps and retrieval labels, InfoSeek further supports advanced optimization strategies, including compound reward design and trajectory-level exploration. We provide our codes and datasets in https://github.com/VectorSpaceLab/InfoSeek{this repository}.</p> + https://arxiv.org/abs/2509.00375 + Sat, 30 Aug 2025 06:02:56 +0000 - Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training - https://arxiv.org/abs/2508.00414 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.00414.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianqing Fang, Zhisong Zhang, Xiaoyang Wang, Rui Wang, Can Qin, Yuxuan Wan, Jun-Yu Ma, Ce Zhang, Jiaqi Chen, Xiyun Li, Hongming Zhang, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 89</p><p><b>Summary:</b> General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence, enabling complex reasoning, web interaction, coding, and autonomous research capabilities. However, current agent systems are either closed-source or heavily reliant on a variety of paid APIs and proprietary tools, limiting accessibility and reproducibility for the research community. In this work, we present Cognitive Kernel-Pro, a fully open-source and (to the maximum extent) free multi-module agent framework designed to democratize the development and evaluation of advanced AI agents. Within Cognitive Kernel-Pro, we systematically investigate the curation of high-quality training data for Agent Foundation Models, focusing on the construction of queries, trajectories, and verifiable answers across four key domains: web, file, code, and general reasoning. Furthermore, we explore novel strategies for agent test-time reflection and voting to enhance agent robustness and performance. We evaluate Cognitive Kernel-Pro on GAIA, achieving state-of-the-art results among open-source and free agents. Notably, our 8B-parameter open-source model surpasses previous leading systems such as WebDancer and WebSailor, establishing a new performance standard for accessible, high-capability AI agents. Code is available at https://github.com/Tencent/CognitiveKernel-Pro</p> - https://arxiv.org/abs/2508.00414 - Fri, 01 Aug 2025 08:11:31 +0000 + Gated Associative Memory: A Parallel O(N) Architecture for Efficient Sequence Modeling + https://arxiv.org/abs/2509.00605 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.00605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rishiraj Acharya</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> The Transformer architecture, underpinned by the self-attention mechanism, has become the de facto standard for sequence modeling tasks. However, its core computational primitive scales quadratically with sequence length (O(N^2)), creating a significant bottleneck for processing long contexts. In this paper, we propose the Gated Associative Memory (GAM) network, a novel, fully parallel architecture for sequence modeling that exhibits linear complexity (O(N)) with respect to sequence length. The GAM block replaces the self-attention layer with two parallel pathways: a causal convolution to efficiently capture local, position-dependent context, and a parallel associative memory retrieval mechanism to model global, content-based patterns. These pathways are dynamically fused using a gating mechanism, allowing the model to flexibly combine local and global information for each token. We implement GAM from scratch and conduct a rigorous comparative analysis against a standard Transformer model and a modern linear-time baseline (Mamba) on the WikiText-2 benchmark, as well as against the Transformer on the TinyStories dataset. Our experiments demonstrate that GAM is consistently faster, outperforming both baselines on training speed, and achieves a superior or competitive final validation perplexity across all datasets, establishing it as a promising and efficient alternative for sequence modeling.</p> + https://arxiv.org/abs/2509.00605 + Sat, 30 Aug 2025 20:59:46 +0000 - Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models - https://arxiv.org/abs/2508.00819 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.00819.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinsong Li, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jiaqi Wang, Dahua Lin</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Diffusion Large Language Models (DLLMs) are emerging as a powerful alternative to the dominant Autoregressive Large Language Models, offering efficient parallel generation and capable global context modeling. However, the practical application of DLLMs is hindered by a critical architectural constraint: the need for a statically predefined generation length. This static length allocation leads to a problematic trade-off: insufficient lengths cripple performance on complex tasks, while excessive lengths incur significant computational overhead and sometimes result in performance degradation. While the inference framework is rigid, we observe that the model itself possesses internal signals that correlate with the optimal response length for a given task. To bridge this gap, we leverage these latent signals and introduce DAEDAL, a novel training-free denoising strategy that enables Dynamic Adaptive Length Expansion for Diffusion Large Language Models. DAEDAL operates in two phases: 1) Before the denoising process, DAEDAL starts from a short initial length and iteratively expands it to a coarse task-appropriate length, guided by a sequence completion metric. 2) During the denoising process, DAEDAL dynamically intervenes by pinpointing and expanding insufficient generation regions through mask token insertion, ensuring the final output is fully developed. Extensive experiments on DLLMs demonstrate that DAEDAL achieves performance comparable, and in some cases superior, to meticulously tuned fixed-length baselines, while simultaneously enhancing computational efficiency by achieving a higher effective token ratio. By resolving the static length constraint, DAEDAL unlocks new potential for DLLMs, bridging a critical gap with their Autoregressive counterparts and paving the way for more efficient and capable generation.</p> - https://arxiv.org/abs/2508.00819 - Fri, 01 Aug 2025 17:56:07 +0000 + LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model + https://arxiv.org/abs/2509.00676 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.00676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiyao Wang, Chunyuan Li, Jianwei Yang, Kai Zhang, Bo Liu, Tianyi Xiong, Furong Huang</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> In vision-language modeling, critic models are typically trained to evaluate outputs -- assigning scalar scores or pairwise preferences -- rather than to generate responses. This separation from policy models, which produce the responses, is so entrenched that critics are rarely considered for direct policy use. In this work, we challenge this convention. We propose to reorganize preference-labeled critic datasets into verifiable training signals and perform reinforcement learning directly on a base generative model, producing LLaVA-Critic-R1, a multimodal critic trained to optimize preference judgments while retaining full generation ability. Surprisingly, LLaVA-Critic-R1 emerges not only as a top-performing critic but also as a competitive policy model -- matching or surpassing specialized reasoning VLMs trained with in-domain data across 26 visual reasoning and understanding benchmarks, with an average gain of +5.7% over its base model (Qwen-2.5-VL-7B). Extending this approach to existing strong reasoning VLMs yields LLaVA-Critic-R1+, which further advances policy performance without sacrificing critic quality, achieving a SoTA performance of 71.9 on MMMU at the 7B scale. Finally, we show that the enhanced critic ability benefits inference: applying self-critique at test time yields an average +13.8% improvement on five representative reasoning tasks without additional training. Our results reveal that RL training on critic data can produce a unified model excelling at both evaluation and generation, offering a simple path toward scalable, self-improving multimodal systems.</p> + https://arxiv.org/abs/2509.00676 + Sun, 31 Aug 2025 03:08:02 +0000 - Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report - https://arxiv.org/abs/2508.01059 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.01059.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sajana Weerawardhena, Paul Kassianik, Blaine Nelson, Baturay Saglam, Anu Vellore, Aman Priyanshu, Supriti Vijay, Massimo Aufiero, Arthur Goldblatt, Fraser Burch, Ed Li, Jianliang He, Dhruv Kedia, Kojin Oshiba, Zhouran Yang, Yaron Singer, Amin Karbasi</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Large language models (LLMs) have shown remarkable success across many domains, yet their integration into cybersecurity applications remains limited due to a lack of general-purpose cybersecurity data, representational complexity, and safety and regulatory concerns. To address this gap, we previously introduced Foundation-Sec-8B, a cybersecurity-focused LLM suitable for fine-tuning on downstream tasks. That model, however, was not designed for chat-style interactions or instruction-following. In this report, we release Foundation-Sec-8B-Instruct: a model specifically trained for general-purpose cybersecurity dialogue. Built on Foundation-Sec-8B, it combines domain-specific knowledge with instruction-following, conversational capabilities, and alignment with human preferences to produce high-quality, relevant responses. Comprehensive evaluations show that Foundation-Sec-8B-Instruct outperforms Llama 3.1-8B-Instruct on a range of cybersecurity tasks while matching its instruction-following performance. It is also competitive with GPT-4o-mini on cyber threat intelligence and instruction-following tasks. We envision Foundation-Sec-8B-Instruct becoming an indispensable assistant in the daily workflows of cybersecurity professionals. We release the model publicly at https://huggingface.co/fdtn-ai/Foundation-Sec-8B-Instruct.</p> - https://arxiv.org/abs/2508.01059 - Fri, 01 Aug 2025 20:25:57 +0000 + VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use + https://arxiv.org/abs/2509.01055 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongfu Jiang, Yi Lu, Zhuofeng Li, Zhiheng Lyu, Ping Nie, Haozhe Wang, Alex Su, Hui Chen, Kai Zou, Chao Du, Tianyu Pang, Wenhu Chen</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated success in enhancing LLM reasoning capabilities, but remains limited to single-turn interactions without tool integration. While recent Agentic Reinforcement Learning with Tool use (ARLT) approaches have emerged to address multi-turn tool interactions, existing works develop task-specific codebases that suffer from fragmentation, synchronous execution bottlenecks, and limited extensibility across domains. These inefficiencies hinder broader community adoption and algorithmic innovation. We introduce VerlTool, a unified and modular framework that addresses these limitations through systematic design principles. VerlTool provides four key contributions: (1) upstream alignment with VeRL ensuring compatibility and simplified maintenance, (2) unified tool management via standardized APIs supporting diverse modalities including code execution, search, SQL databases, and vision processing, (3) asynchronous rollout execution achieving near 2times speedup by eliminating synchronization bottlenecks, and (4) comprehensive evaluation demonstrating competitive performance across 6 ARLT domains. Our framework formalizes ARLT as multi-turn trajectories with multi-modal observation tokens (text/image/video), extending beyond single-turn RLVR paradigms. We train and evaluate models on mathematical reasoning, knowledge QA, SQL generation, visual reasoning, web search, and software engineering tasks, achieving results comparable to specialized systems while providing unified training infrastructure. The modular plugin architecture enables rapid tool integration requiring only lightweight Python definitions, significantly reducing development overhead and providing a scalable foundation for tool-augmented RL research. Our code is open-sourced at https://github.com/TIGER-AI-Lab/verl-tool.</p> + https://arxiv.org/abs/2509.01055 + Mon, 01 Sep 2025 01:45:18 +0000 - Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens - https://arxiv.org/abs/2508.01191 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.01191.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengshuai Zhao, Zhen Tan, Pingchuan Ma, Dawei Li, Bohan Jiang, Yancheng Wang, Yingzhen Yang, Huan Liu</p><p><b>Upvotes:</b> 228</p><p><b>Summary:</b> Chain-of-Thought (CoT) prompting has been shown to improve Large Language Model (LLM) performance on various tasks. With this approach, LLMs appear to produce human-like reasoning steps before providing answers (a.k.a., CoT reasoning), which often leads to the perception that they engage in deliberate inferential processes. However, some initial findings suggest that CoT reasoning may be more superficial than it appears, motivating us to explore further. In this paper, we study CoT reasoning via a data distribution lens and investigate if CoT reasoning reflects a structured inductive bias learned from in-distribution data, allowing the model to conditionally generate reasoning paths that approximate those seen during training. Thus, its effectiveness is fundamentally bounded by the degree of distribution discrepancy between the training data and the test queries. With this lens, we dissect CoT reasoning via three dimensions: task, length, and format. To investigate each dimension, we design DataAlchemy, an isolated and controlled environment to train LLMs from scratch and systematically probe them under various distribution conditions. Our results reveal that CoT reasoning is a brittle mirage that vanishes when it is pushed beyond training distributions. This work offers a deeper understanding of why and when CoT reasoning fails, emphasizing the ongoing challenge of achieving genuine and generalizable reasoning.</p> - https://arxiv.org/abs/2508.01191 - Sat, 02 Aug 2025 04:37:28 +0000 + Robix: A Unified Model for Robot Interaction, Reasoning and Planning + https://arxiv.org/abs/2509.01106 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huang Fang, Mengxi Zhang, Heng Dong, Wei Li, Zixuan Wang, Qifeng Zhang, Xueyun Tian, Yucheng Hu, Hang Li</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture. Acting as the high-level cognitive layer in a hierarchical robot system, Robix dynamically generates atomic commands for the low-level controller and verbal responses for human interaction, enabling robots to follow complex instructions, plan long-horizon tasks, and interact naturally with human within an end-to-end framework. Robix further introduces novel capabilities such as proactive dialogue, real-time interruption handling, and context-aware commonsense reasoning during task execution. At its core, Robix leverages chain-of-thought reasoning and adopts a three-stage training strategy: (1) continued pretraining to enhance foundational embodied reasoning abilities including 3D spatial understanding, visual grounding, and task-centric reasoning; (2) supervised finetuning to model human-robot interaction and task planning as a unified reasoning-action sequence; and (3) reinforcement learning to improve reasoning-action consistency and long-horizon task coherence. Extensive experiments demonstrate that Robix outperforms both open-source and commercial baselines (e.g., GPT-4o and Gemini 2.5 Pro) in interactive task execution, demonstrating strong generalization across diverse instruction types (e.g., open-ended, multi-stage, constrained, invalid, and interrupted) and various user-involved tasks such as table bussing, grocery shopping, and dietary filtering.</p> + https://arxiv.org/abs/2509.01106 + Mon, 01 Sep 2025 03:53:47 +0000 - SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension - https://arxiv.org/abs/2508.01959 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.01959.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Wu, Jiangnan Li, Yuqing Li, Lemao Liu, Liyan Xu, Jiwei Li, Dit-Yan Yeung, Jie Zhou, Mo Yu</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to dependencies across the original document, contextual information is often essential for accurately interpreting each chunk. To address this, prior work has explored encoding longer context windows to produce embeddings for longer chunks. Despite these efforts, gains in retrieval and downstream tasks remain limited. This is because (1) longer chunks strain the capacity of embedding models due to the increased amount of information they must encode, and (2) many real-world applications still require returning localized evidence due to constraints on model or human bandwidth. We propose an alternative approach to this challenge by representing short chunks in a way that is conditioned on a broader context window to enhance retrieval performance -- i.e., situating a chunk's meaning within its context. We further show that existing embedding models are not well-equipped to encode such situated context effectively, and thus introduce a new training paradigm and develop the situated embedding models (SitEmb). To evaluate our method, we curate a book-plot retrieval dataset specifically designed to assess situated retrieval capabilities. On this benchmark, our SitEmb-v1 model based on BGE-M3 substantially outperforms state-of-the-art embedding models, including several with up to 7-8B parameters, with only 1B parameters. Our 8B SitEmb-v1.5 model further improves performance by over 10% and shows strong results across different languages and several downstream applications.</p> - https://arxiv.org/abs/2508.01959 - Sun, 03 Aug 2025 23:59:31 +0000 + POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion + https://arxiv.org/abs/2509.01215 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01215.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan Liu, Zhongyin Zhao, Le Tian, Haicheng Wang, Xubing Ye, Yangxiu You, Zilin Yu, Chuhan Wu, Xiao Zhou, Yang Yu, Jie Zhou</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> High-quality labeled data is essential for training accurate document conversion models, particularly in domains with complex formats such as tables, formulas, and multi-column text. However, manual annotation is both costly and time-consuming, while automatic labeling using existing models often lacks accuracy in handling such challenging scenarios. Consequently, training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications. In this paper, we propose a fully automated, distillation-free framework comprising two stages for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts. In the first stage, we introduce a method for generating large-scale, diverse synthetic data, which enables a model to extract key elements in a unified format with strong initial performance. In the second stage, we present a self-improvement approach that further adapts the model, initially trained on synthetic data, to real-world documents. Specifically, we first use the fine-tuned model to annotate real documents, then apply a suite of filtering strategies to verify annotation quality, and finally retrain the model on the verified dataset. By iteratively repeating this process, we progressively enhance both the model's conversion capabilities and the quality of the generated data. We train a public POINTS-1.5 model to obtain POINTS-Reader, which surpasses many existing public and proprietary models of comparable or larger size. Our model is available at https://github.com/Tencent/POINTS-Reader.</p> + https://arxiv.org/abs/2509.01215 + Mon, 01 Sep 2025 07:54:18 +0000 - Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following - https://arxiv.org/abs/2508.02150 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.02150.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyu Ren, Qianyu He, Bowei Zhang, Jie Zeng, Jiaqing Liang, Yanghua Xiao, Weikang Zhou, Zeye Sun, Fei Yu</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Reasoning models excel in complex problem solving but exhibit a concerning trade off between reasoning capabilities and instruction following abilities. Existing approaches for improving instruction following rely on stronger external models, creating methodological bottlenecks and practical limitations including increased costs and accessibility constraints. We propose a self-supervised RL framework that leverages reasoning models' own internal signals to improve instruction following capabilities without external supervision. Extensive experiments demonstrate that our framework significantly improves instruction following capabilities while maintaining reasoning performance, offering a scalable and cost-effective approach to enhance instruction following in reasoning models. The data and code are publicly available at https://github.com/Rainier-rq/verl-if.</p> - https://arxiv.org/abs/2508.02150 - Mon, 04 Aug 2025 07:48:59 +0000 + Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic + https://arxiv.org/abs/2509.01363 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammad Zbeeb, Hasan Abed Al Kader Hammoud, Bernard Ghanem</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Large language models often require costly optimization, such as reinforcement learning, to master complex reasoning tasks. This work demonstrates that reasoning ability, once learned, can be extracted and transferred between models as a compact task vector. We source two publicly available, identically initialized Qwen2.5 models, one fine-tuned with supervised fine-tuning (SFT) and the other with group relative policy optimization (GRPO) on the same dataset. From these, we extract a reasoning vector: v_{reason} = theta_{GRPO} - theta_{SFT}. We hypothesize that this vector captures the reasoning capability instilled by reinforcement learning while factoring out shared knowledge from the SFT process. When added to compatible instruction-tuned models through simple arithmetic, this vector consistently improves performance across diverse reasoning benchmarks: GSM8K (+4.9%), HumanEval (+4.3%), SciQ (+1.7%), and BigBenchHard (+12.3% for the 1.5B model). The performance improvements persist under adversarial conditions. Conversely, subtracting the vector causes significant performance degradation (-11.8% on GSM8K), demonstrating the vector's strong contribution to the model's reasoning abilities. This work shows how reasoning capabilities, typically developed through expensive training, can be extracted from existing open-source models and reused through simple tensor arithmetic, offering a practical way to enhance models by recycling prior computational investments.</p> + https://arxiv.org/abs/2509.01363 + Mon, 01 Sep 2025 11:04:51 +0000 - Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference - https://arxiv.org/abs/2508.02193 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.02193.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxuan Song, Zheng Zhang, Cheng Luo, Pengyang Gao, Fan Xia, Hao Luo, Zheng Li, Yuehang Yang, Hongli Yu, Xingwei Qu, Yuwei Fu, Jing Su, Ge Zhang, Wenhao Huang, Mingxuan Wang, Lin Yan, Xiaoying Jia, Jingjing Liu, Wei-Ying Ma, Ya-Qin Zhang, Yonghui Wu, Hao Zhou</p><p><b>Upvotes:</b> 128</p><p><b>Summary:</b> We present Seed Diffusion Preview, a large-scale language model based on discrete-state diffusion, offering remarkably fast inference speed. Thanks to non-sequential, parallel generation, discrete diffusion models provide a notable speedup to mitigate the inherent latency of token-by-token decoding, as demonstrated recently (e.g., Mercury Coder, Gemini Diffusion). Seed Diffusion Preview achieves an inference speed of 2,146 token/s over H20 GPUs while maintaining competitive performance across a sweep of standard code evaluation benchmarks, significantly faster than contemporary Mercury and Gemini Diffusion, establishing new state of the art on the speed-quality Pareto frontier for code models.</p> - https://arxiv.org/abs/2508.02193 - Mon, 04 Aug 2025 08:43:01 +0000 + DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks + https://arxiv.org/abs/2509.01396 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01396.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiyuan Wan, Chen Yang, Junchi Yu, Meiqi Tu, Jiaxuan Lu, Di Yu, Jianbao Cao, Ben Gao, Jiaqing Xie, Aoran Wang, Wenlong Zhang, Philip Torr, Dongzhan Zhou</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Deep research agents have attracted growing attention for their potential to orchestrate multi-stage research workflows, spanning literature synthesis, methodological design, and empirical verification. Despite these strides, evaluating their research capability faithfully is rather challenging due to the difficulty of collecting frontier research questions that genuinely capture researchers' attention and intellectual curiosity. To address this gap, we introduce DeepResearch Arena, a benchmark grounded in academic seminars that capture rich expert discourse and interaction, better reflecting real-world research environments and reducing the risk of data leakage. To automatically construct DeepResearch Arena, we propose a Multi-Agent Hierarchical Task Generation (MAHTG) system that extracts research-worthy inspirations from seminar transcripts. The MAHTG system further translates research-worthy inspirations into high-quality research tasks, ensuring the traceability of research task formulation while filtering noise. With the MAHTG system, we curate DeepResearch Arena with over 10,000 high-quality research tasks from over 200 academic seminars, spanning 12 disciplines, such as literature, history, and science. Our extensive evaluation shows that DeepResearch Arena presents substantial challenges for current state-of-the-art agents, with clear performance gaps observed across different models.</p> + https://arxiv.org/abs/2509.01396 + Mon, 01 Sep 2025 11:42:47 +0000 - CellForge: Agentic Design of Virtual Cell Models - https://arxiv.org/abs/2508.02276 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.02276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangru Tang, Zhuoyun Yu, Jiapeng Chen, Yan Cui, Daniel Shao, Weixu Wang, Fang Wu, Yuchen Zhuang, Wenqi Shi, Zhi Huang, Arman Cohan, Xihong Lin, Fabian Theis, Smita Krishnaswamy, Mark Gerstein</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Virtual cell modeling represents an emerging frontier at the intersection of artificial intelligence and biology, aiming to predict quantities such as responses to diverse perturbations quantitatively. However, autonomously building computational models for virtual cells is challenging due to the complexity of biological systems, the heterogeneity of data modalities, and the need for domain-specific expertise across multiple disciplines. Here, we introduce CellForge, an agentic system that leverages a multi-agent framework that transforms presented biological datasets and research objectives directly into optimized computational models for virtual cells. More specifically, given only raw single-cell multi-omics data and task descriptions as input, CellForge outputs both an optimized model architecture and executable code for training virtual cell models and inference. The framework integrates three core modules: Task Analysis for presented dataset characterization and relevant literature retrieval, Method Design, where specialized agents collaboratively develop optimized modeling strategies, and Experiment Execution for automated generation of code. The agents in the Design module are separated into experts with differing perspectives and a central moderator, and have to collaboratively exchange solutions until they achieve a reasonable consensus. We demonstrate CellForge's capabilities in single-cell perturbation prediction, using six diverse datasets that encompass gene knockouts, drug treatments, and cytokine stimulations across multiple modalities. CellForge consistently outperforms task-specific state-of-the-art methods. Overall, CellForge demonstrates how iterative interaction between LLM agents with differing perspectives provides better solutions than directly addressing a modeling challenge. Our code is publicly available at https://github.com/gersteinlab/CellForge.</p> - https://arxiv.org/abs/2508.02276 - Mon, 04 Aug 2025 10:43:31 +0000 + Kwai Keye-VL 1.5 Technical Report + https://arxiv.org/abs/2509.01563 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01563.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Biao Yang, Bin Wen, Boyang Ding, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, Fan Yang, Guorui Zhou, Guowang Zhang, Han Shen, Hao Peng, Haojie Ding, Hao Wang, Hengrui Ju, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jingyun Hua, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Muhao Wei, Qiang Wang, Ruitao Wang, Sen Na, Shengnan Zhang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xingyu Lu, Yi-Fan Zhang, Yiping Yang, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhixin Ling, Zhuoran Yang, Ziming Li, Di Xu, Haixuan Gao, Hang Li, Jing Wang, Lejian Ren, Qigen Hu, Qianqian Wang, Shiyao Wang, Xinchen Luo, Yan Li, Yuhang Hu, Zixing Zhang</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a challenging area due to the dynamic and information-dense nature of videos. Existing models struggle with the trade-off between spatial resolution and temporal coverage when processing video content. We present Keye-VL-1.5, which addresses fundamental challenges in video comprehension through three key innovations. First, we introduce a novel Slow-Fast video encoding strategy that dynamically allocates computational resources based on inter-frame similarity, processing key frames with significant visual changes at higher resolution (Slow pathway) while handling relatively static frames with increased temporal coverage at lower resolution (Fast pathway). Second, we implement a progressive four-stage pre-training methodology that systematically extends the model's context length from 8K to 128K tokens, enabling processing of longer videos and more complex visual content. Third, we develop a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment, incorporating a 5-step chain-of-thought data construction process, iterative GSPO-based reinforcement learning with progressive prompt hinting for difficult cases, and alignment training. Through extensive evaluation on public benchmarks and rigorous internal human assessment, Keye-VL-1.5 demonstrates significant improvements over existing models, particularly excelling in video understanding tasks while maintaining competitive performance on general multimodal benchmarks.</p> + https://arxiv.org/abs/2509.01563 + Mon, 01 Sep 2025 15:46:58 +0000 - Qwen-Image Technical Report - https://arxiv.org/abs/2508.02324 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.02324.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng-ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhengyi Wang, An Yang, Bowen Yu, Chen Cheng, Dayiheng Liu, Deqing Li, Hang Zhang, Hao Meng, Hu Wei, Jingyuan Ni, Kai Chen, Kuan Cao, Liang Peng, Lin Qu, Minggang Wu, Peng Wang, Shuting Yu, Tingkun Wen, Wensen Feng, Xiaoxiao Xu, Yi Wang, Yichang Zhang, Yongqiang Zhu, Yujia Wu, Yuxuan Cai, Zenan Liu</p><p><b>Upvotes:</b> 239</p><p><b>Summary:</b> We present Qwen-Image, an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing. To address the challenges of complex text rendering, we design a comprehensive data pipeline that includes large-scale data collection, filtering, annotation, synthesis, and balancing. Moreover, we adopt a progressive training strategy that starts with non-text-to-text rendering, evolves from simple to complex textual inputs, and gradually scales up to paragraph-level descriptions. This curriculum learning approach substantially enhances the model's native text rendering capabilities. As a result, Qwen-Image not only performs exceptionally well in alphabetic languages such as English, but also achieves remarkable progress on more challenging logographic languages like Chinese. To enhance image editing consistency, we introduce an improved multi-task training paradigm that incorporates not only traditional text-to-image (T2I) and text-image-to-image (TI2I) tasks but also image-to-image (I2I) reconstruction, effectively aligning the latent representations between Qwen2.5-VL and MMDiT. Furthermore, we separately feed the original image into Qwen2.5-VL and the VAE encoder to obtain semantic and reconstructive representations, respectively. This dual-encoding mechanism enables the editing module to strike a balance between preserving semantic consistency and maintaining visual fidelity. Qwen-Image achieves state-of-the-art performance, demonstrating its strong capabilities in both image generation and editing across multiple benchmarks.</p> - https://arxiv.org/abs/2508.02324 - Mon, 04 Aug 2025 11:49:20 +0000 + OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning + https://arxiv.org/abs/2509.01644 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.01644.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanqing Liu, Xianhang Li, Letian Zhang, Zirui Wang, Zeyu Zheng, Yuyin Zhou, Cihang Xie</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> This paper provides a simplification on OpenVision's architecture and loss design for enhancing its training efficiency. Following the prior vision-language pretraining works CapPa and AIMv2, as well as modern multimodal designs like LLaVA, our changes are straightforward: we remove the text encoder (and therefore the contrastive loss), retaining only the captioning loss as a purely generative training signal. We name this new version OpenVision 2. The initial results are promising: despite this simplification, OpenVision 2 competitively matches the original model's performance on a broad set of multimodal benchmarks while substantially cutting both training time and memory consumption. For example, with ViT-L/14, it reduces training time by about 1.5x (from 83h to 57h), and memory usage by about 1.8x (from 24.5GB to 13.8GB, equivalently allowing the maximum batch size to grow from 2k to 8k). This superior training efficiency also allows us to scale far beyond the largest vision encoder used in OpenVision, reaching more than 1 billion parameters. We hold a strong belief that this lightweight, generative-only paradigm is compelling for future vision encoder development in multimodal foundation models.</p> + https://arxiv.org/abs/2509.01644 + Mon, 01 Sep 2025 17:38:21 +0000 - Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation - https://arxiv.org/abs/2508.03320 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.03320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peiyu Wang, Yi Peng, Yimeng Gan, Liang Hu, Tianyidan Xie, Xiaokun Wang, Yichen Wei, Chuanxin Tang, Bo Zhu, Changshi Li, Hongyang Wei, Eric Li, Xuchen Song, Yang Liu, Yahui Zhou</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> We introduce Skywork UniPic, a 1.5 billion-parameter autoregressive model that unifies image understanding, text-to-image generation, and image editing within a single architecture-eliminating the need for task-specific adapters or inter-module connectors-and demonstrate that compact multimodal systems can achieve state-of-the-art performance on commodity hardware. Skywork UniPic achieves a GenEval score of 0.86, surpassing most existing unified models; sets a new DPG-Bench complex-generation record of 85.5; attains 5.83 on GEditBench-EN and 3.49 on ImgEdit-Bench for image editing; and generates 1024 x 1024 images with under 15 GB of GPU memory (e.g., RTX 4090). (1) a decoupled encoding strategy that leverages a masked autoregressive encoder for synthesis and a SigLIP2 encoder for understanding, all feeding a shared autoregressive decoder; (2) a progressive, resolution-aware training schedule scaling from 256 x 256 to 1024 x 1024 while dynamically unfreezing parameters to balance capacity and stability; and (3) meticulously curated, 100 million-scale datasets augmented with task-specific reward models to refine generation and editing objectives. By demonstrating that high-fidelity multimodal integration need not incur prohibitive resource demands, Skywork UniPic establishes a practical paradigm for deployable, high-fidelity multimodal AI. Code and weights are publicly available at https://huggingface.co/Skywork/Skywork-UniPic-1.5B.</p> - https://arxiv.org/abs/2508.03320 - Tue, 05 Aug 2025 10:59:01 +0000 + Baichuan-M2: Scaling Medical Capability with Large Verifier System + https://arxiv.org/abs/2509.02208 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baichuan-M2 Team, Chengfeng Dou, Chong Liu, Fan Yang, Fei Li, Jiyuan Jia, Mingyang Chen, Qiang Ju, Shuai Wang, Shunya Dang, Tianpeng Li, Xiangrong Zeng, Yijie Zhou, Chenzheng Zhu, Da Pan, Fei Deng, Guangwei Ai, Guosheng Dong, Hongda Zhang, Jinyang Tai, Jixiang Hong, Kai Lu, Linzhuang Sun, Peidong Guo, Qian Ma, Rihui Xin, Shihui Yang, Shusen Zhang, Yichuan Mo, Zheng Liang, Zhishou Zhang, Hengfu Cui, Zuyi Zhu, Xiaochuan Wang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> As large language models (LLMs) advance in conversational and reasoning capabilities, their practical application in healthcare has become a critical research focus. However, there is a notable gap between the performance of medical LLMs on static benchmarks such as USMLE and their utility in real-world clinical decision-making. This discrepancy arises because traditional exams fail to capture the dynamic, interactive nature of medical consultations. To address this challenge, we introduce a novel dynamic verification framework that moves beyond static answer verifier, establishing a large-scale, high-fidelity interactive reinforcement learning system. Our framework comprises two key components: a Patient Simulator that creates realistic clinical environments using de-identified medical records, and a Clinical Rubrics Generator that dynamically produces multi-dimensional evaluation metrics. Building on this foundation, we develop Baichuan-M2, a 32B-parameter medical augmented reasoning model trained through a multi-stage reinforcement learning strategy with an improved Group Relative Policy Optimization (GRPO) algorithm. Evaluated on HealthBench, Baichuan-M2 outperforms all other open-source models and most advanced closed-source counterparts, achieving a score above 32 on the challenging HealthBench Hard benchmark-previously exceeded only by GPT-5. Our work demonstrates that robust dynamic verifier system is essential for aligning LLM capabilities with practical clinical applications, establishing a new Pareto front in the performance-parameter trade-off for medical AI deployment.</p> + https://arxiv.org/abs/2509.02208 + Tue, 02 Sep 2025 11:23:35 +0000 - Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning - https://arxiv.org/abs/2508.03501 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.03501.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexander Golubev, Maria Trofimova, Sergei Polezhaev, Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Sergey Abramov, Andrei Andriushchenko, Filipp Fisin, Sergei Skvortsov, Boris Yangel</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Research on applications of Reinforcement Learning (RL) to Large Language Models (LLMs) has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as token-level multi-turn MDPs, this view corresponds to a degenerate case of multi-turn interaction where the environment provides no feedback. This contrasts with many real-world domains, such as software engineering (SWE), which require rich multi-turn interactions with a stateful environment that responds to each action with a non-trivial observation. To bridge this gap, we demonstrate the successful application of RL to this general regime. Using a modified Decoupled Advantage Policy Optimization (DAPO) algorithm, we train an agent based on Qwen2.5-72B-Instruct to solve real-world software engineering tasks. Our approach increases the agent's success rate on the SWE-bench Verified benchmark from a 20% rejection fine-tuned baseline to 39%, without relying on any teacher models. On SWE-rebench, our agent matches or outperforms leading open-weight models such as DeepSeek-V3-0324 and Qwen3-235B-A22B using an identical scaffolding, offering a viable path toward building more capable autonomous agents for complex real-world problems based on open models.</p> - https://arxiv.org/abs/2508.03501 - Tue, 05 Aug 2025 14:30:47 +0000 + SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning + https://arxiv.org/abs/2509.02479 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02479.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenghai Xue, Longtao Zheng, Qian Liu, Yingru Li, Xiaosen Zheng, Zejun Ma, Bo An</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Large Language Models (LLMs) can significantly improve their reasoning capabilities by interacting with external tools, a paradigm known as Tool-Integrated Reasoning (TIR). However, extending TIR to multi-turn scenarios using Reinforcement Learning (RL) is often hindered by training instability and performance collapse. We identify that such instability is primarily caused by a distributional drift from external tool feedback, leading to the generation of low-probability tokens. This issue compounds over successive turns, causing catastrophic gradient norm explosions that derail the training process. To address this challenge, we introduce SimpleTIR , a plug-and-play algorithm that stabilizes multi-turn TIR training. Its core strategy is to identify and filter out trajectories containing void turns, i.e., turns that yield neither a code block nor a final answer. By removing these problematic trajectories from the policy update, SimpleTIR effectively blocks the harmful, high-magnitude gradients, thus stabilizing the learning dynamics. Extensive experiments show that SimpleTIR achieves state-of-the-art performance on challenging math reasoning benchmarks, notably elevating the AIME24 score from a text-only baseline of 22.1 to 50.5 when starting from the Qwen2.5-7B base model. Furthermore, by avoiding the constraints of supervised fine-tuning, SimpleTIR encourages the model to discover diverse and sophisticated reasoning patterns, such as self-correction and cross-validation.</p> + https://arxiv.org/abs/2509.02479 + Tue, 02 Sep 2025 16:30:19 +0000 - Agent Lightning: Train ANY AI Agents with Reinforcement Learning - https://arxiv.org/abs/2508.03680 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.03680.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xufang Luo, Yuge Zhang, Zhiyuan He, Zilong Wang, Siyun Zhao, Dongsheng Li, Luna K. Qiu, Yuqing Yang</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or rely on sequence concatenation with masking, Agent Lightning achieves complete decoupling between agent execution and training, allowing seamless integration with existing agents developed via diverse ways (e.g., using frameworks like LangChain, OpenAI Agents SDK, AutoGen, and building from scratch) with almost ZERO code modifications. By formulating agent execution as Markov decision process, we define an unified data interface and propose a hierarchical RL algorithm, LightningRL, which contains a credit assignment module, allowing us to decompose trajectories generated by ANY agents into training transition. This enables RL to handle complex interaction logic, such as multi-agent scenarios and dynamic workflows. For the system design, we introduce a Training-Agent Disaggregation architecture, and brings agent observability frameworks into agent runtime, providing a standardized agent finetuning interface. Experiments across text-to-SQL, retrieval-augmented generation, and math tool-use tasks demonstrate stable, continuous improvements, showcasing the framework's potential for real-world agent training and deployment.</p> - https://arxiv.org/abs/2508.03680 - Tue, 05 Aug 2025 17:50:13 +0000 + UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning + https://arxiv.org/abs/2509.02544 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02544.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, Junjie Fang, Junting Lu, Longxiang Liu, Qinyu Luo, Shihao Liang, Shijue Huang, Wanjun Zhong, Yining Ye, Yujia Qin, Yuwen Xiong, Yuxin Song, Zhiyong Wu, Bo Li, Chen Dun, Chong Liu, Fuxing Leng, Hanbin Wang, Hao Yu, Haobin Chen, Hongyi Guo, Jing Su, Jingjia Huang, Kai Shen, Kaiyu Shi, Lin Yan, Peiyao Zhao, Pengfei Liu, Qinghao Ye, Renjie Zheng, Wayne Xin Zhao, Wen Heng, Wenhao Huang, Wenqian Wang, Xiaobo Qin, Yi Lin, Youbin Wu, Zehui Chen, Zihao Wang, Baoquan Zhong, Xinchun Zhang, Xujing Li, Yuanfan Li, Zhongkai Zhao, Chengquan Jiang, Faming Wu, Haotian Zhou, Jinlin Pang, Li Han, Qianli Ma, Siyao Liu, Songhua Cai, Wenqi Fu, Xin Liu, Zhi Zhang, Bo Zhou, Guoliang Li, Jiajun Shi, Jiale Yang, Jie Tang, Li Li, Taoran Lu, Woyu Lin, Xiaokang Tong, Xinyao Li, Yichi Zhang, Yu Miao, Zhengxuan Jiang, Zili Li, Ziyuan Zhao, Chenxin Li, Dehua Ma, Feng Lin, Ge Zhang, Haihua Yang, Hangyu Guo, Hongda Zhu, Jiaheng Liu, Junda Du, Kai Cai, Kuanye Li, Lichen Yuan, Meilan Han, Minchao Wang, Shuyue Guo, Tianhao Cheng, Xiaobo Ma, Xiaojun Xiao, Xiaolong Huang, Xinjie Chen, Yidi Du, Yilin Chen, Yiwen Wang, Zhaojian Li, Zhenzhu Yang, Zhiyuan Zeng, Chaolin Jin, Chen Li, Hao Chen, Haoli Chen, Jian Chen, Qinghao Zhao, Guang Shi</p><p><b>Upvotes:</b> 120</p><p><b>Summary:</b> The development of autonomous agents for graphical user interfaces (GUIs) presents major challenges in artificial intelligence. While recent advances in native agent models have shown promise by unifying perception, reasoning, action, and memory through end-to-end learning, open problems remain in data scalability, multi-turn reinforcement learning (RL), the limitations of GUI-only operation, and environment stability. In this technical report, we present UI-TARS-2, a native GUI-centered agent model that addresses these challenges through a systematic training methodology: a data flywheel for scalable data generation, a stabilized multi-turn RL framework, a hybrid GUI environment that integrates file systems and terminals, and a unified sandbox platform for large-scale rollouts. Empirical evaluation demonstrates that UI-TARS-2 achieves significant improvements over its predecessor UI-TARS-1.5. On GUI benchmarks, it reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld, outperforming strong baselines such as Claude and OpenAI agents. In game environments, it attains a mean normalized score of 59.8 across a 15-game suite-roughly 60% of human-level performance-and remains competitive with frontier proprietary models (e.g., OpenAI o3) on LMGame-Bench. Additionally, the model can generalize to long-horizon information-seeking tasks and software engineering benchmarks, highlighting its robustness across diverse agent tasks. Detailed analyses of training dynamics further provide insights into achieving stability and efficiency in large-scale agent RL. These results underscore UI-TARS-2's potential to advance the state of GUI agents and exhibit strong generalization to real-world interactive scenarios.</p> + https://arxiv.org/abs/2509.02544 + Tue, 02 Sep 2025 17:44:45 +0000 - CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward - https://arxiv.org/abs/2508.03686 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.03686.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shudong Liu, Hongwei Liu, Junnan Liu, Linchen Xiao, Songyang Gao, Chengqi Lyu, Yuzhe Gu, Wenwei Zhang, Derek F. Wong, Songyang Zhang, Kai Chen</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Answer verification is crucial not only for evaluating large language models (LLMs) by matching their unstructured outputs against standard answers, but also serves as the reward model to guide LLM optimization. Most evaluation frameworks rely on regularized matching or employ general LLMs for answer verification, which demands extensive, repetitive customization for regex rules or evaluation prompts. Two fundamental limitations persist in current methodologies: 1) the absence of comprehensive benchmarks that systematically evaluate verification capabilities across different LLMs; and 2) the nascent stage of verifier development, where existing approaches lack both the robustness to handle complex edge cases and the generalizability across different domains. In this work, we develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward. It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types, including multi-subproblems, formulas, and sequence answers, while effectively identifying abnormal/invalid responses. We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier. We anticipate that CompassVerifier and VerifierBench will facilitate answer verification, evaluation protocols, and reinforcement learning research. Code and dataset are available at https://github.com/open-compass/CompassVerifier.</p> - https://arxiv.org/abs/2508.03686 - Tue, 05 Aug 2025 17:55:24 +0000 + The Landscape of Agentic Reinforcement Learning for LLMs: A Survey + https://arxiv.org/abs/2509.02547 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.02547.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhongzhi Li, Xiangyuan Xue, Yijiang Li, Yifan Zhou, Yang Chen, Chen Zhang, Yutao Fan, Zihu Wang, Songtao Huang, Yue Liao, Hongru Wang, Mengyue Yang, Heng Ji, Michael Littman, Jun Wang, Shuicheng Yan, Philip Torr, Lei Bai</p><p><b>Upvotes:</b> 211</p><p><b>Summary:</b> The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous, decision-making agents embedded in complex, dynamic worlds. This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM-RL with the temporally extended, partially observable Markov decision processes (POMDPs) that define Agentic RL. Building on this foundation, we propose a comprehensive twofold taxonomy: one organized around core agentic capabilities, including planning, tool use, memory, reasoning, self-improvement, and perception, and the other around their applications across diverse task domains. Central to our thesis is that reinforcement learning serves as the critical mechanism for transforming these capabilities from static, heuristic modules into adaptive, robust agentic behavior. To support and accelerate future research, we consolidate the landscape of open-source environments, benchmarks, and frameworks into a practical compendium. By synthesizing over five hundred recent works, this survey charts the contours of this rapidly evolving field and highlights the opportunities and challenges that will shape the development of scalable, general-purpose AI agents.</p> + https://arxiv.org/abs/2509.02547 + Tue, 02 Sep 2025 17:46:26 +0000 - LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation - https://arxiv.org/abs/2508.03694 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.03694.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianxiong Gao, Zhaoxi Chen, Xian Liu, Jianfeng Feng, Chenyang Si, Yanwei Fu, Yu Qiao, Ziwei Liu</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Controllable ultra-long video generation is a fundamental yet challenging task. Although existing methods are effective for short clips, they struggle to scale due to issues such as temporal inconsistency and visual degradation. In this paper, we initially investigate and identify three key factors: separate noise initialization, independent control signal normalization, and the limitations of single-modality guidance. To address these issues, we propose LongVie, an end-to-end autoregressive framework for controllable long video generation. LongVie introduces two core designs to ensure temporal consistency: 1) a unified noise initialization strategy that maintains consistent generation across clips, and 2) global control signal normalization that enforces alignment in the control space throughout the entire video. To mitigate visual degradation, LongVie employs 3) a multi-modal control framework that integrates both dense (e.g., depth maps) and sparse (e.g., keypoints) control signals, complemented by 4) a degradation-aware training strategy that adaptively balances modality contributions over time to preserve visual quality. We also introduce LongVGenBench, a comprehensive benchmark consisting of 100 high-resolution videos spanning diverse real-world and synthetic environments, each lasting over one minute. Extensive experiments show that LongVie achieves state-of-the-art performance in long-range controllability, consistency, and quality.</p> - https://arxiv.org/abs/2508.03694 - Tue, 05 Aug 2025 17:59:58 +0000 + Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth + https://arxiv.org/abs/2509.03867 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.03867.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Wang, Chenghao Xiao, Chia-Yi Hsiao, Zi Yan Chang, Chi-Li Chen, Tyler Loakman, Chenghua Lin</p><p><b>Upvotes:</b> 206</p><p><b>Summary:</b> We introduce Drivelology, a unique linguistic phenomenon characterised as "nonsense with depth", utterances that are syntactically coherent yet pragmatically paradoxical, emotionally loaded, or rhetorically subversive. While such expressions may resemble surface-level nonsense, they encode implicit meaning requiring contextual inference, moral reasoning, or emotional interpretation. We find that current large language models (LLMs), despite excelling at many natural language processing (NLP) tasks, consistently fail to grasp the layered semantics of Drivelological text. To investigate this, we construct a small but diverse benchmark dataset of over 1,200 meticulously curated examples, with select instances in English, Mandarin, Spanish, French, Japanese, and Korean. Annotation was especially challenging: each of the examples required careful expert review to verify that it truly reflected Drivelological characteristics. The process involved multiple rounds of discussion and adjudication to address disagreements, highlighting the subtle and subjective nature of the Drivelology. We evaluate a range of LLMs on classification, generation, and reasoning tasks. Our results reveal clear limitations of LLMs: models often confuse Drivelology with shallow nonsense, produce incoherent justifications, or miss the implied rhetorical function altogether. These findings highlight a deeper representational gap in LLMs' pragmatic understanding and challenge the assumption that statistical fluency implies cognitive comprehension. We release our dataset and code to facilitate further research in modelling linguistic depth beyond surface-level coherence.</p> + https://arxiv.org/abs/2509.03867 + Thu, 04 Sep 2025 03:58:55 +0000 - VeriGUI: Verifiable Long-Chain GUI Dataset - https://arxiv.org/abs/2508.04026 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.04026.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shunyu Liu, Minghao Liu, Huichi Zhou, Zhenyu Cui, Yang Zhou, Yuhao Zhou, Wendong Fan, Ge Zhang, Jiajun Shi, Weihao Xuan, Jiaxing Huang, Shuang Luo, Fang Wu, Heli Qi, Qingcheng Zeng, Ziqi Ren, Jialiang Gao, Jindi Lv, Junjie Wang, Aosong Feng, Heng Zhou, Wangchunshu Zhou, Zhenfei Yin, Wenlong Zhang, Guohao Li, Wenhao Yu, Irene Li, Lei Ma, Lei Bai, Qunshu Lin, Mingli Song, Dacheng Tao</p><p><b>Upvotes:</b> 156</p><p><b>Summary:</b> Recent studies have delved into constructing autonomous agents capable of performing complex Graphical User Interface (GUI)-based computer tasks, with the potential to revolutionize human-computer interaction. Despite encouraging results, existing efforts mainly focus on short-term interactions and rely on outcome-only verification, thereby limiting their scalability in real-world GUI applications that demand long-horizon task decomposition and execution. In this work, we introduce VeriGUI, a novel verifiable long-chain GUI dataset designed to facilitate the development and evaluation of generalist GUI agents operating in realistic computer environments. Our dataset emphasizes two critical dimensions: (1) long-chain complexity, with tasks decomposed into a sequence of interdependent subtasks spanning hundreds of steps, explicitly designed to allow any subtask to serve as a valid starting point; and (2) subtask-level verifiability, which enables diverse exploration strategies within each subtask, while ensuring that each subtask-level goal remains verifiable and consistent. The dataset consists of GUI task trajectories across both desktop and web, annotated by human experts. Extensive experiments on VeriGUI using various agents with different foundation models reveal significant performance gaps in handling long-horizon tasks, highlighting the need for more robust planning and decision-making capabilities in GUI agents.</p> - https://arxiv.org/abs/2508.04026 - Wed, 06 Aug 2025 02:38:18 +0000 + Set Block Decoding is a Language Model Inference Accelerator + https://arxiv.org/abs/2509.04185 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Itai Gat, Heli Ben-Hamu, Marton Havasi, Daniel Haziza, Jeremy Reizenstein, Gabriel Synnaeve, David Lopez-Paz, Brian Karrer, Yaron Lipman</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Autoregressive next token prediction language models offer powerful capabilities but face significant challenges in practical deployment due to the high computational and memory costs of inference, particularly during the decoding stage. We introduce Set Block Decoding (SBD), a simple and flexible paradigm that accelerates generation by integrating standard next token prediction (NTP) and masked token prediction (MATP) within a single architecture. SBD allows the model to sample multiple, not necessarily consecutive, future tokens in parallel, a key distinction from previous acceleration methods. This flexibility allows the use of advanced solvers from the discrete diffusion literature, offering significant speedups without sacrificing accuracy. SBD requires no architectural changes or extra training hyperparameters, maintains compatibility with exact KV-caching, and can be implemented by fine-tuning existing next token prediction models. By fine-tuning Llama-3.1 8B and Qwen-3 8B, we demonstrate that SBD enables a 3-5x reduction in the number of forward passes required for generation while achieving same performance as equivalent NTP training.</p> + https://arxiv.org/abs/2509.04185 + Thu, 04 Sep 2025 13:02:39 +0000 - Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success - https://arxiv.org/abs/2508.04280 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.04280.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> George Bredis, Stanislav Dereka, Viacheslav Sinii, Ruslan Rakhimov, Daniil Gavrilov</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Interactive multimodal agents must convert raw visual observations into coherent sequences of language-conditioned actions -- a capability that current vision-language models (VLMs) still lack. Earlier reinforcement-learning (RL) efforts could, in principle, endow VLMs with such skills, but they have seldom tested whether the learned behaviours generalize beyond their training simulators, and they depend either on brittle hyperparameter tuning or on dense-reward environments with low state variability. We introduce Vision-Language Decoupled Actor-Critic (VL-DAC), a lightweight, hyperparameter-free RL algorithm. VL-DAC applies PPO updates to action tokens while learning value only at the environment-step level: an arrangement, to our knowledge, not previously explored for large VLMs or LLMs. This simple decoupling removes unstable weighting terms and yields faster, more reliable convergence. Training a single VLM with VL-DAC in one inexpensive simulator at a time (MiniWorld, Gym-Cards, ALFWorld, or WebShop) already produces policies that generalize widely: +50\% relative on BALROG (game-centric agentic control), +5\% relative on the hardest part of VSI-Bench (spatial planning), and +2\% on VisualWebBench (web navigation), all without degrading general image understanding accuracy. These results provide the first evidence that a simple RL algorithm can train VLMs entirely in cheap synthetic worlds while delivering measurable gains on real-image agentic, spatial-reasoning, and web-navigation benchmarks.</p> - https://arxiv.org/abs/2508.04280 - Wed, 06 Aug 2025 10:08:48 +0000 + Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions? + https://arxiv.org/abs/2509.04292 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04292.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qinyan Zhang, Xinping Lei, Ruijie Miao, Yu Fu, Haojie Fan, Le Chang, Jiafan Hou, Dingling Zhang, Zhongfei Hou, Ziqiang Yang, Changxin Pu, Fei Hu, Jingkai Liu, Mengyun Liu, Yang Liu, Xiang Gao, Jiaheng Liu, Tong Yang, Zaiyuan Wang, Ge Zhang, Wenhao Huang</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Large Language Models (LLMs) achieve strong performance on diverse tasks but often exhibit cognitive inertia, struggling to follow instructions that conflict with the standardized patterns learned during supervised fine-tuning (SFT). To evaluate this limitation, we propose Inverse IFEval, a benchmark that measures models Counter-intuitive Abilitytheir capacity to override training-induced biases and comply with adversarial instructions. Inverse IFEval introduces eight types of such challenges, including Question Correction, Intentional Textual Flaws, Code without Comments, and Counterfactual Answering. Using a human-in-the-loop pipeline, we construct a dataset of 1012 high-quality Chinese and English questions across 23 domains, evaluated under an optimized LLM-as-a-Judge framework. Experiments on existing leading LLMs demonstrate the necessity of our proposed Inverse IFEval benchmark. Our findings emphasize that future alignment efforts should not only pursue fluency and factual correctness but also account for adaptability under unconventional contexts. We hope that Inverse IFEval serves as both a diagnostic tool and a foundation for developing methods that mitigate cognitive inertia, reduce overfitting to narrow patterns, and ultimately enhance the instruction-following reliability of LLMs in diverse and unpredictable real-world scenarios.</p> + https://arxiv.org/abs/2509.04292 + Thu, 04 Sep 2025 15:03:02 +0000 - Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL - https://arxiv.org/abs/2508.13167 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.13167.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weizhen Li, Jianbo Lin, Zhuosong Jiang, Jingyi Cao, Xinpeng Liu, Jiayu Zhang, Zhenqiang Huang, Qianben Chen, Weichen Sun, Qiexiang Wang, Hongxuan Lu, Tianrui Qin, Chenghao Zhu, Yi Yao, Shuying Fan, Xiaowan Li, Tiannan Wang, Pai Liu, King Zhu, He Zhu, Dingfeng Shi, Piaohong Wang, Yeyi Guan, Xiangru Tang, Minghao Liu, Yuchen Eleanor Jiang, Jian Yang, Jiaheng Liu, Ge Zhang, Wangchunshu Zhou</p><p><b>Upvotes:</b> 119</p><p><b>Summary:</b> Recent advances in large language models (LLMs) and multi-agent systems have demonstrated remarkable capabilities in complex problem-solving tasks such as deep research, vibe coding, and mathematical reasoning. However, most existing multi-agent systems are built upon manual prompt/workflow engineering with sophisticated agent frameworks, making them computationally inefficient, less capable, and can not benefit from data-centric learning. In this work, we introduce Chain-of-Agents (CoA), a novel paradigm of LLM reasoning that enables native end-to-end complex problem-solving in the same way as a multi-agent system (i.e., multi-turn problem solving with multiple tools and multiple agents) within one model. In chain-of-agents problem-solving, the model dynamically activates different tool agents and role-playing agents to simulate multi-agent collaboration in an end-to-end fashion. To elicit end-to-end chain-of-agents problem-solving abilities in LLMs, we introduce a multi-agent distillation framework to distill state-of-the-art multi-agent systems into chain-of-agents trajectories for agentic supervised fine-tuning. We then use agentic reinforcement learning on verifiable agentic tasks to further improve the models' capabilities on chain-of-agents problem solving. We call the resulting models Agent Foundation Models (AFMs). Our empirical studies demonstrate that AFM establishes new state-of-the-art performance across diverse benchmarks in both web agent and code agent settings. We make the entire research, including the model weights, code for training and evaluation, and the training data, fully open-sourced, which offers a solid starting point for future research on agent models and agentic RL.</p> - https://arxiv.org/abs/2508.13167 - Wed, 06 Aug 2025 17:01:02 +0000 + From Editor to Dense Geometry Estimator + https://arxiv.org/abs/2509.04338 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04338.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> JiYuan Wang, Chunyu Lin, Lei Sun, Rongying Liu, Lang Nie, Mingxing Li, Kang Liao, Xiangxiang Chu, Yao Zhao</p><p><b>Upvotes:</b> 91</p><p><b>Summary:</b> Leveraging visual priors from pre-trained text-to-image (T2I) generative models has shown success in dense prediction. However, dense prediction is inherently an image-to-image task, suggesting that image editing models, rather than T2I generative models, may be a more suitable foundation for fine-tuning. Motivated by this, we conduct a systematic analysis of the fine-tuning behaviors of both editors and generators for dense geometry estimation. Our findings show that editing models possess inherent structural priors, which enable them to converge more stably by ``refining" their innate features, and ultimately achieve higher performance than their generative counterparts. Based on these findings, we introduce FE2E, a framework that pioneeringly adapts an advanced editing model based on Diffusion Transformer (DiT) architecture for dense geometry prediction. Specifically, to tailor the editor for this deterministic task, we reformulate the editor's original flow matching loss into the ``consistent velocity" training objective. And we use logarithmic quantization to resolve the precision conflict between the editor's native BFloat16 format and the high precision demand of our tasks. Additionally, we leverage the DiT's global attention for a cost-free joint estimation of depth and normals in a single forward pass, enabling their supervisory signals to mutually enhance each other. Without scaling up the training data, FE2E achieves impressive performance improvements in zero-shot monocular depth and normal estimation across multiple datasets. Notably, it achieves over 35\% performance gains on the ETH3D dataset and outperforms the DepthAnything series, which is trained on 100times data. The project page can be accessed https://amap-ml.github.io/FE2E/{here}.</p> + https://arxiv.org/abs/2509.04338 + Thu, 04 Sep 2025 15:58:50 +0000 - SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience - https://arxiv.org/abs/2508.04700 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.04700.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyi Sun, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiaoyi Dong, Tong Wu, Dahua Lin, Jiaqi Wang</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Repurposing large vision-language models (LVLMs) as computer use agents (CUAs) has led to substantial breakthroughs, primarily driven by human-labeled data. However, these models often struggle with novel and specialized software, particularly in scenarios lacking human annotations. To address this challenge, we propose SEAgent, an agentic self-evolving framework enabling CUAs to autonomously evolve through interactions with unfamiliar software. Specifically, SEAgent empowers computer-use agents to autonomously master novel software environments via experiential learning, where agents explore new software, learn through iterative trial-and-error, and progressively tackle auto-generated tasks organized from simple to complex. To achieve this goal, we design a World State Model for step-wise trajectory assessment, along with a Curriculum Generator that generates increasingly diverse and challenging tasks. The agent's policy is updated through experiential learning, comprised of adversarial imitation of failure actions and Group Relative Policy Optimization (GRPO) on successful ones. Furthermore, we introduce a specialist-to-generalist training strategy that integrates individual experiential insights from specialist agents, facilitating the development of a stronger generalist CUA capable of continuous autonomous evolution. This unified agent ultimately achieves performance surpassing ensembles of individual specialist agents on their specialized software. We validate the effectiveness of SEAgent across five novel software environments within OS-World. Our approach achieves a significant improvement of 23.2% in success rate, from 11.3% to 34.5%, over a competitive open-source CUA, i.e., UI-TARS.</p> - https://arxiv.org/abs/2508.04700 - Wed, 06 Aug 2025 17:58:46 +0000 + Towards a Unified View of Large Language Model Post-Training + https://arxiv.org/abs/2509.04419 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingtai Lv, Yuxin Zuo, Youbang Sun, Hongyi Liu, Yuntian Wei, Zhekai Chen, Lixuan He, Xuekai Zhu, Kaiyan Zhang, Bingning Wang, Ning Ding, Bowen Zhou</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. These two types of data are typically used by approaches like Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT), respectively. In this paper, we show that these approaches are not in contradiction, but are instances of a single optimization process. We derive a Unified Policy Gradient Estimator, and present the calculations of a wide spectrum of post-training approaches as the gradient of a common objective under different data distribution assumptions and various bias-variance tradeoffs. The gradient estimator is constructed with four interchangeable parts: stabilization mask, reference policy denominator, advantage estimate, and likelihood gradient. Motivated by our theoretical findings, we propose Hybrid Post-Training (HPT), an algorithm that dynamically selects different training signals. HPT is designed to yield both effective exploitation of demonstration and stable exploration without sacrificing learned reasoning patterns. We provide extensive experiments and ablation studies to verify the effectiveness of our unified theoretical framework and HPT. Across six mathematical reasoning benchmarks and two out-of-distribution suites, HPT consistently surpasses strong baselines across models of varying scales and families.</p> + https://arxiv.org/abs/2509.04419 + Thu, 04 Sep 2025 17:40:33 +0000 - Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off - https://arxiv.org/abs/2508.04825 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.04825.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seungyong Lee, Jeong-gi Kwak</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Virtual try-on aims to synthesize a realistic image of a person wearing a target garment, but accurately modeling garment-body correspondence remains a persistent challenge, especially under pose and appearance variation. In this paper, we propose Voost - a unified and scalable framework that jointly learns virtual try-on and try-off with a single diffusion transformer. By modeling both tasks jointly, Voost enables each garment-person pair to supervise both directions and supports flexible conditioning over generation direction and garment category, enhancing garment-body relational reasoning without task-specific networks, auxiliary losses, or additional labels. In addition, we introduce two inference-time techniques: attention temperature scaling for robustness to resolution or mask variation, and self-corrective sampling that leverages bidirectional consistency between tasks. Extensive experiments demonstrate that Voost achieves state-of-the-art results on both try-on and try-off benchmarks, consistently outperforming strong baselines in alignment accuracy, visual fidelity, and generalization.</p> - https://arxiv.org/abs/2508.04825 - Wed, 06 Aug 2025 19:10:58 +0000 + 3D and 4D World Modeling: A Survey + https://arxiv.org/abs/2509.07996 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lingdong Kong, Wesley Yang, Jianbiao Mei, Youquan Liu, Ao Liang, Dekai Zhu, Dongyue Lu, Wei Yin, Xiaotao Hu, Mingkai Jia, Junyuan Deng, Kaiwen Zhang, Yang Wu, Tianyi Yan, Shenyuan Gao, Song Wang, Linfeng Li, Liang Pan, Yong Liu, Jianke Zhu, Wei Tsang Ooi, Steven C. H. Hoi, Ziwei Liu</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> World modeling has become a cornerstone in AI research, enabling agents to understand, represent, and predict the dynamic environments they inhabit. While prior work largely emphasizes generative methods for 2D image and video data, they overlook the rapidly growing body of work that leverages native 3D and 4D representations such as RGB-D imagery, occupancy grids, and LiDAR point clouds for large-scale scene modeling. At the same time, the absence of a standardized definition and taxonomy for ``world models'' has led to fragmented and sometimes inconsistent claims in the literature. This survey addresses these gaps by presenting the first comprehensive review explicitly dedicated to 3D and 4D world modeling and generation. We establish precise definitions, introduce a structured taxonomy spanning video-based (VideoGen), occupancy-based (OccGen), and LiDAR-based (LiDARGen) approaches, and systematically summarize datasets and evaluation metrics tailored to 3D/4D settings. We further discuss practical applications, identify open challenges, and highlight promising research directions, aiming to provide a coherent and foundational reference for advancing the field. A systematic summary of existing literature is available at https://github.com/worldbench/survey</p> + https://arxiv.org/abs/2509.07996 + Thu, 04 Sep 2025 17:59:58 +0000 - R-Zero: Self-Evolving Reasoning LLM from Zero Data - https://arxiv.org/abs/2508.05004 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05004.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengsong Huang, Wenhao Yu, Xiaoyang Wang, Hongming Zhang, Zongxia Li, Ruosen Li, Jiaxin Huang, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 123</p><p><b>Summary:</b> Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, existing methods for training such models still rely heavily on vast human-curated tasks and labels, typically via fine-tuning or reinforcement learning, which poses a fundamental bottleneck to advancing AI systems toward capabilities beyond human intelligence. To overcome this limitation, we introduce R-Zero, a fully autonomous framework that generates its own training data from scratch. Starting from a single base LLM, R-Zero initializes two independent models with distinct roles, a Challenger and a Solver. These models are optimized separately and co-evolve through interaction: the Challenger is rewarded for proposing tasks near the edge of the Solver capability, and the Solver is rewarded for solving increasingly challenging tasks posed by the Challenger. This process yields a targeted, self-improving curriculum without any pre-existing tasks and labels. Empirically, R-Zero substantially improves reasoning capability across different backbone LLMs, e.g., boosting the Qwen3-4B-Base by +6.49 on math-reasoning benchmarks and +7.54 on general-domain reasoning benchmarks.</p> - https://arxiv.org/abs/2508.05004 - Thu, 07 Aug 2025 03:38:16 +0000 + Why Language Models Hallucinate + https://arxiv.org/abs/2509.04664 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.04664.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala, Edwin Zhang</p><p><b>Upvotes:</b> 181</p><p><b>Summary:</b> Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems and undermine trust. We argue that language models hallucinate because the training and evaluation procedures reward guessing over acknowledging uncertainty, and we analyze the statistical causes of hallucinations in the modern training pipeline. Hallucinations need not be mysterious -- they originate simply as errors in binary classification. If incorrect statements cannot be distinguished from facts, then hallucinations in pretrained language models will arise through natural statistical pressures. We then argue that hallucinations persist due to the way most evaluations are graded -- language models are optimized to be good test-takers, and guessing when uncertain improves test performance. This "epidemic" of penalizing uncertain responses can only be addressed through a socio-technical mitigation: modifying the scoring of existing benchmarks that are misaligned but dominate leaderboards, rather than introducing additional hallucination evaluations. This change may steer the field toward more trustworthy AI systems.</p> + https://arxiv.org/abs/2509.04664 + Thu, 04 Sep 2025 21:26:31 +0000 - SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens - https://arxiv.org/abs/2508.05305 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05305.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikita Dragunov, Temurbek Rahmatullaev, Elizaveta Goncharova, Andrey Kuznetsov, Anton Razzhigaev</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-squared error or diffusion objectives. We present SONAR-LLM, a decoder-only transformer that "thinks" in the same continuous SONAR embedding space, yet is supervised through token-level cross-entropy propagated via the frozen SONAR decoder. This hybrid objective retains the semantic abstraction of LCM while eliminating its diffusion sampler and restoring a likelihood-based training signal. Across model sizes from 39M to 1.3B parameters, SONAR-LLM attains competitive generation quality. We report scaling trends, ablations, benchmark results, and release the complete training code and all pretrained checkpoints to foster reproducibility and future research.</p> - https://arxiv.org/abs/2508.05305 - Thu, 07 Aug 2025 12:03:44 +0000 + Symbolic Graphics Programming with Large Language Models + https://arxiv.org/abs/2509.05208 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.05208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yamei Chen, Haoquan Zhang, Yangyi Huang, Zeju Qiu, Kaipeng Zhang, Yandong Wen, Weiyang Liu</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored. We study symbolic graphics programming, where the goal is to generate an SGP from a natural-language description. This task also serves as a lens into how LLMs understand the visual world by prompting them to generate images rendered from SGPs. Among various SGPs, our paper sticks to scalable vector graphics (SVGs). We begin by examining the extent to which LLMs can generate SGPs. To this end, we introduce SGP-GenBench, a comprehensive benchmark covering object fidelity, scene fidelity, and compositionality (attribute binding, spatial relations, numeracy). On SGP-GenBench, we discover that frontier proprietary models substantially outperform open-source models, and performance correlates well with general coding capabilities. Motivated by this gap, we aim to improve LLMs' ability to generate SGPs. We propose a reinforcement learning (RL) with verifiable rewards approach, where a format-validity gate ensures renderable SVG, and a cross-modal reward aligns text and the rendered image via strong vision encoders (e.g., SigLIP for text-image and DINO for image-image). Applied to Qwen-2.5-7B, our method substantially improves SVG generation quality and semantics, achieving performance on par with frontier systems. We further analyze training dynamics, showing that RL induces (i) finer decomposition of objects into controllable primitives and (ii) contextual details that improve scene coherence. Our results demonstrate that symbolic graphics programming offers a precise and interpretable lens on cross-modal grounding.</p> + https://arxiv.org/abs/2509.05208 + Fri, 05 Sep 2025 16:10:53 +0000 - DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning - https://arxiv.org/abs/2508.05405 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05405.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinrun Xu, Pi Bu, Ye Wang, Börje F. Karlsson, Ziming Wang, Tengtao Song, Qi Zhu, Jun Song, Zhiming Ding, Bo Zheng</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Although Vision Language Models (VLMs) exhibit strong perceptual abilities and impressive visual reasoning, they struggle with attention to detail and precise action planning in complex, dynamic environments, leading to subpar performance. Real-world tasks typically require complex interactions, advanced spatial reasoning, long-term planning, and continuous strategy refinement, usually necessitating understanding the physics rules of the target scenario. However, evaluating these capabilities in real-world scenarios is often prohibitively expensive. To bridge this gap, we introduce DeepPHY, a novel benchmark framework designed to systematically evaluate VLMs' understanding and reasoning about fundamental physical principles through a series of challenging simulated environments. DeepPHY integrates multiple physical reasoning environments of varying difficulty levels and incorporates fine-grained evaluation metrics. Our evaluation finds that even state-of-the-art VLMs struggle to translate descriptive physical knowledge into precise, predictive control.</p> - https://arxiv.org/abs/2508.05405 - Thu, 07 Aug 2025 13:58:19 +0000 + Reverse-Engineered Reasoning for Open-Ended Generation + https://arxiv.org/abs/2509.06160 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haozhe Wang, Haoran Que, Qixin Xu, Minghao Liu, Wangchunshu Zhou, Jiazhan Feng, Wanjun Zhong, Wei Ye, Tong Yang, Wenhao Huang, Ge Zhang, Fangzhen Lin</p><p><b>Upvotes:</b> 145</p><p><b>Summary:</b> While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling reasoning -- reinforcement learning (RL) and instruction distillation -- falter in this area; RL struggles with the absence of clear reward signals and high-quality reward models, while distillation is prohibitively expensive and capped by the teacher model's capabilities. To overcome these limitations, we introduce REverse-Engineered Reasoning (REER), a new paradigm that fundamentally shifts the approach. Instead of building a reasoning process ``forwards'' through trial-and-error or imitation, REER works ``backwards'' from known-good solutions to computationally discover the latent, step-by-step deep reasoning process that could have produced them. Using this scalable, gradient-free approach, we curate and open-source DeepWriting-20K, a large-scale dataset of 20,000 deep reasoning trajectories for open-ended tasks. Our model, DeepWriter-8B, trained on this data, not only surpasses strong open-source baselines but also achieves performance competitive with, and at times superior to, leading proprietary models like GPT-4o and Claude 3.5.</p> + https://arxiv.org/abs/2509.06160 + Sun, 07 Sep 2025 18:07:58 +0000 - On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification - https://arxiv.org/abs/2508.05629 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05629.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongliang Wu, Yizhou Zhou, Zhou Ziheng, Yingzhe Peng, Xinyu Ye, Xinting Hu, Wenbo Zhu, Lu Qi, Ming-Hsuan Yang, Xu Yang</p><p><b>Upvotes:</b> 167</p><p><b>Summary:</b> We present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through mathematical analysis, we reveal that standard SFT gradients implicitly encode a problematic reward structure that may severely restrict the generalization capabilities of model. To rectify this, we propose Dynamic Fine-Tuning (DFT), stabilizing gradient updates for each token by dynamically rescaling the objective function with the probability of this token. Remarkably, this single-line code change significantly outperforms standard SFT across multiple challenging benchmarks and base models, demonstrating greatly improved generalization. Additionally, our approach shows competitive results in offline RL settings, offering an effective yet simpler alternative. This work bridges theoretical insight and practical solutions, substantially advancing SFT performance. The code will be available at https://github.com/yongliang-wu/DFT.</p> - https://arxiv.org/abs/2508.05629 - Thu, 07 Aug 2025 17:59:04 +0000 + Does DINOv3 Set a New Medical Vision Standard? + https://arxiv.org/abs/2509.06467 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06467.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Che Liu, Yinda Chen, Haoyuan Shi, Jinpeng Lu, Bailiang Jian, Jiazhen Pan, Linghan Cai, Jiayi Wang, Yundi Zhang, Jun Li, Cosmin I. Bercea, Cheng Ouyang, Chen Chen, Zhiwei Xiong, Benedikt Wiestler, Christian Wachinger, Daniel Rueckert, Wenjia Bai, Rossella Arcucci</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialized domains remains such as medical imaging remains an open question. This report investigates whether DINOv3, a state-of-the-art self-supervised vision transformer (ViT) that features strong capability in dense prediction tasks, can directly serve as a powerful, unified encoder for medical vision tasks without domain-specific pre-training. To answer this, we benchmark DINOv3 across common medical vision tasks, including 2D/3D classification and segmentation on a wide range of medical imaging modalities. We systematically analyze its scalability by varying model sizes and input image resolutions. Our findings reveal that DINOv3 shows impressive performance and establishes a formidable new baseline. Remarkably, it can even outperform medical-specific foundation models like BiomedCLIP and CT-Net on several tasks, despite being trained solely on natural images. However, we identify clear limitations: The model's features degrade in scenarios requiring deep domain specialization, such as in Whole-Slide Pathological Images (WSIs), Electron Microscopy (EM), and Positron Emission Tomography (PET). Furthermore, we observe that DINOv3 does not consistently obey scaling law in the medical domain; performance does not reliably increase with larger models or finer feature resolutions, showing diverse scaling behaviors across tasks. Ultimately, our work establishes DINOv3 as a strong baseline, whose powerful visual features can serve as a robust prior for multiple complex medical tasks. This opens promising future directions, such as leveraging its features to enforce multiview consistency in 3D reconstruction.</p> + https://arxiv.org/abs/2509.06467 + Mon, 08 Sep 2025 09:28:57 +0000 - Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation - https://arxiv.org/abs/2508.05635 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05635.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yue Liao, Pengfei Zhou, Siyuan Huang, Donglin Yang, Shengcong Chen, Yuxin Jiang, Yue Hu, Jingbin Cai, Si Liu, Jianlan Luo, Liliang Chen, Shuicheng Yan, Maoqing Yao, Guanghui Ren</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> We introduce Genie Envisioner (GE), a unified world foundation platform for robotic manipulation that integrates policy learning, evaluation, and simulation within a single video-generative framework. At its core, GE-Base is a large-scale, instruction-conditioned video diffusion model that captures the spatial, temporal, and semantic dynamics of real-world robotic interactions in a structured latent space. Built upon this foundation, GE-Act maps latent representations to executable action trajectories through a lightweight, flow-matching decoder, enabling precise and generalizable policy inference across diverse embodiments with minimal supervision. To support scalable evaluation and training, GE-Sim serves as an action-conditioned neural simulator, producing high-fidelity rollouts for closed-loop policy development. The platform is further equipped with EWMBench, a standardized benchmark suite measuring visual fidelity, physical consistency, and instruction-action alignment. Together, these components establish Genie Envisioner as a scalable and practical foundation for instruction-driven, general-purpose embodied intelligence. All code, models, and benchmarks will be released publicly.</p> - https://arxiv.org/abs/2508.05635 - Thu, 07 Aug 2025 17:59:44 +0000 + WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents + https://arxiv.org/abs/2509.06501 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06501.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junteng Liu, Yunji Li, Chi Zhang, Jingyang Li, Aili Chen, Ke Ji, Weiyu Cheng, Zijia Wu, Chengyu Du, Qidi Xu, Jiayuan Song, Zhengmao Zhu, Wenhu Chen, Pengyu Zhao, Junxian He</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> The paradigm of Large Language Models (LLMs) has increasingly shifted toward agentic applications, where web browsing capabilities are fundamental for retrieving information from diverse online sources. However, existing open-source web agents either demonstrate limited information-seeking abilities on complex tasks or lack transparent implementations. In this work, we identify that the key challenge lies in the scarcity of challenging data for information seeking. To address this limitation, we introduce WebExplorer: a systematic data generation approach using model-based exploration and iterative, long-to-short query evolution. This method creates challenging query-answer pairs that require multi-step reasoning and complex web navigation. By leveraging our curated high-quality dataset, we successfully develop advanced web agent WebExplorer-8B through supervised fine-tuning followed by reinforcement learning. Our model supports 128K context length and up to 100 tool calling turns, enabling long-horizon problem solving. Across diverse information-seeking benchmarks, WebExplorer-8B achieves the state-of-the-art performance at its scale. Notably, as an 8B-sized model, WebExplorer-8B is able to effectively search over an average of 16 turns after RL training, achieving higher accuracy than WebSailor-72B on BrowseComp-en/zh and attaining the best performance among models up to 100B parameters on WebWalkerQA and FRAMES. Beyond these information-seeking tasks, our model also achieves strong generalization on the HLE benchmark even though it is only trained on knowledge-intensive QA data. These results highlight our approach as a practical path toward long-horizon web agents.</p> + https://arxiv.org/abs/2509.06501 + Mon, 08 Sep 2025 10:07:03 +0000 - WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent - https://arxiv.org/abs/2508.05748 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.05748.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Geng, Peng Xia, Zhen Zhang, Xinyu Wang, Qiuchen Wang, Ruixue Ding, Chenxi Wang, Jialong Wu, Yida Zhao, Kuan Li, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 121</p><p><b>Summary:</b> Web agents such as Deep Research have demonstrated superhuman cognitive abilities, capable of solving highly challenging information-seeking problems. However, most research remains primarily text-centric, overlooking visual information in the real world. This makes multimodal Deep Research highly challenging, as such agents require much stronger reasoning abilities in perception, logic, knowledge, and the use of more sophisticated tools compared to text-based agents. To address this limitation, we introduce WebWatcher, a multi-modal Agent for Deep Research equipped with enhanced visual-language reasoning capabilities. It leverages high-quality synthetic multimodal trajectories for efficient cold start training, utilizes various tools for deep reasoning, and further enhances generalization through reinforcement learning. To better evaluate the capabilities of multimodal agents, we propose BrowseComp-VL, a benchmark with BrowseComp-style that requires complex information retrieval involving both visual and textual information. Experimental results show that WebWatcher significantly outperforms proprietary baseline, RAG workflow and open-source agents in four challenging VQA benchmarks, which paves the way for solving complex multimodal information-seeking tasks.</p> - https://arxiv.org/abs/2508.05748 - Thu, 07 Aug 2025 18:03:50 +0000 + Reinforcement Learning Foundations for Deep Research Systems: A Survey + https://arxiv.org/abs/2509.06733 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06733.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenjun Li, Zhi Chen, Jingru Lin, Hannan Cao, Wei Han, Sheng Liang, Zhi Zhang, Kuicai Dong, Dexun Li, Chen Zhang, Yong Liu</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and Executors. In practice, training entire stacks end-to-end remains impractical, so most work trains a single planner connected to core tools such as search, browsing, and code. While SFT imparts protocol fidelity, it suffers from imitation and exposure biases and underuses environment feedback. Preference alignment methods such as DPO are schema and proxy-dependent, off-policy, and weak for long-horizon credit assignment and multi-objective trade-offs. A further limitation of SFT and DPO is their reliance on human defined decision points and subskills through schema design and labeled comparisons. Reinforcement learning aligns with closed-loop, tool-interaction research by optimizing trajectory-level policies, enabling exploration, recovery behaviors, and principled credit assignment, and it reduces dependence on such human priors and rater biases. This survey is, to our knowledge, the first dedicated to the RL foundations of deep research systems. It systematizes work after DeepSeek-R1 along three axes: (i) data synthesis and curation; (ii) RL methods for agentic research covering stability, sample efficiency, long context handling, reward and credit design, multi-objective optimization, and multimodal integration; and (iii) agentic RL training systems and frameworks. We also cover agent architecture and coordination, as well as evaluation and benchmarks, including recent QA, VQA, long-form synthesis, and domain-grounded, tool-interaction tasks. We distill recurring patterns, surface infrastructure bottlenecks, and offer practical guidance for training robust, transparent deep research agents with RL.</p> + https://arxiv.org/abs/2509.06733 + Mon, 08 Sep 2025 14:27:23 +0000 - Memp: Exploring Agent Procedural Memory - https://arxiv.org/abs/2508.06433 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.06433.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu, Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a learnable, updatable, and lifelong procedural memory. We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions, and explore the impact of different strategies for Build, Retrieval, and Update of procedural memory. Coupled with a dynamic regimen that continuously updates, corrects, and deprecates its contents, this repository evolves in lockstep with new experience. Empirical evaluation on TravelPlanner and ALFWorld shows that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks. Moreover, procedural memory built from a stronger model retains its value: migrating the procedural memory to a weaker model yields substantial performance gains.</p> - https://arxiv.org/abs/2508.06433 - Fri, 08 Aug 2025 16:20:56 +0000 + MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML + https://arxiv.org/abs/2509.06806 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06806.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Dong, Pengkun Zhang, Mingzhe Lu, Yanzhen Shen, Guolin Ke</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Large language models (LLMs) possess broad world knowledge and strong general-purpose reasoning ability, yet they struggle to learn from many in-context examples on standard machine learning (ML) tasks, that is, to leverage many-shot demonstrations purely via in-context learning (ICL) without gradient descent. We introduce MachineLearningLM, a portable continued-pretraining framework that equips a general-purpose LLM with robust in-context ML capability while preserving its general knowledge and reasoning for broader chat workflows. Our pretraining procedure synthesizes ML tasks from millions of structural causal models (SCMs), spanning shot counts up to 1,024. We begin with a random-forest teacher, distilling tree-based decision strategies into the LLM to strengthen robustness in numerical modeling. All tasks are serialized with a token-efficient prompt, enabling 3x to 6x more examples per context window and delivering up to 50x amortized throughput via batch inference. Despite a modest setup (Qwen-2.5-7B-Instruct with LoRA rank 8), MachineLearningLM outperforms strong LLM baselines (e.g., GPT-5-mini) by an average of about 15% on out-of-distribution tabular classification across finance, physics, biology, and healthcare domains. It exhibits a striking many-shot scaling law: accuracy increases monotonically as in-context demonstrations grow from 8 to 1,024. Without any task-specific training, it attains random-forest-level accuracy across hundreds of shots. General chat capabilities, including knowledge and reasoning, are preserved: it achieves 75.4% on MMLU.</p> + https://arxiv.org/abs/2509.06806 + Mon, 08 Sep 2025 15:38:31 +0000 - GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models - https://arxiv.org/abs/2508.06471 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.06471.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> GLM-4. 5 Team, Aohan Zeng, Xin Lv, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Da Yin, Hao Zeng, Jiajie Zhang, Kedong Wang, Lucen Zhong, Mingdao Liu, Rui Lu, Shulin Cao, Xiaohan Zhang, Xuancheng Huang, Yao Wei, Yean Cheng, Yifan An, Yilin Niu, Yuanhao Wen, Yushi Bai, Zhengxiao Du, Zihan Wang, Zilin Zhu, Bohan Zhang, Bosi Wen, Bowen Wu, Bowen Xu, Can Huang, Casey Zhao, Changpeng Cai, Chao Yu, Chen Li, Chendi Ge, Chenghua Huang, Chenhui Zhang, Chenxi Xu, Chenzheng Zhu, Chuang Li, Congfeng Yin, Daoyan Lin, Dayong Yang, Dazhi Jiang, Ding Ai, Erle Zhu, Fei Wang, Gengzheng Pan, Guo Wang, Hailong Sun, Haitao Li, Haiyang Li, Haiyi Hu, Hanyu Zhang, Hao Peng, Hao Tai, Haoke Zhang, Haoran Wang, Haoyu Yang, He Liu, He Zhao, Hongwei Liu, Hongxi Yan, Huan Liu, Huilong Chen, Ji Li, Jiajing Zhao, Jiamin Ren, Jian Jiao, Jiani Zhao, Jianyang Yan, Jiaqi Wang, Jiayi Gui, Jiayue Zhao, Jie Liu, Jijie Li, Jing Li, Jing Lu, Jingsen Wang, Jingwei Yuan, Jingxuan Li, Jingzhao Du, Jinhua Du, Jinxin Liu, Junkai Zhi, Junli Gao, Ke Wang, Lekang Yang, Liang Xu, Lin Fan, Lindong Wu, Lintao Ding, Lu Wang, Man Zhang, Minghao Li, Minghuan Xu, Mingming Zhao, Mingshu Zhai, Pengfan Du, Qian Dong, Shangde Lei, Shangqing Tu, Shangtong Yang, Shaoyou Lu, Shijie Li, Shuang Li, Shuang-Li, Shuxun Yang, Sibo Yi, Tianshu Yu, Wei Tian, Weihan Wang, Wenbo Yu, Weng Lam Tam, Wenjie Liang, Wentao Liu, Xiao Wang, Xiaohan Jia, Xiaotao Gu, Xiaoying Ling, Xin Wang, Xing Fan, Xingru Pan, Xinyuan Zhang, Xinze Zhang, Xiuqing Fu, Xunkai Zhang, Yabo Xu, Yandong Wu, Yida Lu, Yidong Wang, Yilin Zhou, Yiming Pan, Ying Zhang, Yingli Wang, Yingru Li, Yinpei Su, Yipeng Geng, Yitong Zhu, Yongkun Yang, Yuhang Li, Yuhao Wu, Yujiang Li, Yunan Liu, Yunqing Wang, Yuntao Li, Yuxuan Zhang, Zezhen Liu, Zhen Yang, Zhengda Zhou, Zhongpei Qiao, Zhuoer Feng, Zhuorui Liu, Zichen Zhang, Zihan Wang, Zijun Yao, Zikang Wang, Ziqiang Liu, Ziwei Chai, Zixuan Li, Zuodong Zhao, Wenguang Chen, Jidong Zhai, Bin Xu, Minlie Huang, Hongning Wang, Juanzi Li, Yuxiao Dong, Jie Tang</p><p><b>Upvotes:</b> 168</p><p><b>Summary:</b> We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes. Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding (ARC) tasks, scoring 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified. With much fewer parameters than several competitors, GLM-4.5 ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks. We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems. Code, models, and more information are available at https://github.com/zai-org/GLM-4.5.</p> - https://arxiv.org/abs/2508.06471 - Fri, 08 Aug 2025 17:21:06 +0000 + Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents + https://arxiv.org/abs/2509.06917 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiacheng Miao, Joe R. Davis, Jonathan K. Pritchard, James Zou</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We introduce Paper2Agent, an automated framework that converts research papers into AI agents. Paper2Agent transforms research output from passive artifacts into active systems that can accelerate downstream use, adoption, and discovery. Conventional research papers require readers to invest substantial effort to understand and adapt a paper's code, data, and methods to their own work, creating barriers to dissemination and reuse. Paper2Agent addresses this challenge by automatically converting a paper into an AI agent that acts as a knowledgeable research assistant. It systematically analyzes the paper and the associated codebase using multiple agents to construct a Model Context Protocol (MCP) server, then iteratively generates and runs tests to refine and robustify the resulting MCP. These paper MCPs can then be flexibly connected to a chat agent (e.g. Claude Code) to carry out complex scientific queries through natural language while invoking tools and workflows from the original paper. We demonstrate Paper2Agent's effectiveness in creating reliable and capable paper agents through in-depth case studies. Paper2Agent created an agent that leverages AlphaGenome to interpret genomic variants and agents based on ScanPy and TISSUE to carry out single-cell and spatial transcriptomics analyses. We validate that these paper agents can reproduce the original paper's results and can correctly carry out novel user queries. By turning static papers into dynamic, interactive AI agents, Paper2Agent introduces a new paradigm for knowledge dissemination and a foundation for the collaborative ecosystem of AI co-scientists.</p> + https://arxiv.org/abs/2509.06917 + Mon, 08 Sep 2025 17:28:42 +0000 - BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent - https://arxiv.org/abs/2508.06600 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.06600.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zijian Chen, Xueguang Ma, Shengyao Zhuang, Ping Nie, Kai Zou, Andrew Liu, Joshua Green, Kshama Patel, Ruoxi Meng, Mingyi Su, Sahel Sharifymoghaddam, Yanxi Li, Haoran Hong, Xinyu Shi, Xuye Liu, Nandan Thakur, Crystina Zhang, Luyu Gao, Wenhu Chen, Jimmy Lin</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require iterative search planning and reasoning over search results. Evaluations on current benchmarks like BrowseComp relies on black-box live web search APIs, have notable limitations in (1) fairness: dynamic and opaque web APIs hinder fair comparisons and reproducibility of deep research methods; (2) transparency: lack of control over the document corpus makes it difficult to isolate retriever contributions. In other words, the current evaluations may compare a complete deep research system at a given time, but they do not foster well-controlled experiments to provide insights into the capability of underlying deep research LLMs. To address these challenges, we introduce BrowseComp-Plus, a benchmark derived from BrowseComp, employing a fixed, carefully curated corpus. Each query in BrowseComp-Plus includes human-verified supporting documents and mined challenging negatives, enabling controlled experimentation. The benchmark is shown to be effective in distinguishing the performance of deep research systems. For instance, the open-source model Search-R1, when paired with the BM25 retriever, achieves 3.86% accuracy, whereas the GPT-5 achieves 55.9%. Integrating the GPT-5 with the Qwen3-Embedding-8B retriever further enhances its accuracy to 70.1% with fewer search calls. This benchmark allows comprehensive evaluation and disentangled analysis of deep research agents and retrieval methods, fostering insights into retrieval effectiveness, citation accuracy, and context engineering in Deep-Research system.</p> - https://arxiv.org/abs/2508.06600 - Fri, 08 Aug 2025 17:55:11 +0000 + Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models + https://arxiv.org/abs/2509.06949 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.06949.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinjie Wang, Ling Yang, Bowen Li, Ye Tian, Ke Shen, Mengdi Wang</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped with a diffusion-based value model that enhances training stability, we demonstrate improved reasoning performance on complex math and coding tasks. Besides, it can also be applied to adapt block-specific models to larger blocks, which improves sampling flexibility. Employing TraceRL, we derive a series of state-of-the-art diffusion language models, namely TraDo. Although smaller than 7B-scale AR models, TraDo-4B-Instruct still consistently outperforms them across complex math reasoning tasks. TraDo-8B-Instruct achieves relative accuracy improvements of 6.1% over Qwen2.5-7B-Instruct and 51.3% over Llama3.1-8B-Instruct on mathematical reasoning benchmarks. Through curriculum learning, we also derive the first long-CoT DLM, outperforming Qwen2.5-7B-Instruct on MATH500 with an 18.1% relative accuracy gain. To facilitate reproducible research and practical applications, we release a comprehensive open-source framework for building, training, and deploying diffusion LLMs across diverse architectures. The framework integrates accelerated KV-cache techniques and inference engines for both inference and reinforcement learning, and includes implementations of various supervised fine-tuning and RL methods for mathematics, coding, and general tasks. Code and Models: https://github.com/Gen-Verse/dLLM-RL</p> + https://arxiv.org/abs/2509.06949 + Mon, 08 Sep 2025 17:58:06 +0000 - ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability - https://arxiv.org/abs/2508.07050 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07050.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenhan Liu, Xinyu Ma, Weiwei Sun, Yutao Zhu, Yuchen Li, Dawei Yin, Zhicheng Dou</p><p><b>Upvotes:</b> 114</p><p><b>Summary:</b> Large Language Model (LLM) based listwise ranking has shown superior performance in many passage ranking tasks. With the development of Large Reasoning Models, many studies have demonstrated that step-by-step reasoning during test-time helps improve listwise ranking performance. However, due to the scarcity of reasoning-intensive training data, existing rerankers perform poorly in many complex ranking scenarios and the ranking ability of reasoning-intensive rerankers remains largely underdeveloped. In this paper, we first propose an automated reasoning-intensive training data synthesis framework, which sources training queries and passages from diverse domains and applies DeepSeek-R1 to generate high-quality training labels. A self-consistency data filtering mechanism is designed to ensure the data quality. To empower the listwise reranker with strong reasoning ability, we further propose a two-stage post-training approach, which includes a cold-start supervised fine-tuning (SFT) stage for reasoning pattern learning and a reinforcement learning (RL) stage for further ranking ability enhancement. During the RL stage, based on the nature of listwise ranking, we design a multi-view ranking reward, which is more effective than a ranking metric-based reward. Extensive experiments demonstrate that our trained reasoning-intensive reranker ReasonRank outperforms existing baselines significantly and also achieves much lower latency than pointwise reranker Rank1. Through further experiments, our ReasonRank has achieved state-of-the-art (SOTA) performance 40.6 on the BRIGHT leaderboard\footnote{https://brightbenchmark.github.io/.} Our codes are available at https://github.com/8421BCD/ReasonRank.</p> - https://arxiv.org/abs/2508.07050 - Sat, 09 Aug 2025 17:26:18 +0000 + Reconstruction Alignment Improves Unified Multimodal Models + https://arxiv.org/abs/2509.07295 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07295.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ji Xie, Trevor Darrell, Luke Zettlemoyer, XuDong Wang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training relies on image-text pairs (or sequences) whose captions are typically sparse and miss fine-grained visual details--even when they use hundreds of words to describe a simple image. We introduce Reconstruction Alignment (RecA), a resource-efficient post-training method that leverages visual understanding encoder embeddings as dense "text prompts," providing rich supervision without captions. Concretely, RecA conditions a UMM on its own visual understanding embeddings and optimizes it to reconstruct the input image with a self-supervised reconstruction loss, thereby realigning understanding and generation. Despite its simplicity, RecA is broadly applicable: across autoregressive, masked-autoregressive, and diffusion-based UMMs, it consistently improves generation and editing fidelity. With only 27 GPU-hours, post-training with RecA substantially improves image generation performance on GenEval (0.73rightarrow0.90) and DPGBench (80.93rightarrow88.15), while also boosting editing benchmarks (ImgEdit 3.38rightarrow3.75, GEdit 6.94rightarrow7.25). Notably, RecA surpasses much larger open-source models and applies broadly across diverse UMM architectures, establishing it as an efficient and general post-training alignment strategy for UMMs</p> + https://arxiv.org/abs/2509.07295 + Mon, 08 Sep 2025 23:59:32 +0000 - A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems - https://arxiv.org/abs/2508.07407 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07407.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinyuan Fang, Yanwen Peng, Xi Zhang, Yingxu Wang, Xinhao Yi, Guibin Zhang, Yi Xu, Bin Wu, Siwei Liu, Zihao Li, Zhaochun Ren, Nikos Aletras, Xi Wang, Han Zhou, Zaiqiao Meng</p><p><b>Upvotes:</b> 88</p><p><b>Summary:</b> Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after deployment, limiting their ability to adapt to dynamic and evolving environments. To this end, recent research has explored agent evolution techniques that aim to automatically enhance agent systems based on interaction data and environmental feedback. This emerging direction lays the foundation for self-evolving AI agents, which bridge the static capabilities of foundation models with the continuous adaptability required by lifelong agentic systems. In this survey, we provide a comprehensive review of existing techniques for self-evolving agentic systems. Specifically, we first introduce a unified conceptual framework that abstracts the feedback loop underlying the design of self-evolving agentic systems. The framework highlights four key components: System Inputs, Agent System, Environment, and Optimisers, serving as a foundation for understanding and comparing different strategies. Based on this framework, we systematically review a wide range of self-evolving techniques that target different components of the agent system. We also investigate domain-specific evolution strategies developed for specialised fields such as biomedicine, programming, and finance, where optimisation objectives are tightly coupled with domain constraints. In addition, we provide a dedicated discussion on the evaluation, safety, and ethical considerations for self-evolving agentic systems, which are critical to ensuring their effectiveness and reliability. This survey aims to provide researchers and practitioners with a systematic understanding of self-evolving AI agents, laying the foundation for the development of more adaptive, autonomous, and lifelong agentic systems.</p> - https://arxiv.org/abs/2508.07407 - Sun, 10 Aug 2025 16:07:32 +0000 + Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search + https://arxiv.org/abs/2509.07969 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07969.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Lai, Junyi Li, Wei Li, Tao Liu, Tianjian Li, Hengshuang Zhao</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Recent advances in large multimodal models have leveraged image-based tools with reinforcement learning to tackle visual problems. However, existing open-source approaches often exhibit monotonous reasoning patterns and allow only a limited number of interaction turns, making them inadequate for difficult tasks that require trial-and-error exploration. In this work, we address this limitation by scaling up tool-based interactions and introduce Mini-o3, a system that executes deep, multi-turn reasoning -- spanning tens of steps -- and achieves state-of-the-art performance on challenging visual search tasks. Our recipe for reproducing OpenAI o3-style behaviors comprises three key components. First, we construct the Visual Probe Dataset, a collection of thousands of challenging visual search problems designed for exploratory reasoning. Second, we develop an iterative data collection pipeline to obtain cold-start trajectories that exhibit diverse reasoning patterns, including depth-first search, trial-and-error, and goal maintenance. Third, we propose an over-turn masking strategy that prevents penalization of over-turn responses (those that hit the maximum number of turns) during reinforcement learning, thereby balancing training-time efficiency with test-time scalability. Despite training with an upper bound of only six interaction turns, our model generates trajectories that naturally scale to tens of turns at inference time, with accuracy improving as the number of turns increases. Extensive experiments demonstrate that Mini-o3 produces rich reasoning patterns and deep thinking paths, effectively solving challenging visual search problems.</p> + https://arxiv.org/abs/2509.07969 + Tue, 09 Sep 2025 17:54:21 +0000 - CharacterShot: Controllable and Consistent 4D Character Animation - https://arxiv.org/abs/2508.07409 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07409.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyao Gao, Jiaxing Li, Wenran Liu, Yanhong Zeng, Fei Shen, Kai Chen, Yanan Sun, Cairong Zhao</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> In this paper, we propose CharacterShot, a controllable and consistent 4D character animation framework that enables any individual designer to create dynamic 3D characters (i.e., 4D character animation) from a single reference character image and a 2D pose sequence. We begin by pretraining a powerful 2D character animation model based on a cutting-edge DiT-based image-to-video model, which allows for any 2D pose sequnce as controllable signal. We then lift the animation model from 2D to 3D through introducing dual-attention module together with camera prior to generate multi-view videos with spatial-temporal and spatial-view consistency. Finally, we employ a novel neighbor-constrained 4D gaussian splatting optimization on these multi-view videos, resulting in continuous and stable 4D character representations. Moreover, to improve character-centric performance, we construct a large-scale dataset Character4D, containing 13,115 unique characters with diverse appearances and motions, rendered from multiple viewpoints. Extensive experiments on our newly constructed benchmark, CharacterBench, demonstrate that our approach outperforms current state-of-the-art methods. Code, models, and datasets will be publicly available at https://github.com/Jeoyal/CharacterShot.</p> - https://arxiv.org/abs/2508.07409 - Sun, 10 Aug 2025 16:15:04 +0000 + Visual Representation Alignment for Multimodal Large Language Models + https://arxiv.org/abs/2509.07979 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07979.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Heeji Yoon, Jaewoo Jung, Junwan Kim, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tasks such as object counting or spatial reasoning. We attribute this gap to the prevailing text-only supervision paradigm, which provides only indirect guidance for the visual pathway and often leads MLLMs to discard fine-grained visual details during training. In this paper, we present VIsual Representation ALignment (VIRAL), a simple yet effective regularization strategy that aligns the internal visual representations of MLLMs with those of pre-trained vision foundation models (VFMs). By explicitly enforcing this alignment, VIRAL enables the model not only to retain critical visual details from the input vision encoder but also to complement additional visual knowledge from VFMs, thereby enhancing its ability to reason over complex visual inputs. Our experiments demonstrate consistent improvements across all tasks on widely adopted multimodal benchmarks. Furthermore, we conduct comprehensive ablation studies to validate the key design choices underlying our framework. We believe this simple finding opens up an important direction for the effective integration of visual information in training MLLMs.</p> + https://arxiv.org/abs/2509.07979 + Tue, 09 Sep 2025 17:59:14 +0000 - Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization - https://arxiv.org/abs/2508.07629 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07629.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenpeng Su, Leiyu Pan, Xue Bai, Dening Liu, Guanting Dong, Jiaming Huang, Wenping Hu, Guorui Zhou</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> We present Klear-Reasoner, a model with long reasoning capabilities that demonstrates careful deliberation during problem solving, achieving outstanding performance across multiple benchmarks. Although there are already many excellent works related to inference models in the current community, there are still many problems with reproducing high-performance inference models due to incomplete disclosure of training details. This report provides an in-depth analysis of the reasoning model, covering the entire post-training workflow from data preparation and long Chain-of-Thought supervised fine-tuning (long CoT SFT) to reinforcement learning (RL), along with detailed ablation studies for each experimental component. For SFT data, our experiments show that a small number of high-quality data sources are more effective than a large number of diverse data sources, and that difficult samples can achieve better results without accuracy filtering. In addition, we investigate two key issues with current clipping mechanisms in RL: Clipping suppresses critical exploration signals and ignores suboptimal trajectories. To address these challenges, we propose Gradient-Preserving clipping Policy Optimization (GPPO) that gently backpropagates gradients from clipped tokens. GPPO not only enhances the model's exploration capacity but also improves its efficiency in learning from negative samples. Klear-Reasoner exhibits exceptional reasoning abilities in mathematics and programming, scoring 90.5\% on AIME 2024, 83.2\% on AIME 2025, 66.0\% on LiveCodeBench V5 and 58.1\% on LiveCodeBench V6.</p> - https://arxiv.org/abs/2508.07629 - Mon, 11 Aug 2025 05:17:51 +0000 + Parallel-R1: Towards Parallel Thinking via Reinforcement Learning + https://arxiv.org/abs/2509.07980 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.07980.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tong Zheng, Hongming Zhang, Wenhao Yu, Xiaoyang Wang, Xinyu Yang, Runpeng Dai, Rui Liu, Huiwen Bao, Chengsong Huang, Heng Huang, Dong Yu</p><p><b>Upvotes:</b> 96</p><p><b>Summary:</b> Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains challenging, as existing methods predominantly rely on supervised fine-tuning (SFT) over synthetic data, which encourages teacher-forced imitation rather than exploration and generalization. Different from them, we propose Parallel-R1, the first reinforcement learning (RL) framework that enables parallel thinking behaviors for complex real-world reasoning tasks. Our framework employs a progressive curriculum that explicitly addresses the cold-start problem in training parallel thinking with RL. We first use SFT on prompt-generated trajectories from easier tasks to instill the parallel thinking ability, then transition to RL to explore and generalize this skill on harder problems. Experiments on various math benchmarks, including MATH, AMC23, and AIME, show that Parallel-R1 successfully instills parallel thinking, leading to 8.4% accuracy improvements over the sequential thinking model trained directly on challenging tasks with RL. Further analysis reveals a clear shift in the model's thinking behavior: at an early stage, it uses parallel thinking as an exploration strategy, while in a later stage, it uses the same capability for multi-perspective verification. Most significantly, we validate parallel thinking as a mid-training exploration scaffold, where this temporary exploratory phase unlocks a higher performance ceiling after RL, yielding a 42.9% improvement over the baseline on AIME25. Our model, data, and code will be open-source at https://github.com/zhengkid/Parallel-R1.</p> + https://arxiv.org/abs/2509.07980 + Tue, 09 Sep 2025 17:59:35 +0000 - Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation - https://arxiv.org/abs/2508.07901 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07901.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Xue, Qixin Yan, Wenjing Wang, Hao Liu, Chen Li</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Generating high-fidelity human videos that match user-specified identities is important yet challenging in the field of generative AI. Existing methods often rely on an excessive number of training parameters and lack compatibility with other AIGC tools. In this paper, we propose Stand-In, a lightweight and plug-and-play framework for identity preservation in video generation. Specifically, we introduce a conditional image branch into the pre-trained video generation model. Identity control is achieved through restricted self-attentions with conditional position mapping, and can be learned quickly with only 2000 pairs. Despite incorporating and training just sim1\% additional parameters, our framework achieves excellent results in video quality and identity preservation, outperforming other full-parameter training methods. Moreover, our framework can be seamlessly integrated for other tasks, such as subject-driven video generation, pose-referenced video generation, stylization, and face swapping.</p> - https://arxiv.org/abs/2508.07901 - Mon, 11 Aug 2025 12:17:38 +0000 + HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning + https://arxiv.org/abs/2509.08519 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08519.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liyang Chen, Tianxiang Ma, Jiawei Liu, Bingchuan Li, Zhuowei Chen, Lijie Liu, Xu He, Gen Li, Qian He, Zhiyong Wu</p><p><b>Upvotes:</b> 123</p><p><b>Summary:</b> Human-Centric Video Generation (HCVG) methods seek to synthesize human videos from multimodal inputs, including text, image, and audio. Existing methods struggle to effectively coordinate these heterogeneous modalities due to two challenges: the scarcity of training data with paired triplet conditions and the difficulty of collaborating the sub-tasks of subject preservation and audio-visual sync with multimodal inputs. In this work, we present HuMo, a unified HCVG framework for collaborative multimodal control. For the first challenge, we construct a high-quality dataset with diverse and paired text, reference images, and audio. For the second challenge, we propose a two-stage progressive multimodal training paradigm with task-specific strategies. For the subject preservation task, to maintain the prompt following and visual generation abilities of the foundation model, we adopt the minimal-invasive image injection strategy. For the audio-visual sync task, besides the commonly adopted audio cross-attention layer, we propose a focus-by-predicting strategy that implicitly guides the model to associate audio with facial regions. For joint learning of controllabilities across multimodal inputs, building on previously acquired capabilities, we progressively incorporate the audio-visual sync task. During inference, for flexible and fine-grained multimodal control, we design a time-adaptive Classifier-Free Guidance strategy that dynamically adjusts guidance weights across denoising steps. Extensive experimental results demonstrate that HuMo surpasses specialized state-of-the-art methods in sub-tasks, establishing a unified framework for collaborative multimodal-conditioned HCVG. Project Page: https://phantom-video.github.io/HuMo.</p> + https://arxiv.org/abs/2509.08519 + Wed, 10 Sep 2025 11:54:29 +0000 - MolmoAct: Action Reasoning Models that can Reason in Space - https://arxiv.org/abs/2508.07917 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jason Lee, Jiafei Duan, Haoquan Fang, Yuquan Deng, Shuo Liu, Boyang Li, Bohan Fang, Jieyu Zhang, Yi Ru Wang, Sangho Lee, Winson Han, Wilbert Pumacay, Angelica Wu, Rose Hendrix, Karen Farley, Eli VanderBilt, Ali Farhadi, Dieter Fox, Ranjay Krishna</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Reasoning is central to purposeful action, yet most robotic foundation models map perception and instructions directly to control, which limits adaptability, generalization, and semantic grounding. We introduce Action Reasoning Models (ARMs), a class of vision-language-action models that integrate perception, planning, and control through a structured three-stage pipeline. Our model, MolmoAct, encodes observations and instructions into depth-aware perception tokens, generates mid-level spatial plans as editable trajectory traces, and predicts precise low-level actions, enabling explainable and steerable behavior. MolmoAct-7B-D achieves strong performance across simulation and real-world settings: 70.5% zero-shot accuracy on SimplerEnv Visual Matching tasks, surpassing closed-source Pi-0 and GR00T N1; 86.6% average success on LIBERO, including an additional 6.3% gain over ThinkAct on long-horizon tasks; and in real-world fine-tuning, an additional 10% (single-arm) and an additional 22.7% (bimanual) task progression over Pi-0-FAST. It also outperforms baselines by an additional 23.3% on out-of-distribution generalization and achieves top human-preference scores for open-ended instruction following and trajectory steering. Furthermore, we release, for the first time, the MolmoAct Dataset -- a mid-training robot dataset comprising over 10,000 high quality robot trajectories across diverse scenarios and tasks. Training with this dataset yields an average 5.5% improvement in general performance over the base model. We release all model weights, training code, our collected dataset, and our action reasoning dataset, establishing MolmoAct as both a state-of-the-art robotics foundation model and an open blueprint for building ARMs that transform perception into purposeful action through structured reasoning. Blogpost: https://allenai.org/blog/molmoact</p> - https://arxiv.org/abs/2508.07917 - Mon, 11 Aug 2025 12:32:45 +0000 + Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing + https://arxiv.org/abs/2509.08721 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08721.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jeffrey Amico, Gabriel Passamani Andrade, John Donaghy, Ben Fielding, Tristin Forbus, Harry Grieve, Semih Kara, Jari Kolehmainen, Yihua Lou, Christopher Nies, Edward Phillip Flores Nuño, Diogo Ortega, Shikhar Rastogi, Austin Virts, Matthew J. Wright</p><p><b>Upvotes:</b> 637</p><p><b>Summary:</b> Post-training language models (LMs) with reinforcement learning (RL) can enhance their complex reasoning capabilities without supervised fine-tuning, as demonstrated by DeepSeek-R1-Zero. However, effectively utilizing RL for LMs requires significant parallelization to scale-up inference, which introduces non-trivial technical challenges (e.g. latency, memory, and reliability) alongside ever-growing financial costs. We present Swarm sAmpling Policy Optimization (SAPO), a fully decentralized and asynchronous RL post-training algorithm. SAPO is designed for decentralized networks of heterogenous compute nodes, where each node manages its own policy model(s) while "sharing" rollouts with others in the network; no explicit assumptions about latency, model homogeneity, or hardware are required and nodes can operate in silo if desired. As a result, the algorithm avoids common bottlenecks in scaling RL post-training while also allowing (and even encouraging) new possibilities. By sampling rollouts "shared" across the network, it enables "Aha moments" to propagate, thereby bootstrapping the learning process. In this paper we show SAPO achieved cumulative reward gains of up to 94% in controlled experiments. We also share insights from tests on a network with thousands of nodes contributed by Gensyn community members running the algorithm on diverse hardware and models during an open-source demo.</p> + https://arxiv.org/abs/2509.08721 + Wed, 10 Sep 2025 16:14:20 +0000 - Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL - https://arxiv.org/abs/2508.07976 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07976.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxuan Gao, Wei Fu, Minyang Xie, Shusheng Xu, Chuyi He, Zhiyu Mei, Banghua Zhu, Yi Wu</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Recent advancements in LLM-based agents have demonstrated remarkable capabilities in handling complex, knowledge-intensive tasks by integrating external tools. Among diverse choices of tools, search tools play a pivotal role in accessing vast external knowledge. However, open-source agents still fall short of achieving expert-level Search Intelligence, the ability to resolve ambiguous queries, generate precise searches, analyze results, and conduct thorough exploration. Existing approaches fall short in scalability, efficiency, and data quality. For example, small turn limits in existing online RL methods, e.g. <=10, restrict complex strategy learning. This paper introduces ASearcher, an open-source project for large-scale RL training of search agents. Our key contributions include: (1) Scalable fully asynchronous RL training that enables long-horizon search while maintaining high training efficiency. (2) A prompt-based LLM agent that autonomously synthesizes high-quality and challenging QAs, creating a large-scale QA dataset. Through RL training, our prompt-based QwQ-32B agent achieves substantial improvements, with 46.7% and 20.8% Avg@4 gains on xBench and GAIA, respectively. Notably, our agent exhibits extreme long-horizon search, with tool calls exceeding 40 turns and output tokens exceeding 150k during training time. With a simple agent design and no external LLMs, ASearcher-Web-QwQ achieves Avg@4 scores of 42.1 on xBench and 52.8 on GAIA, surpassing existing open-source 32B agents. We open-source our models, training data, and codes in https://github.com/inclusionAI/ASearcher.</p> - https://arxiv.org/abs/2508.07976 - Mon, 11 Aug 2025 13:36:57 +0000 + AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning + https://arxiv.org/abs/2509.08755 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08755.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiheng Xi, Jixuan Huang, Chenyang Liao, Baodai Huang, Honglin Guo, Jiaqi Liu, Rui Zheng, Junjie Ye, Jiazheng Zhang, Wenxiang Chen, Wei He, Yiwen Ding, Guanyu Li, Zehui Chen, Zhengyin Du, Xuesong Yao, Yufei Xu, Jiecao Chen, Tao Gui, Zuxuan Wu, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving frontier. Like human cognitive development, agents are expected to acquire knowledge and skills through exploration and interaction with the environment. Despite advances, the community still lacks a unified, interactive reinforcement learning (RL) framework that can effectively train such agents from scratch -- without relying on supervised fine-tuning (SFT) -- across diverse and realistic environments. To bridge this gap, we introduce AgentGym-RL, a new framework to train LLM agents for multi-turn interactive decision-making through RL. The framework features a modular and decoupled architecture, ensuring high flexibility and extensibility. It encompasses a wide variety of real-world scenarios, and supports mainstream RL algorithms. Furthermore, we propose ScalingInter-RL, a training approach designed for exploration-exploitation balance and stable RL optimization. In early stages, it emphasizes exploitation by restricting the number of interactions, and gradually shifts towards exploration with larger horizons to encourage diverse problem-solving strategies. In this way, the agent develops more diverse behaviors and is less prone to collapse under long horizons. We perform extensive experiments to validate the stability and effectiveness of both the AgentGym-RL framework and the ScalingInter-RL approach. Our agents match or surpass commercial models on 27 tasks across diverse environments. We offer key insights and will open-source the complete AgentGym-RL framework -- including code and datasets -- to empower the research community in developing the next generation of intelligent agents.</p> + https://arxiv.org/abs/2509.08755 + Wed, 10 Sep 2025 16:46:11 +0000 - Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation - https://arxiv.org/abs/2508.07981 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07981.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangyuan Mao, Aiming Hao, Jintao Chen, Dongxia Liu, Xiaokun Feng, Jiashu Zhu, Meiqi Wu, Chubin Chen, Jiahong Wu, Xiangxiang Chu</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Visual effects (VFX) are essential visual enhancements fundamental to modern cinematic production. Although video generation models offer cost-efficient solutions for VFX production, current methods are constrained by per-effect LoRA training, which limits generation to single effects. This fundamental limitation impedes applications that require spatially controllable composite effects, i.e., the concurrent generation of multiple effects at designated locations. However, integrating diverse effects into a unified framework faces major challenges: interference from effect variations and spatial uncontrollability during multi-VFX joint training. To tackle these challenges, we propose Omni-Effects, a first unified framework capable of generating prompt-guided effects and spatially controllable composite effects. The core of our framework comprises two key innovations: (1) LoRA-based Mixture of Experts (LoRA-MoE), which employs a group of expert LoRAs, integrating diverse effects within a unified model while effectively mitigating cross-task interference. (2) Spatial-Aware Prompt (SAP) incorporates spatial mask information into the text token, enabling precise spatial control. Furthermore, we introduce an Independent-Information Flow (IIF) module integrated within the SAP, isolating the control signals corresponding to individual effects to prevent any unwanted blending. To facilitate this research, we construct a comprehensive VFX dataset Omni-VFX via a novel data collection pipeline combining image editing and First-Last Frame-to-Video (FLF2V) synthesis, and introduce a dedicated VFX evaluation framework for validating model performance. Extensive experiments demonstrate that Omni-Effects achieves precise spatial control and diverse effect generation, enabling users to specify both the category and location of desired effects.</p> - https://arxiv.org/abs/2508.07981 - Mon, 11 Aug 2025 13:41:24 +0000 + RewardDance: Reward Scaling in Visual Generation + https://arxiv.org/abs/2509.08826 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08826.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Wu, Yu Gao, Zilyu Ye, Ming Li, Liang Li, Hanzhong Guo, Jie Liu, Zeyue Xue, Xiaoxia Hou, Wei Liu, Yan Zeng, Weilin Huang</p><p><b>Upvotes:</b> 69</p><p><b>Summary:</b> Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing approaches: CLIP-based RMs suffer from architectural and input modality constraints, while prevalent Bradley-Terry losses are fundamentally misaligned with the next-token prediction mechanism of Vision-Language Models (VLMs), hindering effective scaling. More critically, the RLHF optimization process is plagued by Reward Hacking issue, where models exploit flaws in the reward signal without improving true quality. To address these challenges, we introduce RewardDance, a scalable reward modeling framework that overcomes these barriers through a novel generative reward paradigm. By reformulating the reward score as the model's probability of predicting a "yes" token, indicating that the generated image outperforms a reference image according to specific criteria, RewardDance intrinsically aligns reward objectives with VLM architectures. This alignment unlocks scaling across two dimensions: (1) Model Scaling: Systematic scaling of RMs up to 26 billion parameters; (2) Context Scaling: Integration of task-specific instructions, reference examples, and chain-of-thought (CoT) reasoning. Extensive experiments demonstrate that RewardDance significantly surpasses state-of-the-art methods in text-to-image, text-to-video, and image-to-video generation. Crucially, we resolve the persistent challenge of "reward hacking": Our large-scale RMs exhibit and maintain high reward variance during RL fine-tuning, proving their resistance to hacking and ability to produce diverse, high-quality outputs. It greatly relieves the mode collapse problem that plagues smaller models.</p> + https://arxiv.org/abs/2509.08826 + Wed, 10 Sep 2025 17:59:31 +0000 - WideSearch: Benchmarking Agentic Broad Info-Seeking - https://arxiv.org/abs/2508.07999 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.07999.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ryan Wong, Jiawei Wang, Junjie Zhao, Li Chen, Yan Gao, Long Zhang, Xuan Zhou, Zuo Wang, Kai Xiang, Ge Zhang, Wenhao Huang, Yang Wang, Ke Wang</p><p><b>Upvotes:</b> 105</p><p><b>Summary:</b> From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search agents powered by LLMs offer a promising solution to liberate humans from this tedious work. However, the capability of these agents to perform such "wide-context" collection reliably and completely remains largely unevaluated due to a lack of suitable benchmarks. To bridge this gap, we introduce WideSearch, a new benchmark engineered to evaluate agent reliability on these large-scale collection tasks. The benchmark features 200 manually curated questions (100 in English, 100 in Chinese) from over 15 diverse domains, grounded in real user queries. Each task requires agents to collect large-scale atomic information, which could be verified one by one objectively, and arrange it into a well-organized output. A rigorous five-stage quality control pipeline ensures the difficulty, completeness, and verifiability of the dataset. We benchmark over 10 state-of-the-art agentic search systems, including single-agent, multi-agent frameworks, and end-to-end commercial systems. Most systems achieve overall success rates near 0\%, with the best performer reaching just 5\%. However, given sufficient time, cross-validation by multiple human testers can achieve a near 100\% success rate. These results demonstrate that present search agents have critical deficiencies in large-scale information seeking, underscoring urgent areas for future research and development in agentic search. Our dataset, evaluation pipeline, and benchmark results have been publicly released at https://widesearch-seed.github.io/</p> - https://arxiv.org/abs/2508.07999 - Mon, 11 Aug 2025 14:03:09 +0000 + A Survey of Reinforcement Learning for Large Reasoning Models + https://arxiv.org/abs/2509.08827 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.08827.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaiyan Zhang, Yuxin Zuo, Bingxiang He, Youbang Sun, Runze Liu, Che Jiang, Yuchen Fan, Kai Tian, Guoli Jia, Pengfei Li, Yu Fu, Xingtai Lv, Yuchen Zhang, Sihang Zeng, Shang Qu, Haozhan Li, Shijie Wang, Yuru Wang, Xinwei Long, Fangfu Liu, Xiang Xu, Jiaze Ma, Xuekai Zhu, Ermo Hua, Yihao Liu, Zonglin Li, Huayu Chen, Xiaoye Qu, Yafu Li, Weize Chen, Zhenzhao Yuan, Junqi Gao, Dong Li, Zhiyuan Ma, Ganqu Cui, Zhiyuan Liu, Biqing Qi, Ning Ding, Bowen Zhou</p><p><b>Upvotes:</b> 174</p><p><b>Summary:</b> In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontier of LLM capabilities, particularly in addressing complex logical tasks such as mathematics and coding. As a result, RL has emerged as a foundational methodology for transforming LLMs into LRMs. With the rapid progress of the field, further scaling of RL for LRMs now faces foundational challenges not only in computational resources but also in algorithm design, training data, and infrastructure. To this end, it is timely to revisit the development of this domain, reassess its trajectory, and explore strategies to enhance the scalability of RL toward Artificial SuperIntelligence (ASI). In particular, we examine research applying RL to LLMs and LRMs for reasoning abilities, especially since the release of DeepSeek-R1, including foundational components, core problems, training resources, and downstream applications, to identify future opportunities and directions for this rapidly evolving area. We hope this review will promote future research on RL for broader reasoning models. Github: https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs</p> + https://arxiv.org/abs/2509.08827 + Wed, 10 Sep 2025 17:59:43 +0000 - Matrix-3D: Omnidirectional Explorable 3D World Generation - https://arxiv.org/abs/2508.08086 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.08086.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongqi Yang, Wenhang Ge, Yuqi Li, Jiaqi Chen, Haoyuan Li, Mengyin An, Fei Kang, Hua Xue, Baixin Xu, Yuyang Yin, Eric Li, Yang Liu, Yikai Wang, Hao-Xiang Guo, Yahui Zhou</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Explorable 3D world generation from a single image or text prompt forms a cornerstone of spatial intelligence. Recent works utilize video model to achieve wide-scope and generalizable 3D world generation. However, existing approaches often suffer from a limited scope in the generated scenes. In this work, we propose Matrix-3D, a framework that utilize panoramic representation for wide-coverage omnidirectional explorable 3D world generation that combines conditional video generation and panoramic 3D reconstruction. We first train a trajectory-guided panoramic video diffusion model that employs scene mesh renders as condition, to enable high-quality and geometrically consistent scene video generation. To lift the panorama scene video to 3D world, we propose two separate methods: (1) a feed-forward large panorama reconstruction model for rapid 3D scene reconstruction and (2) an optimization-based pipeline for accurate and detailed 3D scene reconstruction. To facilitate effective training, we also introduce the Matrix-Pano dataset, the first large-scale synthetic collection comprising 116K high-quality static panoramic video sequences with depth and trajectory annotations. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance in panoramic video generation and 3D world generation. See more in https://matrix-3d.github.io.</p> - https://arxiv.org/abs/2508.08086 - Mon, 11 Aug 2025 15:29:57 +0000 + EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs + https://arxiv.org/abs/2509.09174 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09174.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Zhang, Yuhao Du, Zhanchen Dai, Xiangnan Ma, Kaiqi Kou, Benyou Wang, Haizhou Li</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Speech-to-speech large language models (SLLMs) are attracting increasing attention. Derived from text-based large language models (LLMs), SLLMs often exhibit degradation in knowledge and reasoning capabilities. We hypothesize that this limitation arises because current training paradigms for SLLMs fail to bridge the acoustic-semantic gap in the feature representation space. To address this issue, we propose EchoX, which leverages semantic representations and dynamically generates speech training targets. This approach integrates both acoustic and semantic learning, enabling EchoX to preserve strong reasoning abilities as a speech LLM. Experimental results demonstrate that EchoX, with about six thousand hours of training data, achieves advanced performance on multiple knowledge-based question-answering benchmarks. The project is available at https://github.com/FreedomIntelligence/EchoX.</p> + https://arxiv.org/abs/2509.09174 + Thu, 11 Sep 2025 06:17:59 +0000 - Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning - https://arxiv.org/abs/2508.08221 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.08221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihe Liu, Jiashun Liu, Yancheng He, Weixun Wang, Jiaheng Liu, Ling Pan, Xinyu Hu, Shaopan Xiong, Ju Huang, Jian Hu, Shengyi Huang, Siran Yang, Jiamang Wang, Wenbo Su, Bo Zheng</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Reinforcement learning for LLM reasoning has rapidly emerged as a prominent research area, marked by a significant surge in related studies on both algorithmic innovations and practical applications. Despite this progress, several critical challenges remain, including the absence of standardized guidelines for employing RL techniques and a fragmented understanding of their underlying mechanisms. Additionally, inconsistent experimental settings, variations in training data, and differences in model initialization have led to conflicting conclusions, obscuring the key characteristics of these techniques and creating confusion among practitioners when selecting appropriate techniques. This paper systematically reviews widely adopted RL techniques through rigorous reproductions and isolated evaluations within a unified open-source framework. We analyze the internal mechanisms, applicable scenarios, and core principles of each technique through fine-grained experiments, including datasets of varying difficulty, model sizes, and architectures. Based on these insights, we present clear guidelines for selecting RL techniques tailored to specific setups, and provide a reliable roadmap for practitioners navigating the RL for the LLM domain. Finally, we reveal that a minimalist combination of two techniques can unlock the learning capability of critic-free policies using vanilla PPO loss. The results demonstrate that our simple combination consistently improves performance, surpassing strategies like GRPO and DAPO.</p> - https://arxiv.org/abs/2508.08221 - Mon, 11 Aug 2025 17:39:45 +0000 + Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents + https://arxiv.org/abs/2509.09265 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09265.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Wang, Jiacai Liu, Yuqian Fu, Yingru Li, Xintao Wang, Yuan Lin, Yu Yue, Lin Zhang, Yang Wang, Ke Wang</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> In long-horizon tasks, recent agents based on Large Language Models (LLMs) face a significant challenge that sparse, outcome-based rewards make it difficult to assign credit to intermediate steps. Previous methods mainly focus on creating dense reward signals to guide learning, either through traditional reinforcement learning techniques like inverse reinforcement learning or by using Process Reward Models for step-by-step feedback. In this paper, we identify a fundamental problem in the learning dynamics of LLMs: the magnitude of policy gradients is inherently coupled with the entropy, which leads to inefficient small updates for confident correct actions and potentially destabilizes large updates for uncertain ones. To resolve this, we propose Entropy-Modulated Policy Gradients (EMPG), a framework that re-calibrates the learning signal based on step-wise uncertainty and the final task outcome. EMPG amplifies updates for confident correct actions, penalizes confident errors, and attenuates updates from uncertain steps to stabilize exploration. We further introduce a bonus term for future clarity that encourages agents to find more predictable solution paths. Through comprehensive experiments on three challenging agent tasks, WebShop, ALFWorld, and Deep Search, we demonstrate that EMPG achieves substantial performance gains and significantly outperforms strong policy gradient baselines. Project page is at https://empgseed-seed.github.io/</p> + https://arxiv.org/abs/2509.09265 + Thu, 11 Sep 2025 08:50:01 +0000 - ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks - https://arxiv.org/abs/2508.08240 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.08240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaijun Wang, Liqin Lu, Mingyu Liu, Jianuo Jiang, Zeju Li, Bolin Zhang, Wancai Zheng, Xinyi Yu, Hao Chen, Chunhua Shen</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Language-guided long-horizon mobile manipulation has long been a grand challenge in embodied semantic reasoning, generalizable manipulation, and adaptive locomotion. Three fundamental limitations hinder progress: First, although large language models have improved spatial reasoning and task planning through semantic priors, existing implementations remain confined to tabletop scenarios, failing to address the constrained perception and limited actuation ranges of mobile platforms. Second, current manipulation strategies exhibit insufficient generalization when confronted with the diverse object configurations encountered in open-world environments. Third, while crucial for practical deployment, the dual requirement of maintaining high platform maneuverability alongside precise end-effector control in unstructured settings remains understudied. In this work, we present ODYSSEY, a unified mobile manipulation framework for agile quadruped robots equipped with manipulators, which seamlessly integrates high-level task planning with low-level whole-body control. To address the challenge of egocentric perception in language-conditioned tasks, we introduce a hierarchical planner powered by a vision-language model, enabling long-horizon instruction decomposition and precise action execution. At the control level, our novel whole-body policy achieves robust coordination across challenging terrains. We further present the first benchmark for long-horizon mobile manipulation, evaluating diverse indoor and outdoor scenarios. Through successful sim-to-real transfer, we demonstrate the system's generalization and robustness in real-world deployments, underscoring the practicality of legged manipulators in unstructured environments. Our work advances the feasibility of generalized robotic assistants capable of complex, dynamic tasks. Our project page: https://kaijwang.github.io/odyssey.github.io/</p> - https://arxiv.org/abs/2508.08240 - Mon, 11 Aug 2025 17:54:31 +0000 + VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model + https://arxiv.org/abs/2509.09372 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09372.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihao Wang, Pengxiang Ding, Lingxiao Li, Can Cui, Zirui Ge, Xinyang Tong, Wenxuan Song, Han Zhao, Wei Zhao, Pengxu Hou, Siteng Huang, Yifan Tang, Wenhui Wang, Ru Zhang, Jianyi Liu, Donglin Wang</p><p><b>Upvotes:</b> 216</p><p><b>Summary:</b> Vision-Language-Action (VLA) models typically bridge the gap between perceptual and action spaces by pre-training a large-scale Vision-Language Model (VLM) on robotic data. While this approach greatly enhances performance, it also incurs significant training costs. In this paper, we investigate how to effectively bridge vision-language (VL) representations to action (A). We introduce VLA-Adapter, a novel paradigm designed to reduce the reliance of VLA models on large-scale VLMs and extensive pre-training. To this end, we first systematically analyze the effectiveness of various VL conditions and present key findings on which conditions are essential for bridging perception and action spaces. Based on these insights, we propose a lightweight Policy module with Bridge Attention, which autonomously injects the optimal condition into the action space. In this way, our method achieves high performance using only a 0.5B-parameter backbone, without any robotic data pre-training. Extensive experiments on both simulated and real-world robotic benchmarks demonstrate that VLA-Adapter not only achieves state-of-the-art level performance, but also offers the fast inference speed reported to date. Furthermore, thanks to the proposed advanced bridging paradigm, VLA-Adapter enables the training of a powerful VLA model in just 8 hours on a single consumer-grade GPU, greatly lowering the barrier to deploying the VLA model. Project page: https://vla-adapter.github.io/.</p> + https://arxiv.org/abs/2509.09372 + Thu, 11 Sep 2025 11:42:21 +0000 - Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery - https://arxiv.org/abs/2508.08401 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.08401.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiatong Li, Weida Wang, Qinggang Zhang, Junxian Li, Di Zhang, Changmeng Zheng, Shufei Zhang, Xiaoyong Wei, Qing Li</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Large language models (LLMs), especially Explicit Long Chain-of-Thought (CoT) reasoning models like DeepSeek-R1 and QWQ, have demonstrated powerful reasoning capabilities, achieving impressive performance in commonsense reasoning and mathematical inference. Despite their effectiveness, Long-CoT reasoning models are often criticized for their limited ability and low efficiency in knowledge-intensive domains such as molecule discovery. Success in this field requires a precise understanding of domain knowledge, including molecular structures and chemical principles, which is challenging due to the inherent complexity of molecular data and the scarcity of high-quality expert annotations. To bridge this gap, we introduce Mol-R1, a novel framework designed to improve explainability and reasoning performance of R1-like Explicit Long-CoT reasoning LLMs in text-based molecule generation. Our approach begins with a high-quality reasoning dataset curated through Prior Regulation via In-context Distillation (PRID), a dedicated distillation strategy to effectively generate paired reasoning traces guided by prior regulations. Building upon this, we introduce MoIA, Molecular Iterative Adaptation, a sophisticated training strategy that iteratively combines Supervised Fine-tuning (SFT) with Reinforced Policy Optimization (RPO), tailored to boost the reasoning performance of R1-like reasoning models for molecule discovery. Finally, we examine the performance of Mol-R1 in the text-based molecule reasoning generation task, showing superior performance against existing baselines.</p> - https://arxiv.org/abs/2508.08401 - Mon, 11 Aug 2025 18:50:05 +0000 + Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis + https://arxiv.org/abs/2509.09595 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09595.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yikang Ding, Jiwen Liu, Wenyuan Zhang, Zekun Wang, Wentao Hu, Liyuan Cui, Mingming Lao, Yingchao Shao, Hui Liu, Xiaohan Li, Ming Chen, Xiaoqiang Liu, Yu-Shen Liu, Pengfei Wan</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-level tracking driven by acoustic or visual cues, without modeling the communicative purpose conveyed by the instructions. This limitation compromises their narrative coherence and character expressiveness. To bridge this gap, we introduce Kling-Avatar, a novel cascaded framework that unifies multimodal instruction understanding with photorealistic portrait generation. Our approach adopts a two-stage pipeline. In the first stage, we design a multimodal large language model (MLLM) director that produces a blueprint video conditioned on diverse instruction signals, thereby governing high-level semantics such as character motion and emotions. In the second stage, guided by blueprint keyframes, we generate multiple sub-clips in parallel using a first-last frame strategy. This global-to-local framework preserves fine-grained details while faithfully encoding the high-level intent behind multimodal instructions. Our parallel architecture also enables fast and stable generation of long-duration videos, making it suitable for real-world applications such as digital human livestreaming and vlogging. To comprehensively evaluate our method, we construct a benchmark of 375 curated samples covering diverse instructions and challenging scenarios. Extensive experiments demonstrate that Kling-Avatar is capable of generating vivid, fluent, long-duration videos at up to 1080p and 48 fps, achieving superior performance in lip synchronization accuracy, emotion and dynamic expressiveness, instruction controllability, identity preservation, and cross-domain generalization. These results establish Kling-Avatar as a new benchmark for semantically grounded, high-fidelity audio-driven avatar synthesis.</p> + https://arxiv.org/abs/2509.09595 + Thu, 11 Sep 2025 16:34:57 +0000 - VertexRegen: Mesh Generation with Continuous Level of Detail - https://arxiv.org/abs/2508.09062 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09062.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiang Zhang, Yawar Siddiqui, Armen Avetisyan, Chris Xie, Jakob Engel, Henry Howard-Jenkins</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> We introduce VertexRegen, a novel mesh generation framework that enables generation at a continuous level of detail. Existing autoregressive methods generate meshes in a partial-to-complete manner and thus intermediate steps of generation represent incomplete structures. VertexRegen takes inspiration from progressive meshes and reformulates the process as the reversal of edge collapse, i.e. vertex split, learned through a generative model. Experimental results demonstrate that VertexRegen produces meshes of comparable quality to state-of-the-art methods while uniquely offering anytime generation with the flexibility to halt at any step to yield valid meshes with varying levels of detail.</p> - https://arxiv.org/abs/2508.09062 - Tue, 12 Aug 2025 16:25:46 +0000 + SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning + https://arxiv.org/abs/2509.09674 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09674.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haozhan Li, Yuxin Zuo, Jiale Yu, Yuhao Zhang, Zhaohui Yang, Kaiyan Zhang, Xuekai Zhu, Yuchen Zhang, Tianxing Chen, Ganqu Cui, Dehui Wang, Dingxiang Luo, Yuchen Fan, Youbang Sun, Jia Zeng, Jiangmiao Pang, Shanghang Zhang, Yu Wang, Yao Mu, Bowen Zhou, Ning Ding</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have recently emerged as a powerful paradigm for robotic manipulation. Despite substantial progress enabled by large-scale pretraining and supervised fine-tuning (SFT), these models face two fundamental challenges: (i) the scarcity and high cost of large-scale human-operated robotic trajectories required for SFT scaling, and (ii) limited generalization to tasks involving distribution shift. Recent breakthroughs in Large Reasoning Models (LRMs) demonstrate that reinforcement learning (RL) can dramatically enhance step-by-step reasoning capabilities, raising a natural question: Can RL similarly improve the long-horizon step-by-step action planning of VLA? In this work, we introduce SimpleVLA-RL, an efficient RL framework tailored for VLA models. Building upon veRL, we introduce VLA-specific trajectory sampling, scalable parallelization, multi-environment rendering, and optimized loss computation. When applied to OpenVLA-OFT, SimpleVLA-RL achieves SoTA performance on LIBERO and even outperforms pi_0 on RoboTwin 1.0\&2.0 with the exploration-enhancing strategies we introduce. SimpleVLA-RL not only reduces dependence on large-scale data and enables robust generalization, but also remarkably surpasses SFT in real-world tasks. Moreover, we identify a novel phenomenon ``pushcut'' during RL training, wherein the policy discovers previously unseen patterns beyond those seen in the previous training process. Github: https://github.com/PRIME-RL/SimpleVLA-RL</p> + https://arxiv.org/abs/2509.09674 + Thu, 11 Sep 2025 17:59:17 +0000 - Complex Logical Instruction Generation - https://arxiv.org/abs/2508.09125 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09125.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mian Zhang, Shujian Liu, Sixun Dong, Ming Yin, Yebowen Hu, Xun Wang, Steven Ma, Song Wang, Sathish Reddy Indurthi, Haoyun Deng, Zhiyu Zoey Chen, Kaiqiang Song</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabilities such as reasoning and agentic behaviors. As tasks grow more challenging, the logic structures embedded in natural language instructions becomes increasingly intricate. However, how well LLMs perform on such logic-rich instructions remains under-explored. We propose LogicIFGen and LogicIFEval. LogicIFGen is a scalable, automated framework for generating verifiable instructions from code functions, which can naturally express rich logic such as conditionals, nesting, recursion, and function calls. We further curate a collection of complex code functions and use LogicIFGen to construct LogicIFEval, a benchmark comprising 426 verifiable logic-rich instructions. Our experiments demonstrate that current state-of-the-art LLMs still struggle to correctly follow the instructions in LogicIFEval. Most LLMs can only follow fewer than 60% of the instructions, revealing significant deficiencies in the instruction-following ability. Code and Benchmark: https://github.com/mianzhang/LogicIF</p> - https://arxiv.org/abs/2508.09125 - Tue, 12 Aug 2025 17:54:27 +0000 + SpatialVID: A Large-Scale Video Dataset with Spatial Annotations + https://arxiv.org/abs/2509.09676 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Wang, Yufeng Yuan, Rujie Zheng, Youtian Lin, Jian Gao, Lin-Zhuo Chen, Yajie Bao, Yi Zhang, Chang Zeng, Yanxi Zhou, Xiaoxiao Long, Hao Zhu, Zhaoxiang Zhang, Xun Cao, Yao Yao</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Significant progress has been made in spatial intelligence, spanning both spatial reconstruction and world exploration. However, the scalability and real-world fidelity of current models remain severely constrained by the scarcity of large-scale, high-quality training data. While several datasets provide camera pose information, they are typically limited in scale, diversity, and annotation richness, particularly for real-world dynamic scenes with ground-truth camera motion. To this end, we collect SpatialVID, a dataset consists of a large corpus of in-the-wild videos with diverse scenes, camera movements and dense 3D annotations such as per-frame camera poses, depth, and motion instructions. Specifically, we collect more than 21,000 hours of raw video, and process them into 2.7 million clips through a hierarchical filtering pipeline, totaling 7,089 hours of dynamic content. A subsequent annotation pipeline enriches these clips with detailed spatial and semantic information, including camera poses, depth maps, dynamic masks, structured captions, and serialized motion instructions. Analysis of SpatialVID's data statistics reveals a richness and diversity that directly foster improved model generalization and performance, establishing it as a key asset for the video and 3D vision research community.</p> + https://arxiv.org/abs/2509.09676 + Thu, 11 Sep 2025 17:59:31 +0000 - Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models - https://arxiv.org/abs/2508.09138 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09138.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wen Wang, Bozhen Fang, Chenchen Jing, Yongliang Shen, Yangyi Shen, Qiuyu Wang, Hao Ouyang, Hao Chen, Chunhua Shen</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Diffusion large language models (dLLMs) generate text through iterative denoising, yet current decoding strategies discard rich intermediate predictions in favor of the final output. Our work here reveals a critical phenomenon, temporal oscillation, where correct answers often emerge in the middle process, but are overwritten in later denoising steps. To address this issue, we introduce two complementary methods that exploit temporal consistency: 1) Temporal Self-Consistency Voting, a training-free, test-time decoding strategy that aggregates predictions across denoising steps to select the most consistent output; and 2) a post-training method termed Temporal Consistency Reinforcement, which uses Temporal Semantic Entropy (TSE), a measure of semantic stability across intermediate predictions, as a reward signal to encourage stable generations. Empirical results across multiple benchmarks demonstrate the effectiveness of our approach. Using the negative TSE reward alone, we observe a remarkable average improvement of 24.7% on the Countdown dataset over an existing dLLM. Combined with the accuracy reward, we achieve absolute gains of 2.0% on GSM8K, 4.3% on MATH500, 6.6% on SVAMP, and 25.3% on Countdown, respectively. Our findings underscore the untapped potential of temporal dynamics in dLLMs and offer two simple yet effective tools to harness them.</p> - https://arxiv.org/abs/2508.09138 - Tue, 12 Aug 2025 17:59:57 +0000 + FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark + https://arxiv.org/abs/2509.09680 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.09680.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rongyao Fang, Aldrich Yu, Chengqi Duan, Linjiang Huang, Shuai Bai, Yuxuan Cai, Kun Wang, Si Liu, Xihui Liu, Hongsheng Li</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> The advancement of open-source text-to-image (T2I) models has been hindered by the absence of large-scale, reasoning-focused datasets and comprehensive evaluation benchmarks, resulting in a performance gap compared to leading closed-source systems. To address this challenge, We introduce FLUX-Reason-6M and PRISM-Bench (Precise and Robust Image Synthesis Measurement Benchmark). FLUX-Reason-6M is a massive dataset consisting of 6 million high-quality FLUX-generated images and 20 million bilingual (English and Chinese) descriptions specifically designed to teach complex reasoning. The image are organized according to six key characteristics: Imagination, Entity, Text rendering, Style, Affection, and Composition, and design explicit Generation Chain-of-Thought (GCoT) to provide detailed breakdowns of image generation steps. The whole data curation takes 15,000 A100 GPU days, providing the community with a resource previously unattainable outside of large industrial labs. PRISM-Bench offers a novel evaluation standard with seven distinct tracks, including a formidable Long Text challenge using GCoT. Through carefully designed prompts, it utilizes advanced vision-language models for nuanced human-aligned assessment of prompt-image alignment and image aesthetics. Our extensive evaluation of 19 leading models on PRISM-Bench reveals critical performance gaps and highlights specific areas requiring improvement. Our dataset, benchmark, and evaluation code are released to catalyze the next wave of reasoning-oriented T2I generation. Project page: https://flux-reason-6m.github.io/ .</p> + https://arxiv.org/abs/2509.09680 + Thu, 11 Sep 2025 17:59:59 +0000 - Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory - https://arxiv.org/abs/2508.09736 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09736.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lin Long, Yichen He, Wentao Ye, Yiyuan Pan, Yuan Lin, Hang Li, Junbo Zhao, Wei Li</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> We introduce M3-Agent, a novel multimodal agent framework equipped with long-term memory. Like humans, M3-Agent can process real-time visual and auditory inputs to build and update its long-term memory. Beyond episodic memory, it also develops semantic memory, enabling it to accumulate world knowledge over time. Its memory is organized in an entity-centric, multimodal format, allowing deeper and more consistent understanding of the environment. Given an instruction, M3-Agent autonomously performs multi-turn, iterative reasoning and retrieves relevant information from memory to accomplish the task. To evaluate memory effectiveness and memory-based reasoning in multimodal agents, we develop M3-Bench, a new long-video question answering benchmark. M3-Bench comprises 100 newly recorded real-world videos captured from a robot's perspective (M3-Bench-robot) and 929 web-sourced videos across diverse scenarios (M3-Bench-web). We annotate question-answer pairs designed to test key capabilities essential for agent applications, such as human understanding, general knowledge extraction, and cross-modal reasoning. Experimental results show that M3-Agent, trained via reinforcement learning, outperforms the strongest baseline, a prompting agent using Gemini-1.5-pro and GPT-4o, achieving 6.7%, 7.7%, and 5.3% higher accuracy on M3-Bench-robot, M3-Bench-web and VideoMME-long, respectively. Our work advances the multimodal agents toward more human-like long-term memory and provides insights into their practical design. Model, code and data are available at https://github.com/bytedance-seed/m3-agent</p> - https://arxiv.org/abs/2508.09736 - Wed, 13 Aug 2025 12:03:03 +0000 + UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning + https://arxiv.org/abs/2509.11543 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.11543.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Graphical User Interface (GUI) agents have demonstrated remarkable progress in automating complex user interface interactions through reinforcement learning. However, current approaches face a fundamental dilemma: offline RL enables stable training on pre-collected trajectories, but struggles with multi-step task execution for lack of trajectory-level reward signals; online RL captures these signals through environment interaction, but suffers from sparse rewards and prohibitive deployment costs. To address it, we present Semi-online Reinforcement Learning, a novel paradigm that simulates online RL on offline trajectories. During each rollout process, we preserve the original model output within the multi-turn dialogue, where a Patch Module adaptively recovers the divergence between rollout and expert trajectories. To capture long-term training signals, Semi-online RL introduces discounted future returns into the reward computation and optimizes the policy with weighted step-level and episode-level advantages. We further introduce Semi-Online Performance (SOP), a metric that aligns better with true online performance, serving as a practical and effective proxy for real-world evaluation. Experiments show that ours Semi-online RL achieves SOTA performance among 7B models across four dynamic benchmarks, with significant gains over the base model (e.g., +12.0% on AndroidWorld, +23.8% on AITW), demonstrating significant progress in bridging the gap between offline training efficiency and online multi-turn reasoning. The code is available at https://github.com/X-PLUG/MobileAgent/tree/main/UI-S1.</p> + https://arxiv.org/abs/2509.11543 + Mon, 15 Sep 2025 03:24:08 +0000 - Speed Always Wins: A Survey on Efficient Architectures for Large Language Models - https://arxiv.org/abs/2508.09834 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09834.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weigao Sun, Jiaxi Hu, Yucheng Zhou, Jusen Du, Disen Lan, Kexin Wang, Tong Zhu, Xiaoye Qu, Yu Zhang, Xiaoyu Mo, Daizong Liu, Yuxuan Liang, Wenliang Chen, Guoqi Li, Yu Cheng</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Large Language Models (LLMs) have delivered impressive results in language understanding, generation, reasoning, and pushes the ability boundary of multimodal models. Transformer models, as the foundation of modern LLMs, offer a strong baseline with excellent scaling properties. However, the traditional transformer architecture requires substantial computations and poses significant obstacles for large-scale training and practical deployment. In this survey, we offer a systematic examination of innovative LLM architectures that address the inherent limitations of transformers and boost the efficiency. Starting from language modeling, this survey covers the background and technical details of linear and sparse sequence modeling methods, efficient full attention variants, sparse mixture-of-experts, hybrid model architectures incorporating the above techniques, and emerging diffusion LLMs. Additionally, we discuss applications of these techniques to other modalities and consider their wider implications for developing scalable, resource-aware foundation models. By grouping recent studies into the above category, this survey presents a blueprint of modern efficient LLM architectures, and we hope this could help motivate future research toward more efficient, versatile AI systems.</p> - https://arxiv.org/abs/2508.09834 - Wed, 13 Aug 2025 14:13:46 +0000 + OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling + https://arxiv.org/abs/2509.12201 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12201.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Zhou, Yifan Wang, Jianjun Zhou, Wenzheng Chang, Haoyu Guo, Zizun Li, Kaijing Ma, Xinyue Li, Yating Wang, Haoyi Zhu, Mingyu Liu, Dingning Liu, Jiange Yang, Zhoujie Fu, Junyi Chen, Chunhua Shen, Jiangmiao Pang, Kaipeng Zhang, Tong He</p><p><b>Upvotes:</b> 103</p><p><b>Summary:</b> The field of 4D world modeling - aiming to jointly capture spatial geometry and temporal dynamics - has witnessed remarkable progress in recent years, driven by advances in large-scale generative models and multimodal learning. However, the development of truly general 4D world models remains fundamentally constrained by the availability of high-quality data. Existing datasets and benchmarks often lack the dynamic complexity, multi-domain diversity, and spatial-temporal annotations required to support key tasks such as 4D geometric reconstruction, future prediction, and camera-control video generation. To address this gap, we introduce OmniWorld, a large-scale, multi-domain, multi-modal dataset specifically designed for 4D world modeling. OmniWorld consists of a newly collected OmniWorld-Game dataset and several curated public datasets spanning diverse domains. Compared with existing synthetic datasets, OmniWorld-Game provides richer modality coverage, larger scale, and more realistic dynamic interactions. Based on this dataset, we establish a challenging benchmark that exposes the limitations of current state-of-the-art (SOTA) approaches in modeling complex 4D environments. Moreover, fine-tuning existing SOTA methods on OmniWorld leads to significant performance gains across 4D reconstruction and video generation tasks, strongly validating OmniWorld as a powerful resource for training and evaluation. We envision OmniWorld as a catalyst for accelerating the development of general-purpose 4D world models, ultimately advancing machines' holistic understanding of the physical world.</p> + https://arxiv.org/abs/2509.12201 + Mon, 15 Sep 2025 17:59:19 +0000 - PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts - https://arxiv.org/abs/2508.09848 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mo Yu, Tsz Ting Chung, Chulun Zhou, Tong Li, Rui Lu, Jiangnan Li, Liyan Xu, Haoshu Lu, Ning Zhang, Jing Li, Jie Zhou</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> We introduce PRELUDE, a benchmark for evaluating long-context understanding through the task of determining whether a character's prequel story is consistent with the canonical narrative of the original book. Our task poses a stronger demand for global comprehension and deep reasoning than existing benchmarks -- as the prequels are not part of the original story, assessing their plausibility typically requires searching and integrating information that is only indirectly related. Empirically, 88% of instances require evidence from multiple parts of the narrative. Experimental results highlight the challenge of our task: in-context learning, RAG and in-domain training with state-of-the-art LLMs, and commercial DeepResearch services, lag behind humans by >15%. A further human study reveals that models often produce correct answers with flawed reasoning, leading to an over 30% gap in reasoning accuracy compared to humans. These findings underscore the substantial room for improvement in long-context understanding and reasoning.</p> - https://arxiv.org/abs/2508.09848 - Wed, 13 Aug 2025 14:28:25 +0000 + Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation + https://arxiv.org/abs/2509.12815 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.12815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Biwen Lei, Yang Li, Xinhai Liu, Shuhui Yang, Lixin Xu, Jingwei Huang, Ruining Tang, Haohan Weng, Jian Liu, Jing Xu, Zhen Zhou, Yiling Zhu, Jiankai Xing, Jiachen Xu, Changfeng Ma, Xinhao Yan, Yunhan Yang, Chunshi Wang, Duoteng Xu, Xueqi Ma, Yuguang Chen, Jing Li, Mingxin Yang, Sheng Zhang, Yifei Feng, Xin Huang, Di Luo, Zebin He, Puhua Jiang, Changrong Hu, Zihan Qin, Shiwei Miao, Haolin Liu, Yunfei Zhao, Zeqiang Lai, Qingxiang Lin, Zibo Zhao, Kunhong Li, Xianghui Yang, Huiwen Shi, Xin Yang, Yuxuan Wang, Zebin Yao, Yihang Lian, Sicong Liu, Xintong Han, Wangchen Qin, Caisheng Ouyang, Jianyin Liu, Tianwen Yuan, Shuai Jiang, Hong Duan, Yanqi Niu, Wencong Lin, Yifu Sun, Shirui Huang, Lin Niu, Gu Gong, Guojian Xiao, Bojian Zheng, Xiang Yuan, Qi Chen, Jie Xiao, Dongyang Zheng, Xiaofeng Yang, Kai Liu, Jianchen Zhu, Lifu Wang, Qinglin Lu, Jie Liu, Liang Dong, Fan Jiang, Ruibin Chen, Lei Wang, Chao Zhang, Jiaxin Lin, Hao Zhang, Zheng Ye, Peng He, Runzhou Wu, Yinhe Wu, Jiayao Du, Jupeng Chen, Xinyue Mao, Dongyuan Guo, Yixuan Tang, Yulin Tsai, Yonghao Tan, Jiaao Yu, Junlin Yu, Keren Zhang, Yifan Li, Peng Chen, Tian Liu, Di Wang, Yuhong Liu, Linus, Jie Jiang, Zhuo Chen, Chunchao Guo</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> The creation of high-quality 3D assets, a cornerstone of modern game development, has long been characterized by labor-intensive and specialized workflows. This paper presents Hunyuan3D Studio, an end-to-end AI-powered content creation platform designed to revolutionize the game production pipeline by automating and streamlining the generation of game-ready 3D assets. At its core, Hunyuan3D Studio integrates a suite of advanced neural modules (such as Part-level 3D Generation, Polygon Generation, Semantic UV, etc.) into a cohesive and user-friendly system. This unified framework allows for the rapid transformation of a single concept image or textual description into a fully-realized, production-quality 3D model complete with optimized geometry and high-fidelity PBR textures. We demonstrate that assets generated by Hunyuan3D Studio are not only visually compelling but also adhere to the stringent technical requirements of contemporary game engines, significantly reducing iteration time and lowering the barrier to entry for 3D content creation. By providing a seamless bridge from creative intent to technical asset, Hunyuan3D Studio represents a significant leap forward for AI-assisted workflows in game development and interactive media.</p> + https://arxiv.org/abs/2509.12815 + Tue, 16 Sep 2025 08:33:03 +0000 - AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving - https://arxiv.org/abs/2508.09889 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09889.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhitian Xie, Qintong Wu, Chengyue Yu, Chenyi Zhuang, Jinjie Gu</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> The rapid advancement of large language models (LLMs) has empowered intelligent agents to leverage diverse external tools for solving complex real-world problems. However, as agents increasingly depend on multiple tools, they encounter new challenges: extended contexts from disparate sources and noisy or irrelevant tool outputs can undermine system reliability and accuracy. These challenges underscore the necessity for enhanced stability in agent-based systems. To address this, we introduce dynamic supervision and maneuvering mechanisms, constructing a robust and dynamic Multi-Agent System (MAS) architecture within the AWorld framework. In our approach, the Execution Agent invokes the Guard Agent at critical steps to verify and correct the reasoning process, effectively reducing errors arising from noise and bolstering problem-solving robustness. Extensive experiments on the GAIA test dataset reveal that our dynamic maneuvering mechanism significantly improves both the effectiveness and stability of solutions, outperforming single-agent system (SAS) and standard tool-augmented systems. As a result, our dynamic MAS system achieved first place among open-source projects on the prestigious GAIA leaderboard. These findings highlight the practical value of collaborative agent roles in developing more reliable and trustworthy intelligent systems.</p> - https://arxiv.org/abs/2508.09889 - Wed, 13 Aug 2025 15:46:25 +0000 + Single-stream Policy Optimization + https://arxiv.org/abs/2509.13232 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13232.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongwen Xu, Zihan Ding</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> We revisit policy-gradient optimization for Large Language Models (LLMs) from a single-stream perspective. Prevailing group-based methods like GRPO reduce variance with on-the-fly baselines but suffer from critical flaws: frequent degenerate groups erase learning signals, and synchronization barriers hinder scalability. We introduce Single-stream Policy Optimization (SPO), which eliminates these issues by design. SPO replaces per-group baselines with a persistent, KL-adaptive value tracker and normalizes advantages globally across the batch, providing a stable, low-variance learning signal for every sample. Being group-free, SPO enables higher throughput and scales effectively in long-horizon or tool-integrated settings where generation times vary. Furthermore, the persistent value tracker naturally enables an adaptive curriculum via prioritized sampling. Experiments using Qwen3-8B show that SPO converges more smoothly and attains higher accuracy than GRPO, while eliminating computation wasted on degenerate groups. Ablation studies confirm that SPO's gains stem from its principled approach to baseline estimation and advantage normalization, offering a more robust and efficient path for LLM reasoning. Across five hard math benchmarks with Qwen3 8B, SPO improves the average maj@32 by +3.4 percentage points (pp) over GRPO, driven by substantial absolute point gains on challenging datasets, including +7.3 pp on BRUMO 25, +4.4 pp on AIME 25, +3.3 pp on HMMT 25, and achieves consistent relative gain in pass@k across the evaluated k values. SPO's success challenges the prevailing trend of adding incidental complexity to RL algorithms, highlighting a path where fundamental principles, not architectural workarounds, drive the next wave of progress in LLM reasoning.</p> + https://arxiv.org/abs/2509.13232 + Tue, 16 Sep 2025 16:39:11 +0000 - Story2Board: A Training-Free Approach for Expressive Storyboard Generation - https://arxiv.org/abs/2508.09983 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.09983.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> David Dinkevich, Matan Levy, Omri Avrahami, Dvir Samuel, Dani Lischinski</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> We present Story2Board, a training-free framework for expressive storyboard generation from natural language. Existing methods narrowly focus on subject identity, overlooking key aspects of visual storytelling such as spatial composition, background evolution, and narrative pacing. To address this, we introduce a lightweight consistency framework composed of two components: Latent Panel Anchoring, which preserves a shared character reference across panels, and Reciprocal Attention Value Mixing, which softly blends visual features between token pairs with strong reciprocal attention. Together, these mechanisms enhance coherence without architectural changes or fine-tuning, enabling state-of-the-art diffusion models to generate visually diverse yet consistent storyboards. To structure generation, we use an off-the-shelf language model to convert free-form stories into grounded panel-level prompts. To evaluate, we propose the Rich Storyboard Benchmark, a suite of open-domain narratives designed to assess layout diversity and background-grounded storytelling, in addition to consistency. We also introduce a new Scene Diversity metric that quantifies spatial and pose variation across storyboards. Our qualitative and quantitative results, as well as a user study, show that Story2Board produces more dynamic, coherent, and narratively engaging storyboards than existing baselines.</p> - https://arxiv.org/abs/2508.09983 - Wed, 13 Aug 2025 17:56:26 +0000 + WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning + https://arxiv.org/abs/2509.13305 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13305.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kuan Li, Zhongwang Zhang, Huifeng Yin, Rui Ye, Yida Zhao, Liwen Zhang, Litu Ou, Dingchu Zhang, Xixi Wu, Jialong Wu, Xinyu Wang, Zile Qiao, Zhen Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all open-source agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.</p> + https://arxiv.org/abs/2509.13305 + Tue, 16 Sep 2025 17:57:03 +0000 - DINOv3 - https://arxiv.org/abs/2508.10104 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10104.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie, Julien Mairal, Hervé Jégou, Patrick Labatut, Piotr Bojanowski</p><p><b>Upvotes:</b> 221</p><p><b>Summary:</b> Self-supervised learning holds the promise of eliminating the need for manual data annotation, enabling models to scale effortlessly to massive datasets and larger architectures. By not being tailored to specific tasks or domains, this training paradigm has the potential to learn visual representations from diverse sources, ranging from natural to aerial images -- using a single algorithm. This technical report introduces DINOv3, a major milestone toward realizing this vision by leveraging simple yet effective strategies. First, we leverage the benefit of scaling both dataset and model size by careful data preparation, design, and optimization. Second, we introduce a new method called Gram anchoring, which effectively addresses the known yet unsolved issue of dense feature maps degrading during long training schedules. Finally, we apply post-hoc strategies that further enhance our models' flexibility with respect to resolution, model size, and alignment with text. As a result, we present a versatile vision foundation model that outperforms the specialized state of the art across a broad range of settings, without fine-tuning. DINOv3 produces high-quality dense features that achieve outstanding performance on various vision tasks, significantly surpassing previous self- and weakly-supervised foundation models. We also share the DINOv3 suite of vision models, designed to advance the state of the art on a wide spectrum of tasks and data by providing scalable solutions for diverse resource constraints and deployment scenarios.</p> - https://arxiv.org/abs/2508.10104 - Wed, 13 Aug 2025 18:00:55 +0000 + WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents + https://arxiv.org/abs/2509.13309 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zile Qiao, Guoxin Chen, Xuanzhong Chen, Donglei Yu, Wenbiao Yin, Xinyu Wang, Zhen Zhang, Baixuan Li, Huifeng Yin, Kuan Li, Rui Min, Minpeng Liao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such agents through two key components: (1) WebResearcher, an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process, where agents periodically consolidate findings into evolving reports while maintaining focused workspaces, overcoming the context suffocation and noise contamination that plague existing mono-contextual approaches; and (2) WebFrontier, a scalable data synthesis engine that generates high-quality training data through tool-augmented complexity escalation, enabling systematic creation of research tasks that bridge the gap between passive knowledge recall and active knowledge construction. Notably, we find that the training data from our paradigm significantly enhances tool-use capabilities even for traditional mono-contextual methods. Furthermore, our paradigm naturally scales through parallel thinking, enabling concurrent multi-agent exploration for more comprehensive conclusions. Extensive experiments across 6 challenging benchmarks demonstrate that WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.</p> + https://arxiv.org/abs/2509.13309 + Tue, 16 Sep 2025 17:57:17 +0000 - XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization - https://arxiv.org/abs/2508.10395 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10395.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aditya Tomar, Coleman Hooper, Minjae Lee, Haocheng Xi, Rishabh Tiwari, Wonjun Kang, Luca Manolache, Michael W. Mahoney, Kurt Keutzer, Amir Gholami</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Although LLM inference has emerged as a critical workload for many downstream applications, efficiently inferring LLMs is challenging due to the substantial memory footprint and bandwidth requirements. In parallel, compute capabilities have steadily outpaced both memory capacity and bandwidth over the last few decades, a trend that remains evident in modern GPU hardware and exacerbates the challenge of LLM inference. As such, new algorithms are emerging that trade increased computation for reduced memory operations. To that end, we present XQuant, which takes advantage of this trend, enabling an order-of-magnitude reduction in memory consumption through low-bit quantization with substantial accuracy benefits relative to state-of-the-art KV cache quantization methods. We accomplish this by quantizing and caching the layer input activations X, instead of using standard KV caching, and then rematerializing the Keys and Values on-the-fly during inference. This results in an immediate 2times memory savings compared to KV caching. By applying XQuant, we achieve up to sim 7.7times memory savings with <0.1 perplexity degradation compared to the FP16 baseline. Furthermore, our approach leverages the fact that X values are similar across layers. Building on this observation, we introduce XQuant-CL, which exploits the cross-layer similarity in the X embeddings for extreme compression. Across different models, XQuant-CL attains up to 10times memory savings relative to the FP16 baseline with only 0.01 perplexity degradation, and 12.5times memory savings with only 0.1 perplexity degradation. XQuant exploits the rapidly increasing compute capabilities of hardware platforms to eliminate the memory bottleneck, while surpassing state-of-the-art KV cache quantization methods and achieving near-FP16 accuracy across a wide range of models.</p> - https://arxiv.org/abs/2508.10395 - Thu, 14 Aug 2025 06:52:38 +0000 + Scaling Agents via Continual Pre-training + https://arxiv.org/abs/2509.13310 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13310.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liangcai Su, Zhen Zhang, Guangyu Li, Zhuo Chen, Chenxi Wang, Maojia Song, Xinyu Wang, Kuan Li, Jialong Wu, Xuanzhong Chen, Zile Qiao, Zhongwang Zhang, Huifeng Yin, Shihao Cai, Runnan Fang, Zhengwei Tao, Wenbiao Yin, Chenxiong Qian, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 107</p><p><b>Summary:</b> Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models consistently underperform in agentic tasks, particularly in open-source implementations. We identify the root cause: the absence of robust agentic foundation models forces models during post-training to simultaneously learn diverse agentic behaviors while aligning them to expert demonstrations, thereby creating fundamental optimization tensions. To this end, we are the first to propose incorporating Agentic Continual Pre-training (Agentic CPT) into the deep research agents training pipeline to build powerful agentic foundational models. Based on this approach, we develop a deep research agent model named AgentFounder. We evaluate our AgentFounder-30B on 10 benchmarks and achieve state-of-the-art performance while retains strong tool-use ability, notably 39.9% on BrowseComp-en, 43.3% on BrowseComp-zh, and 31.5% Pass@1 on HLE.</p> + https://arxiv.org/abs/2509.13310 + Tue, 16 Sep 2025 17:57:19 +0000 - ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning - https://arxiv.org/abs/2508.10419 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juyuan Wang, Rongchen Zhao, Wei Wei, Yufeng Wang, Mo Yu, Jie Zhou, Jin Xu, Liyan Xu</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Narrative comprehension on long stories and novels has been a challenging domain attributed to their intricate plotlines and entangled, often evolving relations among characters and entities. Given the LLM's diminished reasoning over extended context and high computational cost, retrieval-based approaches remain a pivotal role in practice. However, traditional RAG methods can fall short due to their stateless, single-step retrieval process, which often overlooks the dynamic nature of capturing interconnected relations within long-range context. In this work, we propose ComoRAG, holding the principle that narrative reasoning is not a one-shot process, but a dynamic, evolving interplay between new evidence acquisition and past knowledge consolidation, analogous to human cognition when reasoning with memory-related signals in the brain. Specifically, when encountering a reasoning impasse, ComoRAG undergoes iterative reasoning cycles while interacting with a dynamic memory workspace. In each cycle, it generates probing queries to devise new exploratory paths, then integrates the retrieved evidence of new aspects into a global memory pool, thereby supporting the emergence of a coherent context for the query resolution. Across four challenging long-context narrative benchmarks (200K+ tokens), ComoRAG outperforms strong RAG baselines with consistent relative gains up to 11% compared to the strongest baseline. Further analysis reveals that ComoRAG is particularly advantageous for complex queries requiring global comprehension, offering a principled, cognitively motivated paradigm for retrieval-based long context comprehension towards stateful reasoning. Our code is publicly released at https://github.com/EternityJune25/ComoRAG</p> - https://arxiv.org/abs/2508.10419 - Thu, 14 Aug 2025 07:52:09 +0000 + Towards General Agentic Intelligence via Environment Scaling + https://arxiv.org/abs/2509.13311 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13311.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments. The breadth of function-calling competence is closely tied to the diversity of environments in which agents are trained. In this work, we scale up environments as a step towards advancing general agentic intelligence. This gives rise to two central challenges: (i) how to scale environments in a principled manner, and (ii) how to effectively train agentic capabilities from experiences derived through interactions with these environments. To address these, we design a scalable framework that automatically constructs heterogeneous environments that are fully simulated, systematically broadening the space of function-calling scenarios. We further adapt a two-phase agent fine-tuning strategy: first endowing agents with fundamental agentic capabilities, then specializing them for domain-specific contexts. Extensive experiments on agentic benchmarks, tau-bench, tau2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the function-calling capability of models.</p> + https://arxiv.org/abs/2509.13311 + Tue, 16 Sep 2025 17:57:20 +0000 - We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning - https://arxiv.org/abs/2508.10433 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10433.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runqi Qiao, Qiuna Tan, Peiqing Yang, Yanzi Wang, Xiaowan Wang, Enhui Wan, Sitong Zhou, Guanting Dong, Yuchen Zeng, Yida Xu, Jie Wang, Chong Sun, Chen Li, Honggang Zhang</p><p><b>Upvotes:</b> 142</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various tasks, but still struggle with complex mathematical reasoning. Existing research primarily focuses on dataset construction and method optimization, often overlooking two critical aspects: comprehensive knowledge-driven design and model-centric data space modeling. In this paper, we introduce We-Math 2.0, a unified system that integrates a structured mathematical knowledge system, model-centric data space modeling, and a reinforcement learning (RL)-based training paradigm to comprehensively enhance the mathematical reasoning abilities of MLLMs. The key contributions of We-Math 2.0 are fourfold: (1) MathBook Knowledge System: We construct a five-level hierarchical system encompassing 491 knowledge points and 1,819 fundamental principles. (2) MathBook-Standard & Pro: We develop MathBook-Standard, a dataset that ensures broad conceptual coverage and flexibility through dual expansion. Additionally, we define a three-dimensional difficulty space and generate 7 progressive variants per problem to build MathBook-Pro, a challenging dataset for robust training. (3) MathBook-RL: We propose a two-stage RL framework comprising: (i) Cold-Start Fine-tuning, which aligns the model with knowledge-oriented chain-of-thought reasoning; and (ii) Progressive Alignment RL, leveraging average-reward learning and dynamic data scheduling to achieve progressive alignment across difficulty levels. (4) MathBookEval: We introduce a comprehensive benchmark covering all 491 knowledge points with diverse reasoning step distributions. Experimental results show that MathBook-RL performs competitively with existing baselines on four widely-used benchmarks and achieves strong results on MathBookEval, suggesting promising generalization in mathematical reasoning.</p> - https://arxiv.org/abs/2508.10433 - Thu, 14 Aug 2025 08:15:41 +0000 + WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research + https://arxiv.org/abs/2509.13312 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13312.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zijian Li, Xin Guan, Bo Zhang, Shen Huang, Houquan Zhou, Shaopeng Lai, Ming Yan, Yong Jiang, Pengjun Xie, Fei Huang, Jun Zhang, Jingren Zhou</p><p><b>Upvotes:</b> 100</p><p><b>Summary:</b> This paper tackles open-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports. Current approaches are plagued by dual-fold limitations: static research pipelines that decouple planning from evidence acquisition and one-shot generation paradigms that easily suffer from long-context failure issues like "loss in the middle" and hallucinations. To address these challenges, we introduce WebWeaver, a novel dual-agent framework that emulates the human research process. The planner operates in a dynamic cycle, iteratively interleaving evidence acquisition with outline optimization to produce a comprehensive, source-grounded outline linking to a memory bank of evidence. The writer then executes a hierarchical retrieval and writing process, composing the report section by section. By performing targeted retrieval of only the necessary evidence from the memory bank for each part, it effectively mitigates long-context issues. Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym. These results validate our human-centric, iterative methodology, demonstrating that adaptive planning and focused synthesis are crucial for producing high-quality, reliable, and well-structured reports.</p> + https://arxiv.org/abs/2509.13312 + Tue, 16 Sep 2025 17:57:21 +0000 - NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale - https://arxiv.org/abs/2508.10711 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10711.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> NextStep Team, Chunrui Han, Guopeng Li, Jingwei Wu, Quan Sun, Yan Cai, Yuang Peng, Zheng Ge, Deyu Zhou, Haomiao Tang, Hongyu Zhou, Kenkun Liu, Ailin Huang, Bin Wang, Changxin Miao, Deshan Sun, En Yu, Fukun Yin, Gang Yu, Hao Nie, Haoran Lv, Hanpeng Hu, Jia Wang, Jian Zhou, Jianjian Sun, Kaijun Tan, Kang An, Kangheng Lin, Liang Zhao, Mei Chen, Peng Xing, Rui Wang, Shiyu Liu, Shutao Xia, Tianhao You, Wei Ji, Xianfang Zeng, Xin Han, Xuelin Zhang, Yana Wei, Yanming Xu, Yimin Jiang, Yingming Wang, Yu Zhou, Yucheng Han, Ziyang Meng, Binxing Jiao, Daxin Jiang, Xiangyu Zhang, Yibo Zhu</p><p><b>Upvotes:</b> 139</p><p><b>Summary:</b> Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with quantization loss. In this paper, we push the autoregressive paradigm forward with NextStep-1, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives. NextStep-1 achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis. Furthermore, our method shows strong performance in image editing, highlighting the power and versatility of our unified approach. To facilitate open research, we will release our code and models to the community.</p> - https://arxiv.org/abs/2508.10711 - Thu, 14 Aug 2025 14:54:22 +0000 + ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization + https://arxiv.org/abs/2509.13313 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.13313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xixi Wu, Kuan Li, Yida Zhao, Liwen Zhang, Litu Ou, Huifeng Yin, Zhongwang Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Minhao Cheng, Shuai Wang, Hong Cheng, Jingren Zhou</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> Large Language Model (LLM)-based web agents demonstrate strong performance on knowledge-intensive tasks but are hindered by context window limitations in paradigms like ReAct. Complex queries involving multiple entities, intertwined relationships, and high uncertainty demand extensive search cycles that rapidly exhaust context budgets before reaching complete solutions. To overcome this challenge, we introduce ReSum, a novel paradigm that enables indefinite exploration through periodic context summarization. ReSum converts growing interaction histories into compact reasoning states, maintaining awareness of prior discoveries while bypassing context constraints. For paradigm adaptation, we propose ReSum-GRPO, integrating GRPO with segmented trajectory training and advantage broadcasting to familiarize agents with summary-conditioned reasoning. Extensive experiments on web agents of varying scales across three benchmarks demonstrate that ReSum delivers an average absolute improvement of 4.5\% over ReAct, with further gains of up to 8.2\% following ReSum-GRPO training. Notably, with only 1K training samples, our WebResummer-30B (a ReSum-GRPO-trained version of WebSailor-30B) achieves 33.3\% Pass@1 on BrowseComp-zh and 18.3\% on BrowseComp-en, surpassing existing open-source web agents.</p> + https://arxiv.org/abs/2509.13313 + Tue, 16 Sep 2025 17:57:22 +0000 - UI-Venus Technical Report: Building High-performance UI Agents with RFT - https://arxiv.org/abs/2508.10833 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10833.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhangxuan Gu, Zhengwen Zeng, Zhenyu Xu, Xingran Zhou, Shuheng Shen, Yunfei Liu, Beitong Zhou, Changhua Meng, Tianyu Xia, Weizhi Chen, Yue Wen, Jingya Dou, Fei Tang, Jinzhen Lin, Yulin Liu, Zhenlin Guo, Yichen Gong, Heng Jia, Changlong Gao, Yuan Guo, Yong Deng, Zhenyu Guo, Liang Chen, Weiqiang Wang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> We present UI-Venus, a native UI agent that takes only screenshots as input based on a multimodal large language model. UI-Venus achieves SOTA performance on both UI grounding and navigation tasks using only several hundred thousand high-quality training samples through reinforcement finetune (RFT) based on Qwen2.5-VL. Specifically, the 7B and 72B variants of UI-Venus obtain 94.1% / 50.8% and 95.3% / 61.9% on the standard grounding benchmarks, i.e., Screenspot-V2 / Pro, surpassing the previous SOTA baselines including open-source GTA1 and closed-source UI-TARS-1.5.To show UI-Venus's summary and planing ability, we also evaluate it on the AndroidWorld, an online UI navigation arena, on which our 7B and 72B variants achieve 49.1% and 65.9% success rate, also beating existing models.To achieve this, we introduce carefully designed reward functions for both UI grounding and navigation tasks and corresponding efficient data cleaning strategies.To further boost navigation performance, we propose Self-Evolving Trajectory History Alignment \& Sparse Action Enhancement that refine historical reasoning traces and balances the distribution of sparse but critical actions, leading to more coherent planning and better generalization in complex UI tasks. Our contributions include the publish of SOTA open-source UI agents, comprehensive data cleaning protocols and a novel self-evolving framework for improving navigation performance, which encourage further research and development in the community. Code is available at https://github.com/antgroup/UI-Venus.</p> - https://arxiv.org/abs/2508.10833 - Thu, 14 Aug 2025 16:58:07 +0000 + MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe + https://arxiv.org/abs/2509.18154 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18154.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Yu, Zefan Wang, Chongyi Wang, Fuwei Huang, Wenshuo Ma, Zhihui He, Tianchi Cai, Weize Chen, Yuxiang Huang, Yuanqian Zhao, Bokai Xu, Junbo Cui, Yingjing Xu, Liqing Ruan, Luoyuan Zhang, Hanyu Liu, Jingkun Tang, Hongyuan Liu, Qining Guo, Wenhao Hu, Bingxiang He, Jie Zhou, Jie Cai, Ji Qi, Zonghao Guo, Chi Chen, Guoyang Zeng, Yuxuan Li, Ganqu Cui, Ning Ding, Xu Han, Yuan Yao, Zhiyuan Liu, Maosong Sun</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) are undergoing rapid progress and represent the frontier of AI development. However, their training and inference efficiency have emerged as a core bottleneck in making MLLMs more accessible and scalable. To address the challenges, we present MiniCPM-V 4.5, an 8B parameter model designed for high efficiency and strong performance. We introduce three core improvements in model architecture, data strategy and training method: a unified 3D-Resampler model architecture for highly compact encoding over images and videos, a unified learning paradigm for document knowledge and text recognition without heavy data engineering, and a hybrid reinforcement learning strategy for proficiency in both short and long reasoning modes. Comprehensive experimental results in OpenCompass evaluation show that MiniCPM-V 4.5 surpasses widely used proprietary models such as GPT-4o-latest, and significantly larger open-source models such as Qwen2.5-VL 72B. Notably, the strong performance is achieved with remarkable efficiency. For example, on the widely adopted VideoMME benchmark, MiniCPM-V 4.5 achieves state-of-the-art performance among models under 30B size, using just 46.7\% GPU memory cost and 8.7\% inference time of Qwen2.5-VL 7B.</p> + https://arxiv.org/abs/2509.18154 + Tue, 16 Sep 2025 19:41:48 +0000 - SSRL: Self-Search Reinforcement Learning - https://arxiv.org/abs/2508.10874 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10874.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Fan, Kaiyan Zhang, Heng Zhou, Yuxin Zuo, Yanxu Chen, Yu Fu, Xinwei Long, Xuekai Zhu, Che Jiang, Yuchen Zhang, Li Kang, Gang Chen, Cheng Huang, Zhizhou He, Bingning Wang, Lei Bai, Ning Ding, Bowen Zhou</p><p><b>Upvotes:</b> 90</p><p><b>Summary:</b> We investigate the potential of large language models (LLMs) to serve as efficient simulators for agentic search tasks in reinforcement learning (RL), thereby reducing dependence on costly interactions with external search engines. To this end, we first quantify the intrinsic search capability of LLMs via structured prompting and repeated sampling, which we term Self-Search. Our results reveal that LLMs exhibit strong scaling behavior with respect to the inference budget, achieving high pass@k on question-answering benchmarks, including the challenging BrowseComp task. Building on these observations, we introduce Self-Search RL (SSRL), which enhances LLMs' Self-Search capability through format-based and rule-based rewards. SSRL enables models to iteratively refine their knowledge utilization internally, without requiring access to external tools. Empirical evaluations demonstrate that SSRL-trained policy models provide a cost-effective and stable environment for search-driven RL training, reducing reliance on external search engines and facilitating robust sim-to-real transfer. We draw the following conclusions: 1) LLMs possess world knowledge that can be effectively elicited to achieve high performance; 2) SSRL demonstrates the potential of leveraging internal knowledge to reduce hallucination; 3) SSRL-trained models integrate seamlessly with external search engines without additional effort. Our findings highlight the potential of LLMs to support more scalable RL agent training.</p> - https://arxiv.org/abs/2508.10874 - Thu, 14 Aug 2025 17:46:01 +0000 + Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale + https://arxiv.org/abs/2509.14008 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hasan Abed Al Kader Hammoud, Mohammad Zbeeb, Bernard Ghanem</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> We present Hala, a family of Arabic-centric instruction and translation models built with our translate-and-tune pipeline. We first compress a strong ARleftrightarrowEN teacher to FP8 (yielding sim2times higher throughput with no quality loss) and use it to create high-fidelity bilingual supervision. A lightweight language model LFM2-1.2B is then fine-tuned on this data and used to translate high-quality English instruction sets into Arabic, producing a million-scale corpus tailored to instruction following. We train Hala models at 350M, 700M, 1.2B, and 9B parameters, and apply slerp merging to balance Arabic specialization with base-model strengths. On Arabic-centric benchmarks, Hala achieves state-of-the-art results within both the "nano" (leq2B) and "small" (7-9B) categories, outperforming their bases. We release models, data, evaluation, and recipes to accelerate research in Arabic NLP.</p> + https://arxiv.org/abs/2509.14008 + Wed, 17 Sep 2025 14:19:28 +0000 - A Survey on Diffusion Language Models - https://arxiv.org/abs/2508.10875 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10875.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyi Li, Mingda Chen, Bowei Guo, Zhiqiang Shen</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent advantages in reducing inference latency and capturing bidirectional context, thereby enabling fine-grained control over the generation process. While achieving a several-fold speed-up, recent advancements have allowed DLMs to show performance comparable to their autoregressive counterparts, making them a compelling choice for various natural language processing tasks. In this survey, we provide a holistic overview of the current DLM landscape. We trace its evolution and relationship with other paradigms, such as autoregressive and masked language models, and cover both foundational principles and state-of-the-art models. Our work offers an up-to-date, comprehensive taxonomy and an in-depth analysis of current techniques, from pre-training strategies to advanced post-training methods. Another contribution of this survey is a thorough review of DLM inference strategies and optimizations, including improvements in decoding parallelism, caching mechanisms, and generation quality. We also highlight the latest approaches to multimodal extensions of DLMs and delineate their applications across various practical scenarios. Furthermore, our discussion addresses the limitations and challenges of DLMs, including efficiency, long-sequence handling, and infrastructure requirements, while outlining future research directions to sustain progress in this rapidly evolving field. Project GitHub is available at https://github.com/VILA-Lab/Awesome-DLMs.</p> - https://arxiv.org/abs/2508.10875 - Thu, 14 Aug 2025 17:47:22 +0000 + SAIL-VL2 Technical Report + https://arxiv.org/abs/2509.14033 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14033.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weijie Yin, Yongjie Ye, Fangxun Shu, Yue Liao, Zijian Kang, Hongyuan Dong, Haiyang Yu, Dingkang Yang, Jiacong Wang, Han Wang, Wenzhuo Liu, Xiao Liang, Shuicheng Yan, Chao Feng</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> We introduce SAIL-VL2, an open-suite vision-language foundation model (LVM) for comprehensive multimodal understanding and reasoning. As the successor to SAIL-VL, SAIL-VL2 achieves state-of-the-art performance at the 2B and 8B parameter scales across diverse image and video benchmarks, demonstrating strong capabilities from fine-grained perception to complex reasoning. Three core innovations drive its effectiveness. First, a large-scale data curation pipeline with scoring and filtering strategies enhances both quality and distribution across captioning, OCR, QA, and video data, improving training efficiency. Second, a progressive training framework begins with a powerful pre-trained vision encoder (SAIL-ViT), advances through multimodal pre-training, and culminates in a thinking-fusion SFT-RL hybrid paradigm that systematically strengthens model capabilities. Third, architectural advances extend beyond dense LLMs to efficient sparse Mixture-of-Experts (MoE) designs. With these contributions, SAIL-VL2 demonstrates competitive performance across 106 datasets and achieves state-of-the-art results on challenging reasoning benchmarks such as MMMU and MathVista. Furthermore, on the OpenCompass leaderboard, SAIL-VL2-2B ranks first among officially released open-source models under the 4B parameter scale, while serving as an efficient and extensible foundation for the open-source multimodal community.</p> + https://arxiv.org/abs/2509.14033 + Wed, 17 Sep 2025 14:34:02 +0000 - ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing - https://arxiv.org/abs/2508.10881 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lingen Li, Guangzhi Wang, Zhaoyang Zhang, Yaowei Li, Xiaoyu Li, Qi Dou, Jinwei Gu, Tianfan Xue, Ying Shan</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Traditional cartoon and anime production involves keyframing, inbetweening, and colorization stages, which require intensive manual effort. Despite recent advances in AI, existing methods often handle these stages separately, leading to error accumulation and artifacts. For instance, inbetweening approaches struggle with large motions, while colorization methods require dense per-frame sketches. To address this, we introduce ToonComposer, a generative model that unifies inbetweening and colorization into a single post-keyframing stage. ToonComposer employs a sparse sketch injection mechanism to provide precise control using keyframe sketches. Additionally, it uses a cartoon adaptation method with the spatial low-rank adapter to tailor a modern video foundation model to the cartoon domain while keeping its temporal prior intact. Requiring as few as a single sketch and a colored reference frame, ToonComposer excels with sparse inputs, while also supporting multiple sketches at any temporal location for more precise motion control. This dual capability reduces manual workload and improves flexibility, empowering artists in real-world scenarios. To evaluate our model, we further created PKBench, a benchmark featuring human-drawn sketches that simulate real-world use cases. Our evaluation demonstrates that ToonComposer outperforms existing methods in visual quality, motion consistency, and production efficiency, offering a superior and more flexible solution for AI-assisted cartoon production.</p> - https://arxiv.org/abs/2508.10881 - Thu, 14 Aug 2025 17:50:11 +0000 + Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR + https://arxiv.org/abs/2509.18174 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18174.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Khalil Hennara, Muhammad Hreden, Mohamed Motasim Hamed, Ahmad Bastati, Zeina Aldallal, Sara Chrouf, Safwan AlModhayan</p><p><b>Upvotes:</b> 121</p><p><b>Summary:</b> Arabic document OCR remains a challenging task due to the language's cursive script, diverse fonts, diacritics, and right-to-left orientation. While modern Multimodal Large Language Models (MLLMs) have advanced document understanding for high-resource languages, their performance on Arabic remains limited. In this work, we introduce Baseer, a vision-language model fine- tuned specifically for Arabic document OCR. Leveraging a large-scale dataset combining synthetic and real-world documents, Baseer is trained using a decoder-only fine-tuning strategy to adapt a pre-trained MLLM while preserving general visual features. We also present Misraj-DocOCR, a high-quality, expert-verified benchmark designed for rigorous evaluation of Arabic OCR systems. Our experiments show that Baseer significantly outperforms existing open-source and commercial solutions, achieving a WER of 0.25 and establishing a new state-of-the-art in the domain of Arabic document OCR. Our results highlight the benefits of domain-specific adaptation of general-purpose MLLMs and establish a strong baseline for high-accuracy OCR on morphologically rich languages like Arabic.</p> + https://arxiv.org/abs/2509.18174 + Wed, 17 Sep 2025 15:07:29 +0000 - BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining - https://arxiv.org/abs/2508.10975 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10975.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pratyush Maini, Vineeth Dorna, Parth Doshi, Aldo Carranza, Fan Pan, Jack Urbanek, Paul Burstein, Alex Fang, Alvin Deng, Amro Abbas, Brett Larsen, Cody Blakeney, Charvi Bannur, Christina Baek, Darren Teh, David Schwab, Haakon Mongstad, Haoli Yin, Josh Wills, Kaleigh Mentzer, Luke Merrick, Ricardo Monti, Rishabh Adiga, Siddharth Joshi, Spandan Das, Zhengping Wang, Bogdan Gaza, Ari Morcos, Matthew Leavitt</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Recent advances in large language model (LLM) pretraining have shown that simply scaling data quantity eventually leads to diminishing returns, hitting a data wall. In response, the use of synthetic data for pretraining has emerged as a promising paradigm for pushing the frontier of performance. Despite this, the factors affecting synthetic data quality remain poorly understood. In this work, we introduce BeyondWeb, a synthetic data generation framework that produces high-quality synthetic data for pretraining. BeyondWeb significantly extends the capabilities of traditional web-scale datasets, outperforming state-of-the-art synthetic pretraining datasets such as Cosmopedia and Nemotron-CC's high-quality synthetic subset (Nemotron-Synth) by up to 5.1 percentage points (pp) and 2.6pp, respectively, when averaged across a suite of 14 benchmark evaluations. It delivers up to 7.7x faster training than open web data and 2.7x faster than Nemotron-Synth. Remarkably, a 3B model trained for 180B tokens on BeyondWeb outperforms an 8B model trained for the same token budget on Cosmopedia. We also present several insights from BeyondWeb on synthetic data for pretraining: what drives its benefits, which data to rephrase and how, and the impact of model size and family on data quality. Overall, our work shows that there's no silver bullet for generating high-quality synthetic pretraining data. The best outcomes require jointly optimizing many factors, a challenging task that requires rigorous science and practical expertise. Naive approaches can yield modest improvements, potentially at great cost, while well-executed methods can yield transformative improvements, as exemplified by BeyondWeb.</p> - https://arxiv.org/abs/2508.10975 - Thu, 14 Aug 2025 17:55:47 +0000 + AToken: A Unified Tokenizer for Vision + https://arxiv.org/abs/2509.14476 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14476.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiasen Lu, Liangchen Song, Mingze Xu, Byeongjoo Ahn, Yanjun Wang, Chen Chen, Afshin Dehghan, Yinfei Yang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or understanding for single modalities, AToken encodes these diverse visual inputs into a shared 4D latent space, unifying both tasks and modalities in a single framework. Specifically, we introduce a pure transformer architecture with 4D rotary position embeddings to process visual inputs of arbitrary resolutions and temporal durations. To ensure stable training, we introduce an adversarial-free training objective that combines perceptual and Gram matrix losses, achieving state-of-the-art reconstruction quality. By employing a progressive training curriculum, AToken gradually expands from single images, videos, and 3D, and supports both continuous and discrete latent tokens. AToken achieves 0.21 rFID with 82.2% ImageNet accuracy for images, 3.01 rFVD with 32.6% MSRVTT retrieval for videos, and 28.19 PSNR with 90.9% classification accuracy for 3D. In downstream applications, AToken enables both visual generation tasks (e.g., image generation with continuous and discrete tokens, text-to-video generation, image-to-3D synthesis) and understanding tasks (e.g., multimodal LLMs), achieving competitive performance across all benchmarks. These results shed light on the next-generation multimodal AI systems built upon unified visual tokenization.</p> + https://arxiv.org/abs/2509.14476 + Wed, 17 Sep 2025 23:11:18 +0000 - When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs - https://arxiv.org/abs/2508.11383 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.11383.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mikhail Seleznyov, Mikhail Chaichuk, Gleb Ershov, Alexander Panchenko, Elena Tutubalina, Oleg Somov</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Large Language Models (LLMs) are highly sensitive to subtle, non-semantic variations in prompt phrasing and formatting. In this work, we present the first systematic evaluation of 5 methods for improving prompt robustness within a unified experimental framework. We benchmark these techniques on 8 models from Llama, Qwen and Gemma families across 52 tasks from Natural Instructions dataset. Our evaluation covers robustness methods from both fine-tuned and in-context learning paradigms, and tests their generalization against multiple types of distribution shifts. Finally, we extend our analysis to GPT-4.1 and DeepSeek V3 to assess frontier models' current robustness to format perturbations. Our findings offer actionable insights into the relative effectiveness of these robustness methods, enabling practitioners to make informed decisions when aiming for stable and reliable LLM performance in real-world applications. Code: https://github.com/AIRI-Institute/when-punctuation-matters.</p> - https://arxiv.org/abs/2508.11383 - Fri, 15 Aug 2025 10:32:50 +0000 + SWE-QA: Can Language Models Answer Repository-level Code Questions? + https://arxiv.org/abs/2509.14635 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14635.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weihan Peng, Yuling Shi, Yuhang Wang, Xinyun Zhang, Beijun Shen, Xiaodong Gu</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Understanding and reasoning about entire software repositories is an essential capability for intelligent software engineering tools. While existing benchmarks such as CoSQA and CodeQA have advanced the field, they predominantly focus on small, self-contained code snippets. These setups fail to capture the complexity of real-world repositories, where effective understanding and reasoning often require navigating multiple files, understanding software architecture, and grounding answers in long-range code dependencies. In this paper, we present SWE-QA, a repository-level code question answering (QA) benchmark designed to facilitate research on automated QA systems in realistic code environments. SWE-QA involves 576 high-quality question-answer pairs spanning diverse categories, including intention understanding, cross-file reasoning, and multi-hop dependency analysis. To construct SWE-QA, we first crawled 77,100 GitHub issues from 11 popular repositories. Based on an analysis of naturally occurring developer questions extracted from these issues, we developed a two-level taxonomy of repository-level questions and constructed a set of seed questions for each category. For each category, we manually curated and validated questions and collected their corresponding answers. As a prototype application, we further develop SWE-QA-Agent, an agentic framework in which LLM agents reason and act to find answers automatically. We evaluate six advanced LLMs on SWE-QA under various context augmentation strategies. Experimental results highlight the promise of LLMs, particularly our SWE-QA-Agent framework, in addressing repository-level QA, while also revealing open challenges and pointing to future research directions.</p> + https://arxiv.org/abs/2509.14635 + Thu, 18 Sep 2025 05:25:32 +0000 - Ovis2.5 Technical Report - https://arxiv.org/abs/2508.11737 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.11737.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiyin Lu, Yang Li, Yu Xia, Yuwei Hu, Shanshan Zhao, Yanqing Ma, Zhichao Wei, Yinglun Li, Lunhao Duan, Jianshan Zhao, Yuxuan Han, Haijun Li, Wanying Chen, Junke Tang, Chengkun Hou, Zhixing Du, Tianli Zhou, Wenjie Zhang, Huping Ding, Jiahe Li, Wen Li, Gui Hu, Yiliang Gu, Siran Yang, Jiamang Wang, Hailong Sun, Yibo Wang, Hui Sun, Jinlong Huang, Yuping He, Shengze Shi, Weihong Zhang, Guodong Zheng, Junpeng Jiang, Sensen Gao, Yi-Feng Wu, Sijia Chen, Yuhui Chen, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang</p><p><b>Upvotes:</b> 104</p><p><b>Summary:</b> We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer that processes images at their native, variable resolutions, avoiding the degradation from fixed-resolution tiling and preserving both fine detail and global layout -- crucial for visually dense content like complex charts. To strengthen reasoning, we train the model to move beyond linear chain-of-thought and perform reflection -- including self-checking and revision. This advanced capability is exposed as an optional "thinking mode" at inference time, allowing users to trade latency for enhanced accuracy on difficult inputs. The model is trained via a comprehensive five-phase curriculum that progressively builds its skills. The process begins with foundational visual and multimodal pretraining, advances through large-scale instruction tuning, and culminates in alignment and reasoning enhancement using DPO and GRPO. To scale these upgrades efficiently, we employ multimodal data packing and hybrid parallelism, yielding a significant end-to-end speedup. We release two open-source models: Ovis2.5-9B and Ovis2.5-2B. The latter continues the "small model, big performance" philosophy of Ovis2, making it ideal for resource-constrained, on-device scenarios. On the OpenCompass multimodal leaderboard, Ovis2.5-9B averages 78.3, marking a substantial improvement over its predecessor, Ovis2-8B, and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9, establishing SOTA for its size. Beyond aggregate scores, Ovis2.5 achieves leading results on STEM benchmarks, exhibits strong capabilities on grounding and video tasks, and achieves open-source SOTA at its scale for complex chart analysis.</p> - https://arxiv.org/abs/2508.11737 - Fri, 15 Aug 2025 17:01:08 +0000 + Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration + https://arxiv.org/abs/2509.14760 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoran Zhang, Yafu Li, Xuyang Hu, Dongrui Liu, Zhilin Wang, Bo Li, Yu Cheng</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Large language models (LLMs) are increasingly applied in diverse real-world scenarios, each governed by bespoke behavioral and safety specifications (spec) custom-tailored by users or organizations. These spec, categorized into safety-spec and behavioral-spec, vary across scenarios and evolve with changing preferences and requirements. We formalize this challenge as specification alignment, focusing on LLMs' ability to follow dynamic, scenario-specific spec from both behavioral and safety perspectives. To address this challenge, we propose Align3, a lightweight method that employs Test-Time Deliberation (TTD) with hierarchical reflection and revision to reason over the specification boundaries. We further present SpecBench, a unified benchmark for measuring specification alignment, covering 5 scenarios, 103 spec, and 1,500 prompts. Experiments on 15 reasoning and 18 instruct models with several TTD methods, including Self-Refine, TPO, and MoreThink, yield three key findings: (i) test-time deliberation enhances specification alignment; (ii) Align3 advances the safety-helpfulness trade-off frontier with minimal overhead; (iii) SpecBench effectively reveals alignment gaps. These results highlight the potential of test-time deliberation as an effective strategy for reasoning over the real-world specification boundaries.</p> + https://arxiv.org/abs/2509.14760 + Thu, 18 Sep 2025 09:08:53 +0000 - Thyme: Think Beyond Images - https://arxiv.org/abs/2508.11630 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.11630.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi-Fan Zhang, Xingyu Lu, Shukang Yin, Chaoyou Fu, Wei Chen, Xiao Hu, Bin Wen, Kaiyu Jiang, Changyi Liu, Tianke Zhang, Haonan Fan, Kaibing Chen, Jiankang Chen, Haojie Ding, Kaiyu Tang, Zhang Zhang, Liang Wang, Fan Yang, Tingting Gao, Guorui Zhou</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> Following OpenAI's introduction of the ``thinking with images'' concept, recent efforts have explored stimulating the use of visual information in the reasoning process to enhance model performance in perception and reasoning tasks. However, to the best of our knowledge, no open-source work currently offers a feature set as rich as proprietary models (O3), which can perform diverse image manipulations and simultaneously enhance logical reasoning capabilities through code. In this paper, we make a preliminary attempt in this direction by introducing Thyme (Think Beyond Images), a novel paradigm for enabling MLLMs to transcend existing ``think with images'' approaches by autonomously generating and executing diverse image processing and computational operations via executable code. This approach not only facilitates a rich, on-the-fly set of image manipulations (e.g., cropping, rotation, contrast enhancement) but also allows for mathematical computations, all while maintaining high autonomy in deciding when and how to apply these operations. We activate this capability through a two-stage training strategy: an initial SFT on a curated dataset of 500K samples to teach code generation, followed by a RL phase to refine decision-making. For the RL stage, we manually collect and design high-resolution question-answer pairs to increase the learning difficulty, and we propose GRPO-ATS (Group Relative Policy Optimization with Adaptive Temperature Sampling), an algorithm that applies distinct temperatures to text and code generation to balance reasoning exploration with code execution precision. We conduct extensive experimental analysis and ablation studies. Comprehensive evaluations on nearly 20 benchmarks show that Thyme yields significant and consistent performance gains, particularly in challenging high-resolution perception and complex reasoning tasks.</p> - https://arxiv.org/abs/2508.11630 - Fri, 15 Aug 2025 17:59:49 +0000 + Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation + https://arxiv.org/abs/2509.15194 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15194.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujun Zhou, Zhenwen Liang, Haolin Liu, Wenhao Yu, Kishan Panaganti, Linfeng Song, Dian Yu, Xiangliang Zhang, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR), yet real-world deployment demands models that can self-improve without labels or external judges. Existing label-free methods, confidence minimization, self-consistency, or majority-vote objectives, stabilize learning but steadily shrink exploration, causing an entropy collapse: generations become shorter, less diverse, and brittle. Unlike prior approaches such as Test-Time Reinforcement Learning (TTRL), which primarily adapt models to the immediate unlabeled dataset at hand, our goal is broader: to enable general improvements without sacrificing the model's inherent exploration capacity and generalization ability, i.e., evolving. We formalize this issue and propose EVolution-Oriented and Label-free Reinforcement Learning (EVOL-RL), a simple rule that couples stability with variation under a label-free setting. EVOL-RL keeps the majority-voted answer as a stable anchor (selection) while adding a novelty-aware reward that favors responses whose reasoning differs from what has already been produced (variation), measured in semantic space. Implemented with GRPO, EVOL-RL also uses asymmetric clipping to preserve strong signals and an entropy regularizer to sustain search. This majority-for-selection + novelty-for-variation design prevents collapse, maintains longer and more informative chains of thought, and improves both pass@1 and pass@n. EVOL-RL consistently outperforms the majority-only TTRL baseline; e.g., training on label-free AIME24 lifts Qwen3-4B-Base AIME25 pass@1 from TTRL's 4.6% to 16.4%, and pass@16 from 18.5% to 37.9%. EVOL-RL not only prevents diversity collapse but also unlocks stronger generalization across domains (e.g., GPQA). Furthermore, we demonstrate that EVOL-RL also boosts performance in the RLVR setting, highlighting its broad applicability.</p> + https://arxiv.org/abs/2509.15194 + Thu, 18 Sep 2025 17:50:04 +0000 - FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction - https://arxiv.org/abs/2508.11987 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.11987.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Zeng, Jiashuo Liu, Siyuan Chen, Tianci He, Yali Liao, Jinpeng Wang, Zaiyuan Wang, Yang Yang, Lingyue Yin, Mingren Yin, Zhenwei Zhu, Tianle Cai, Zehui Chen, Jiecao Chen, Yantao Du, Xiang Gao, Jiacheng Guo, Liang Hu, Jianpeng Jiao, Xiangsheng Li, Jingkai Liu, Shuang Ni, Zhoufutu Wen, Ge Zhang, Kaiyuan Zhang, Xin Zhou, Jose Blanchet, Xipeng Qiu, Mengdi Wang, Wenhao Huang</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Future prediction is a complex task for LLM agents, requiring a high level of analytical thinking, information gathering, contextual understanding, and decision-making under uncertainty. Agents must not only gather and interpret vast amounts of dynamic information but also integrate diverse data sources, weigh uncertainties, and adapt predictions based on emerging trends, just as human experts do in fields like politics, economics, and finance. Despite its importance, no large-scale benchmark exists for evaluating agents on future prediction, largely due to challenges in handling real-time updates and retrieving timely, accurate answers. To address this, we introduce FutureX, a dynamic and live evaluation benchmark specifically designed for LLM agents performing future prediction tasks. FutureX is the largest and most diverse live benchmark for future prediction, supporting real-time daily updates and eliminating data contamination through an automated pipeline for question gathering and answer collection. We evaluate 25 LLM/agent models, including those with reasoning, search capabilities, and integration of external tools such as the open-source Deep Research Agent and closed-source Deep Research models. This comprehensive evaluation assesses agents' adaptive reasoning and performance in dynamic environments. Additionally, we provide in-depth analyses of agents' failure modes and performance pitfalls in future-oriented tasks, including the vulnerability to fake web pages and the temporal validity. Our goal is to establish a dynamic, contamination-free evaluation standard that drives the development of LLM agents capable of performing at the level of professional human analysts in complex reasoning and predictive thinking.</p> - https://arxiv.org/abs/2508.11987 - Sat, 16 Aug 2025 08:54:08 +0000 + FlowRL: Matching Reward Distributions for LLM Reasoning + https://arxiv.org/abs/2509.15207 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15207.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang, Hengli Li, Kaiyan Zhang, Che Jiang, Youbang Sun, Ermo Hua, Yuxin Zuo, Xingtai Lv, Qizheng Zhang, Lin Chen, Fanghao Shao, Bo Xue, Yunchong Song, Zhenjie Yang, Ganqu Cui, Ning Ding, Jianfeng Gao, Xiaodong Liu, Bowen Zhou, Hongyuan Mei, Zhouhan Lin</p><p><b>Upvotes:</b> 103</p><p><b>Summary:</b> We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced reasoning models adopt reward-maximizing methods (\eg, PPO and GRPO), which tend to over-optimize dominant reward signals while neglecting less frequent but valid reasoning paths, thus reducing diversity. In contrast, we transform scalar rewards into a normalized target distribution using a learnable partition function, and then minimize the reverse KL divergence between the policy and the target distribution. We implement this idea as a flow-balanced optimization method that promotes diverse exploration and generalizable reasoning trajectories. We conduct experiments on math and code reasoning tasks: FlowRL achieves a significant average improvement of 10.0% over GRPO and 5.1% over PPO on math benchmarks, and performs consistently better on code reasoning tasks. These results highlight reward distribution-matching as a key step toward efficient exploration and diverse reasoning in LLM reinforcement learning.</p> + https://arxiv.org/abs/2509.15207 + Thu, 18 Sep 2025 17:56:36 +0000 - Next Visual Granularity Generation - https://arxiv.org/abs/2508.12811 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.12811.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yikai Wang, Zhouxia Wang, Zhonghua Wu, Qingyi Tao, Kang Liao, Chen Change Loy</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> We propose a novel approach to image generation by decomposing an image into a structured sequence, where each element in the sequence shares the same spatial resolution but differs in the number of unique tokens used, capturing different level of visual granularity. Image generation is carried out through our newly introduced Next Visual Granularity (NVG) generation framework, which generates a visual granularity sequence beginning from an empty image and progressively refines it, from global layout to fine details, in a structured manner. This iterative process encodes a hierarchical, layered representation that offers fine-grained control over the generation process across multiple granularity levels. We train a series of NVG models for class-conditional image generation on the ImageNet dataset and observe clear scaling behavior. Compared to the VAR series, NVG consistently outperforms it in terms of FID scores (3.30 -> 3.03, 2.57 ->2.44, 2.09 -> 2.06). We also conduct extensive analysis to showcase the capability and potential of the NVG framework. Our code and models will be released.</p> - https://arxiv.org/abs/2508.12811 - Mon, 18 Aug 2025 10:47:37 +0000 + ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data + https://arxiv.org/abs/2509.15221 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoyang Liu, JingJing Xie, Zichen Ding, Zehao Li, Bowen Yang, Zhenyu Wu, Xuehui Wang, Qiushi Sun, Shi Liu, Weiyun Wang, Shenglong Ye, Qingyun Li, Zeyue Tian, Gen Luo, Xiangyu Yue, Biqing Qi, Kai Chen, Bowen Zhou, Yu Qiao, Qifeng Chen, Wenhai Wang</p><p><b>Upvotes:</b> 102</p><p><b>Summary:</b> Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer use data and foundation models. In this work, we introduce ScaleCUA, a step toward scaling open-source CUAs. It offers a large-scale dataset spanning 6 operating systems and 3 task domains, built via a closed-loop pipeline uniting automated agents with human experts. Trained on this scaled-up data, ScaleCUA can operate seamlessly across platforms. Specifically, it delivers strong gains over baselines (+26.6 on WebArena-Lite-v2, +10.7 on ScreenSpot-Pro) and sets new state-of-the-art results (94.4% on MMBench-GUI L1-Hard, 60.6% on OSWorld-G, 47.4% on WebArena-Lite-v2). These findings underscore the power of data-driven scaling for general-purpose computer use agents. We will release data, models, and code to advance future research: https://github.com/OpenGVLab/ScaleCUA.</p> + https://arxiv.org/abs/2509.15221 + Thu, 18 Sep 2025 17:59:22 +0000 - S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models - https://arxiv.org/abs/2508.12880 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.12880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chubin Chen, Jiashu Zhu, Xiaokun Feng, Nisha Huang, Meiqi Wu, Fangyuan Mao, Jiahong Wu, Xiangxiang Chu, Xiu Li</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Classifier-free Guidance (CFG) is a widely used technique in modern diffusion models for enhancing sample quality and prompt adherence. However, through an empirical analysis on Gaussian mixture modeling with a closed-form solution, we observe a discrepancy between the suboptimal results produced by CFG and the ground truth. The model's excessive reliance on these suboptimal predictions often leads to semantic incoherence and low-quality outputs. To address this issue, we first empirically demonstrate that the model's suboptimal predictions can be effectively refined using sub-networks of the model itself. Building on this insight, we propose S^2-Guidance, a novel method that leverages stochastic block-dropping during the forward process to construct stochastic sub-networks, effectively guiding the model away from potential low-quality predictions and toward high-quality outputs. Extensive qualitative and quantitative experiments on text-to-image and text-to-video generation tasks demonstrate that S^2-Guidance delivers superior performance, consistently surpassing CFG and other advanced guidance strategies. Our code will be released.</p> - https://arxiv.org/abs/2508.12880 - Mon, 18 Aug 2025 12:31:20 +0000 + Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification + https://arxiv.org/abs/2509.15591 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.15591.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zinan Lin, Enshu Liu, Xuefei Ning, Junyi Zhu, Wenyu Wang, Sergey Yekhanin</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Generative modeling, representation learning, and classification are three core problems in machine learning (ML), yet their state-of-the-art (SoTA) solutions remain largely disjoint. In this paper, we ask: Can a unified principle address all three? Such unification could simplify ML pipelines and foster greater synergy across tasks. We introduce Latent Zoning Network (LZN) as a step toward this goal. At its core, LZN creates a shared Gaussian latent space that encodes information across all tasks. Each data type (e.g., images, text, labels) is equipped with an encoder that maps samples to disjoint latent zones, and a decoder that maps latents back to data. ML tasks are expressed as compositions of these encoders and decoders: for example, label-conditional image generation uses a label encoder and image decoder; image embedding uses an image encoder; classification uses an image encoder and label decoder. We demonstrate the promise of LZN in three increasingly complex scenarios: (1) LZN can enhance existing models (image generation): When combined with the SoTA Rectified Flow model, LZN improves FID on CIFAR10 from 2.76 to 2.59-without modifying the training objective. (2) LZN can solve tasks independently (representation learning): LZN can implement unsupervised representation learning without auxiliary loss functions, outperforming the seminal MoCo and SimCLR methods by 9.3% and 0.2%, respectively, on downstream linear classification on ImageNet. (3) LZN can solve multiple tasks simultaneously (joint generation and classification): With image and label encoders/decoders, LZN performs both tasks jointly by design, improving FID and achieving SoTA classification accuracy on CIFAR10. The code and trained models are available at https://github.com/microsoft/latent-zoning-networks. The project website is at https://zinanlin.me/blogs/latent_zoning_networks.html.</p> + https://arxiv.org/abs/2509.15591 + Fri, 19 Sep 2025 04:47:16 +0000 - Has GPT-5 Achieved Spatial Intelligence? An Empirical Study - https://arxiv.org/abs/2508.13142 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.13142.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongang Cai, Yubo Wang, Qingping Sun, Ruisi Wang, Chenyang Gu, Wanqi Yin, Zhiqian Lin, Zhitao Yang, Chen Wei, Xuanke Shi, Kewang Deng, Xiaoyang Han, Zukai Chen, Jiaqi Li, Xiangyu Fan, Hanming Deng, Lewei Lu, Bo Li, Ziwei Liu, Quan Wang, Dahua Lin, Lei Yang</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Multi-modal models have achieved remarkable progress in recent years. Nevertheless, they continue to exhibit notable limitations in spatial understanding and reasoning, which are fundamental capabilities to achieving artificial general intelligence. With the recent release of GPT-5, allegedly the most powerful AI model to date, it is timely to examine where the leading models stand on the path toward spatial intelligence. First, we propose a comprehensive taxonomy of spatial tasks that unifies existing benchmarks and discuss the challenges in ensuring fair evaluation. We then evaluate state-of-the-art proprietary and open-source models on eight key benchmarks, at a cost exceeding one billion total tokens. Our empirical study reveals that (1) GPT-5 demonstrates unprecedented strength in spatial intelligence, yet (2) still falls short of human performance across a broad spectrum of tasks. Moreover, we (3) identify the more challenging spatial intelligence problems for multi-modal models, and (4) proprietary models do not exhibit a decisive advantage when facing the most difficult problems. In addition, we conduct a qualitative evaluation across a diverse set of scenarios that are intuitive for humans yet fail even the most advanced multi-modal models.</p> - https://arxiv.org/abs/2508.13142 - Mon, 18 Aug 2025 17:55:17 +0000 + MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer + https://arxiv.org/abs/2509.16197 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.16197.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, Haoshuo Huang, Bowen Zhang, Jialing Tong, Haoxuan You, Xianzhi Du, Zhe Gan, Hyunjik Kim, Chao Jia, Zhenbang Wang, Yinfei Yang, Mingfei Gao, Zi-Yi Dou, Wenze Hu, Chang Gao, Dongxu Li, Philipp Dufter, Zirui Wang, Guoli Yin, Zhengdong Zhang, Chen Chen, Yang Zhao, Ruoming Pang, Zhifeng Chen</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from a performance trade-off between these capabilities. We present Manzano, a simple and scalable unified framework that substantially reduces this tension by coupling a hybrid image tokenizer with a well-curated training recipe. A single shared vision encoder feeds two lightweight adapters that produce continuous embeddings for image-to-text understanding and discrete tokens for text-to-image generation within a common semantic space. A unified autoregressive LLM predicts high-level semantics in the form of text and image tokens, with an auxiliary diffusion decoder subsequently translating the image tokens into pixels. The architecture, together with a unified training recipe over understanding and generation data, enables scalable joint learning of both capabilities. Manzano achieves state-of-the-art results among unified models, and is competitive with specialist models, particularly on text-rich evaluation. Our studies show minimal task conflicts and consistent gains from scaling model size, validating our design choice of a hybrid tokenizer.</p> + https://arxiv.org/abs/2509.16197 + Fri, 19 Sep 2025 17:58:00 +0000 - 4DNeX: Feed-Forward 4D Generative Modeling Made Easy - https://arxiv.org/abs/2508.13154 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.13154.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoxi Chen, Tianqi Liu, Long Zhuo, Jiawei Ren, Zeng Tao, He Zhu, Fangzhou Hong, Liang Pan, Ziwei Liu</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on computationally intensive optimization or require multi-frame video inputs, 4DNeX enables efficient, end-to-end image-to-4D generation by fine-tuning a pretrained video diffusion model. Specifically, 1) to alleviate the scarcity of 4D data, we construct 4DNeX-10M, a large-scale dataset with high-quality 4D annotations generated using advanced reconstruction approaches. 2) we introduce a unified 6D video representation that jointly models RGB and XYZ sequences, facilitating structured learning of both appearance and geometry. 3) we propose a set of simple yet effective adaptation strategies to repurpose pretrained video diffusion models for 4D modeling. 4DNeX produces high-quality dynamic point clouds that enable novel-view video synthesis. Extensive experiments demonstrate that 4DNeX outperforms existing 4D generation methods in efficiency and generalizability, offering a scalable solution for image-to-4D modeling and laying the foundation for generative 4D world models that simulate dynamic scene evolution.</p> - https://arxiv.org/abs/2508.13154 - Mon, 18 Aug 2025 17:59:55 +0000 + RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation + https://arxiv.org/abs/2509.16198 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.16198.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jane Luo, Xin Zhang, Steven Liu, Jie Wu, Yiming Huang, Yangyu Huang, Chengyu Yin, Ying Xin, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qi Chen, Scarlett Li, Mao Yang</p><p><b>Upvotes:</b> 119</p><p><b>Summary:</b> Large language models excel at function- and file-level code generation, yet generating complete repositories from scratch remains a fundamental challenge. This process demands coherent and reliable planning across proposal- and implementation-level stages, while natural language, due to its ambiguity and verbosity, is ill-suited for faithfully representing complex software structures. To address this, we introduce the Repository Planning Graph (RPG), a persistent representation that unifies proposal- and implementation-level planning by encoding capabilities, file structures, data flows, and functions in one graph. RPG replaces ambiguous natural language with an explicit blueprint, enabling long-horizon planning and scalable repository generation. Building on RPG, we develop ZeroRepo, a graph-driven framework for repository generation from scratch. It operates in three stages: proposal-level planning and implementation-level refinement to construct the graph, followed by graph-guided code generation with test validation. To evaluate this setting, we construct RepoCraft, a benchmark of six real-world projects with 1,052 tasks. On RepoCraft, ZeroRepo produces repositories averaging nearly 36K LOC, roughly 3.9times the strongest baseline (Claude Code) and about 64times other baselines. It attains 81.5% functional coverage and a 69.7% pass rate, exceeding Claude Code by 27.3 and 35.8 percentage points, respectively. Further analysis shows that RPG models complex dependencies, enables progressively more sophisticated planning through near-linear scaling, and enhances LLM understanding of repositories, thereby accelerating agent localization.</p> + https://arxiv.org/abs/2509.16198 + Fri, 19 Sep 2025 17:58:14 +0000 - From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models - https://arxiv.org/abs/2508.13491 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.13491.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyan Kuang, Feiyu Zhu, Maowei Jiang, Yanzhao Lai, Zelin Wang, Zhitong Wang, Meikang Qiu, Jiajia Huang, Min Peng, Qianqian Xie, Sophia Ananiadou</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Large Language Models (LLMs) have shown promise for financial applications, yet their suitability for this high-stakes domain remains largely unproven due to inadequacies in existing benchmarks. Existing benchmarks solely rely on score-level evaluation, summarizing performance with a single score that obscures the nuanced understanding of what models truly know and their precise limitations. They also rely on datasets that cover only a narrow subset of financial concepts, while overlooking other essentials for real-world applications. To address these gaps, we introduce FinCDM, the first cognitive diagnosis evaluation framework tailored for financial LLMs, enabling the evaluation of LLMs at the knowledge-skill level, identifying what financial skills and knowledge they have or lack based on their response patterns across skill-tagged tasks, rather than a single aggregated number. We construct CPA-QKA, the first cognitively informed financial evaluation dataset derived from the Certified Public Accountant (CPA) examination, with comprehensive coverage of real-world accounting and financial skills. It is rigorously annotated by domain experts, who author, validate, and annotate questions with high inter-annotator agreement and fine-grained knowledge labels. Our extensive experiments on 30 proprietary, open-source, and domain-specific LLMs show that FinCDM reveals hidden knowledge gaps, identifies under-tested areas such as tax and regulatory reasoning overlooked by traditional benchmarks, and uncovers behavioral clusters among models. FinCDM introduces a new paradigm for financial LLM evaluation by enabling interpretable, skill-aware diagnosis that supports more trustworthy and targeted model development, and all datasets and evaluation scripts will be publicly released to support further research.</p> - https://arxiv.org/abs/2508.13491 - Tue, 19 Aug 2025 03:52:15 +0000 + ARE: Scaling Up Agent Environments and Evaluations + https://arxiv.org/abs/2509.17158 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17158.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pierre Andrews, Amine Benhalloum, Gerard Moreno-Torres Bertran, Matteo Bettini, Amar Budhiraja, Ricardo Silveira Cabral, Virginie Do, Romain Froger, Emilien Garreau, Jean-Baptiste Gaya, Hugo Laurençon, Maxime Lecanu, Kunal Malkan, Dheeraj Mekala, Pierre Ménard, Grégoire Mialon, Ulyana Piterbarg, Mikhail Plekhanov, Mathieu Rita, Andrey Rusakov, Thomas Scialom, Vladislav Vorotilov, Mengjue Wang, Ian Yu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> We introduce Meta Agents Research Environments (ARE), a research platform for scalable creation of environments, integration of synthetic or real applications, and execution of agentic orchestrations. ARE provides simple abstractions to build complex and diverse environments, each with their own rules, tools, content, and verifiers, helping to bridge the gap between model development and real-world deployment. We also propose Gaia2, a benchmark built in ARE and designed to measure general agent capabilities. Beyond search and execution, Gaia2 requires agents to handle ambiguities and noise, adapt to dynamic environments, collaborate with other agents, and operate under temporal constraints. Unlike prior benchmarks, Gaia2 runs asynchronously, surfacing new failure modes that are invisible in static settings. Our experiments show that no system dominates across the intelligence spectrum: stronger reasoning often comes at the cost of efficiency, and budget scaling curves plateau, highlighting the need for new architectures and adaptive compute strategies. Perhaps more importantly, ARE abstractions enable continuous extension of Gaia2 to other environments, empowering the community to rapidly create new benchmarks tailored to their domains. In AI's second half, progress increasingly depends on defining meaningful tasks and robust evaluations to drive frontier capabilities forward.</p> + https://arxiv.org/abs/2509.17158 + Sun, 21 Sep 2025 16:59:45 +0000 - Prompt Orchestration Markup Language - https://arxiv.org/abs/2508.13948 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.13948.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuge Zhang, Nan Chen, Jiahang Xu, Yuqing Yang</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Large Language Models (LLMs) require sophisticated prompting, yet current practices face challenges in structure, data integration, format sensitivity, and tooling. Existing methods lack comprehensive solutions for organizing complex prompts involving diverse data types (documents, tables, images) or managing presentation variations systematically. To address these gaps, we introduce POML (Prompt Orchestration Markup Language). POML employs component-based markup for logical structure (roles, tasks, examples), specialized tags for seamless data integration, and a CSS-like styling system to decouple content from presentation, reducing formatting sensitivity. It includes templating for dynamic prompts and a comprehensive developer toolkit (IDE support, SDKs) to improve version control and collaboration. We validate POML through two case studies demonstrating its impact on complex application integration (PomLink) and accuracy performance (TableQA), as well as a user study assessing its effectiveness in real-world development scenarios.</p> - https://arxiv.org/abs/2508.13948 - Tue, 19 Aug 2025 15:37:29 +0000 + LIMI: Less is More for Agency + https://arxiv.org/abs/2509.17567 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17567.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Xiao, Mohan Jiang, Jie Sun, Keyu Li, Jifan Lin, Yumin Zhuang, Ji Zeng, Shijie Xia, Qishuo Hua, Xuefeng Li, Xiaojie Cai, Tongyu Wang, Yue Zhang, Liming Liu, Xia Wu, Jinlong Hou, Yuan Cheng, Wenjie Li, Xiang Wang, Dequan Wang, Pengfei Liu</p><p><b>Upvotes:</b> 94</p><p><b>Summary:</b> We define Agency as the emergent capacity of AI systems to function as autonomous agents actively discovering problems, formulating hypotheses, and executing solutions through self-directed engagement with environments and tools. This fundamental capability marks the dawn of the Age of AI Agency, driven by a critical industry shift: the urgent need for AI systems that don't just think, but work. While current AI excels at reasoning and generating responses, industries demand autonomous agents that can execute tasks, operate tools, and drive real-world outcomes. As agentic intelligence becomes the defining characteristic separating cognitive systems from productive workers, efficiently cultivating machine autonomy becomes paramount. Current approaches assume that more data yields better agency, following traditional scaling laws from language modeling. We fundamentally challenge this paradigm. LIMI (Less Is More for Intelligent Agency) demonstrates that agency follows radically different development principles. Through strategic focus on collaborative software development and scientific research workflows, we show that sophisticated agentic intelligence can emerge from minimal but strategically curated demonstrations of autonomous behavior. Using only 78 carefully designed training samples, LIMI achieves 73.5% on comprehensive agency benchmarks, dramatically outperforming state-of-the-art models: Kimi-K2-Instruct (24.1%), DeepSeek-V3.1 (11.9%), Qwen3-235B-A22B-Instruct (27.5%), and GLM-4.5 (45.1%). Most strikingly, LIMI demonstrates 53.7% improvement over models trained on 10,000 samples-achieving superior agentic intelligence with 128 times fewer samples. Our findings establish the Agency Efficiency Principle: machine autonomy emerges not from data abundance but from strategic curation of high-quality agentic demonstrations.</p> + https://arxiv.org/abs/2509.17567 + Mon, 22 Sep 2025 10:59:32 +0000 - Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR - https://arxiv.org/abs/2508.14029 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14029.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiao Liang, Zhongzhi Li, Yeyun Gong, Yelong Shen, Ying Nian Wu, Zhijiang Guo, Weizhu Chen</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a key paradigm for post-training Large Language Models (LLMs), particularly for complex reasoning tasks. However, vanilla RLVR training has been shown to improve Pass@1 performance at the expense of policy entropy, leading to reduced generation diversity and limiting the Pass@k performance, which typically represents the upper bound of LLM reasoning capability. In this paper, we systematically analyze the policy's generation diversity from the perspective of training problems and find that augmenting and updating training problems helps mitigate entropy collapse during training. Based on these observations, we propose an online Self-play with Variational problem Synthesis (SvS) strategy for RLVR training, which uses the policy's correct solutions to synthesize variational problems while ensuring their reference answers remain identical to the originals. This self-improving strategy effectively maintains policy entropy during training and substantially improves Pass@k compared with standard RLVR, sustaining prolonged improvements and achieving absolute gains of 18.3% and 22.8% in Pass@32 performance on the competition-level AIME24 and AIME25 benchmarks. Experiments on 12 reasoning benchmarks across varying model sizes from 3B to 32B consistently demonstrate the generalizability and robustness of SvS.</p> - https://arxiv.org/abs/2508.14029 - Tue, 19 Aug 2025 17:42:45 +0000 + OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models + https://arxiv.org/abs/2509.17627 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17627.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinshu Chen, Xinghui Li, Xu Bai, Tianxiang Ma, Pengze Zhang, Zhuowei Chen, Gen Li, Lijie Liu, Songtao Zhao, Bingchuan Li, Qian He</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Recent advances in video insertion based on diffusion models are impressive. However, existing methods rely on complex control signals but struggle with subject consistency, limiting their practical applicability. In this paper, we focus on the task of Mask-free Video Insertion and aim to resolve three key challenges: data scarcity, subject-scene equilibrium, and insertion harmonization. To address the data scarcity, we propose a new data pipeline InsertPipe, constructing diverse cross-pair data automatically. Building upon our data pipeline, we develop OmniInsert, a novel unified framework for mask-free video insertion from both single and multiple subject references. Specifically, to maintain subject-scene equilibrium, we introduce a simple yet effective Condition-Specific Feature Injection mechanism to distinctly inject multi-source conditions and propose a novel Progressive Training strategy that enables the model to balance feature injection from subjects and source video. Meanwhile, we design the Subject-Focused Loss to improve the detailed appearance of the subjects. To further enhance insertion harmonization, we propose an Insertive Preference Optimization methodology to optimize the model by simulating human preferences, and incorporate a Context-Aware Rephraser module during reference to seamlessly integrate the subject into the original scenes. To address the lack of a benchmark for the field, we introduce InsertBench, a comprehensive benchmark comprising diverse scenes with meticulously selected subjects. Evaluation on InsertBench indicates OmniInsert outperforms state-of-the-art closed-source commercial solutions. The code will be released.</p> + https://arxiv.org/abs/2509.17627 + Mon, 22 Sep 2025 11:35:55 +0000 - LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos - https://arxiv.org/abs/2508.14041 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14041.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chin-Yang Lin, Cheng Sun, Fu-En Yang, Min-Hung Chen, Yen-Yu Lin, Yu-Lun Liu</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer from pose drift, inaccurate geometry initialization, and severe memory limitations. To address these issues, we introduce LongSplat, a robust unposed 3D Gaussian Splatting framework featuring: (1) Incremental Joint Optimization that concurrently optimizes camera poses and 3D Gaussians to avoid local minima and ensure global consistency; (2) a robust Pose Estimation Module leveraging learned 3D priors; and (3) an efficient Octree Anchor Formation mechanism that converts dense point clouds into anchors based on spatial density. Extensive experiments on challenging benchmarks demonstrate that LongSplat achieves state-of-the-art results, substantially improving rendering quality, pose accuracy, and computational efficiency compared to prior approaches. Project page: https://linjohnss.github.io/longsplat/</p> - https://arxiv.org/abs/2508.14041 - Tue, 19 Aug 2025 17:59:56 +0000 + Qwen3-Omni Technical Report + https://arxiv.org/abs/2509.17765 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.17765.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zhang, Xinyu Zhang, Hongkun Hao, Zishan Guo, Baosong Yang, Bin Zhang, Ziyang Ma, Xipin Wei, Shuai Bai, Keqin Chen, Xuejing Liu, Peng Wang, Mingkun Yang, Dayiheng Liu, Xingzhang Ren, Bo Zheng, Rui Men, Fan Zhou, Bowen Yu, Jianxin Yang, Le Yu, Jingren Zhou, Junyang Lin</p><p><b>Upvotes:</b> 121</p><p><b>Summary:</b> We present Qwen3-Omni, a single multimodal model that, for the first time, maintains state-of-the-art performance across text, image, audio, and video without any degradation relative to single-modal counterparts. Qwen3-Omni matches the performance of same-sized single-modal models within the Qwen series and excels particularly on audio tasks. Across 36 audio and audio-visual benchmarks, Qwen3-Omni achieves open-source SOTA on 32 benchmarks and overall SOTA on 22, outperforming strong closed-source models such as Gemini-2.5-Pro, Seed-ASR, and GPT-4o-Transcribe. Qwen3-Omni adopts a Thinker-Talker MoE architecture that unifies perception and generation across text, images, audio, and video, yielding fluent text and natural real-time speech. It supports text interaction in 119 languages, speech understanding in 19 languages, and speech generation in 10 languages. To reduce first-packet latency in streaming synthesis, Talker autoregressively predicts discrete speech codecs using a multi-codebook scheme. Leveraging the representational capacity of these codebooks, we replace computationally intensive block-wise diffusion with a lightweight causal ConvNet, enabling streaming from the first codec frame. In cold-start settings, Qwen3-Omni achieves a theoretical end-to-end first-packet latency of 234 ms. To further strengthen multimodal reasoning, we introduce a Thinking model that explicitly reasons over inputs from any modality. Since the research community currently lacks a general-purpose audio captioning model, we fine-tuned Qwen3-Omni-30B-A3B to obtain Qwen3-Omni-30B-A3B-Captioner, which produces detailed, low-hallucination captions for arbitrary audio inputs. Qwen3-Omni-30B-A3B, Qwen3-Omni-30B-A3B-Thinking, and Qwen3-Omni-30B-A3B-Captioner are publicly released under the Apache 2.0 license.</p> + https://arxiv.org/abs/2509.17765 + Mon, 22 Sep 2025 13:26:24 +0000 - NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model - https://arxiv.org/abs/2508.14444 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14444.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> NVIDIA, Aarti Basant, Abhijit Khairnar, Abhijit Paithankar, Abhinav Khattar, Adi Renduchintala, Adithya Renduchintala, Aditya Malte, Akhiad Bercovich, Akshay Hazare, Alejandra Rico, Aleksander Ficek, Alex Kondratenko, Alex Shaposhnikov, Ali Taghibakhshi, Amelia Barton, Ameya Sunil Mahabaleshwarkar, Amy Shen, Andrew Tao, Ann Guan, Anna Shors, Anubhav Mandarwal, Arham Mehta, Arun Venkatesan, Ashton Sharabiani, Ashwath Aithal, Ashwin Poojary, Ayush Dattagupta, Balaram Buddharaju, Banghua Zhu, Barnaby Simkin, Bilal Kartal, Bita Darvish Rouhani, Bobby Chen, Boris Ginsburg, Brandon Norick, Brian Yu, Bryan Catanzaro, Charles Wang, Charlie Truong, Chetan Mungekar, Chintan Patel, Chris Alexiuk, Christian Munley, Christopher Parisien, Dan Su, Daniel Afrimi, Daniel Korzekwa, Daniel Rohrer, Daria Gitman, David Mosallanezhad, Deepak Narayanan, Dima Rekesh, Dina Yared, Dmytro Pykhtar, Dong Ahn, Duncan Riach, Eileen Long, Elliott Ning, Eric Chung, Erick Galinkin, Evelina Bakhturina, Gargi Prasad, Gerald Shen, Haim Elisha, Harsh Sharma, Hayley Ross, Helen Ngo, Herman Sahota, Hexin Wang, Hoo Chang Shin, Hua Huang, Iain Cunningham, Igor Gitman, Ivan Moshkov, Jaehun Jung, Jan Kautz, Jane Polak Scowcroft, Jared Casper, Jimmy Zhang, Jinze Xue, Jocelyn Huang, Joey Conway, John Kamalu, Jonathan Cohen, Joseph Jennings, Julien Veron Vialard, Junkeun Yi, Jupinder Parmar, Kari Briski, Katherine Cheung, Katherine Luna, Keith Wyss, Keshav Santhanam, Kezhi Kong, Krzysztof Pawelec, Kumar Anik, Kunlun Li, Kushan Ahmadian, Lawrence McAfee, Laya Sleiman, Leon Derczynski, Luis Vega, Maer Rodrigues de Melo, Makesh Narsimhan Sreedhar, Marcin Chochowski, Mark Cai, Markus Kliegl, Marta Stepniewska-Dziubinska, Matvei Novikov, Mehrzad Samadi, Meredith Price, Meriem Boubdir, Michael Boone, Michael Evans, Michal Bien, Michal Zawalski, Miguel Martinez, Mike Chrzanowski, Mohammad Shoeybi, Mostofa Patwary, Namit Dhameja, Nave Assaf, Negar Habibi, Nidhi Bhatia, Nikki Pope, Nima Tajbakhsh, Nirmal Kumar Juluru, Oleg Rybakov, Oleksii Hrinchuk, Oleksii Kuchaiev, Oluwatobi Olabiyi, Pablo Ribalta, Padmavathy Subramanian, Parth Chadha, Pavlo Molchanov, Peter Dykas, Peter Jin, Piotr Bialecki, Piotr Januszewski, Pradeep Thalasta, Prashant Gaikwad, Prasoon Varshney, Pritam Gundecha, Przemek Tredak, Rabeeh Karimi Mahabadi, Rajen Patel, Ran El-Yaniv, Ranjit Rajan, Ria Cheruvu, Rima Shahbazyan, Ritika Borkar, Ritu Gala, Roger Waleffe, Ruoxi Zhang, Russell J. Hewett, Ryan Prenger, Sahil Jain, Samuel Kriman, Sanjeev Satheesh, Saori Kaji, Sarah Yurick, Saurav Muralidharan, Sean Narenthiran, Seonmyeong Bak, Sepehr Sameni, Seungju Han, Shanmugam Ramasamy, Shaona Ghosh, Sharath Turuvekere Sreenivas, Shelby Thomas, Shizhe Diao, Shreya Gopal, Shrimai Prabhumoye, Shubham Toshniwal, Shuoyang Ding, Siddharth Singh, Siddhartha Jain, Somshubra Majumdar, Stefania Alborghetti, Syeda Nahida Akter, Terry Kong, Tim Moon, Tomasz Hliwiak, Tomer Asida, Tony Wang, Twinkle Vashishth, Tyler Poon, Udi Karpas, Vahid Noroozi, Venkat Srinivasan, Vijay Korthikanti, Vikram Fugro, Vineeth Kalluru, Vitaly Kurin, Vitaly Lavrukhin, Wasi Uddin Ahmad, Wei Du, Wonmin Byeon, Ximing Lu, Xin Dong, Yashaswi Karnati, Yejin Choi, Yian Zhang, Ying Lin, Yonggan Fu, Yoshi Suhara, Zhen Dong, Zhiyu Li, Zhongbo Zhu, Zijia Chen</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> We introduce Nemotron-Nano-9B-v2, a hybrid Mamba-Transformer language model designed to increase throughput for reasoning workloads while achieving state-of-the-art accuracy compared to similarly-sized models. Nemotron-Nano-9B-v2 builds on the Nemotron-H architecture, in which the majority of the self-attention layers in the common Transformer architecture are replaced with Mamba-2 layers, to achieve improved inference speed when generating the long thinking traces needed for reasoning. We create Nemotron-Nano-9B-v2 by first pre-training a 12-billion-parameter model (Nemotron-Nano-12B-v2-Base) on 20 trillion tokens using an FP8 training recipe. After aligning Nemotron-Nano-12B-v2-Base, we employ the Minitron strategy to compress and distill the model with the goal of enabling inference on up to 128k tokens on a single NVIDIA A10G GPU (22GiB of memory, bfloat16 precision). Compared to existing similarly-sized models (e.g., Qwen3-8B), we show that Nemotron-Nano-9B-v2 achieves on-par or better accuracy on reasoning benchmarks while achieving up to 6x higher inference throughput in reasoning settings like 8k input and 16k output tokens. We are releasing Nemotron-Nano-9B-v2, Nemotron-Nano12B-v2-Base, and Nemotron-Nano-9B-v2-Base checkpoints along with the majority of our pre- and post-training datasets on Hugging Face.</p> - https://arxiv.org/abs/2508.14444 - Wed, 20 Aug 2025 06:00:57 +0000 + OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System + https://arxiv.org/abs/2509.18091 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18091.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sunhao Dai, Jiakai Tang, Jiahua Wu, Kun Wang, Yuxuan Zhu, Bingjun Chen, Bangyang Hong, Yu Zhao, Cong Fu, Kangle Wu, Yabo Ni, Anxiang Zeng, Wenjie Wang, Xu Chen, Jun Xu, See-Kiong Ng</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Despite the growing interest in replicating the scaled success of large language models (LLMs) in industrial search and recommender systems, most existing industrial efforts remain limited to transplanting Transformer architectures, which bring only incremental improvements over strong Deep Learning Recommendation Models (DLRMs). From a first principle perspective, the breakthroughs of LLMs stem not only from their architectures but also from two complementary mechanisms: context engineering, which enriches raw input queries with contextual cues to better elicit model capabilities, and multi-step reasoning, which iteratively refines model outputs through intermediate reasoning paths. However, these two mechanisms and their potential to unlock substantial improvements remain largely underexplored in industrial ranking systems. In this paper, we propose OnePiece, a unified framework that seamlessly integrates LLM-style context engineering and reasoning into both retrieval and ranking models of industrial cascaded pipelines. OnePiece is built on a pure Transformer backbone and further introduces three key innovations: (1) structured context engineering, which augments interaction history with preference and scenario signals and unifies them into a structured tokenized input sequence for both retrieval and ranking; (2) block-wise latent reasoning, which equips the model with multi-step refinement of representations and scales reasoning bandwidth via block size; (3) progressive multi-task training, which leverages user feedback chains to effectively supervise reasoning steps during training. OnePiece has been deployed in the main personalized search scenario of Shopee and achieves consistent online gains across different key business metrics, including over +2% GMV/UU and a +2.90% increase in advertising revenue.</p> + https://arxiv.org/abs/2509.18091 + Mon, 22 Sep 2025 17:59:07 +0000 - DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization - https://arxiv.org/abs/2508.14460 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14460.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuaijie She, Yu Bao, Yu Lu, Lu Xu, Tao Li, Wenhao Zhu, Shujian Huang, Shanbo Cheng, Lu Lu, Yuxuan Wang</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> We present DuPO, a dual learning-based preference optimization framework that generates annotation-free feedback via a generalized duality. DuPO addresses two key limitations: Reinforcement Learning with Verifiable Rewards (RLVR)'s reliance on costly labels and applicability restricted to verifiable tasks, and traditional dual learning's restriction to strictly dual task pairs (e.g., translation and back-translation). Specifically, DuPO decomposes a primal task's input into known and unknown components, then constructs its dual task to reconstruct the unknown part using the primal output and known information (e.g., reversing math solutions to recover hidden variables), broadening applicability to non-invertible tasks. The quality of this reconstruction serves as a self-supervised reward to optimize the primal task, synergizing with LLMs' ability to instantiate both tasks via a single model. Empirically, DuPO achieves substantial gains across diverse tasks: it enhances the average translation quality by 2.13 COMET over 756 directions, boosts the mathematical reasoning accuracy by an average of 6.4 points on three challenge benchmarks, and enhances performance by 9.3 points as an inference-time reranker (trading computation for accuracy). These results position DuPO as a scalable, general, and annotation-free paradigm for LLM optimization.</p> - https://arxiv.org/abs/2508.14460 - Wed, 20 Aug 2025 06:31:18 +0000 + Do You Need Proprioceptive States in Visuomotor Policies? + https://arxiv.org/abs/2509.18644 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18644.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juntu Zhao, Wenbo Lu, Di Zhang, Yufeng Liu, Yushen Liang, Tianluo Zhang, Yifeng Cao, Junyuan Xie, Yingdong Hu, Shengjie Wang, Junliang Guo, Dequan Wang, Yang Gao</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Imitation-learning-based visuomotor policies have been widely used in robot manipulation, where both visual observations and proprioceptive states are typically adopted together for precise control. However, in this study, we find that this common practice makes the policy overly reliant on the proprioceptive state input, which causes overfitting to the training trajectories and results in poor spatial generalization. On the contrary, we propose the State-free Policy, removing the proprioceptive state input and predicting actions only conditioned on visual observations. The State-free Policy is built in the relative end-effector action space, and should ensure the full task-relevant visual observations, here provided by dual wide-angle wrist cameras. Empirical results demonstrate that the State-free policy achieves significantly stronger spatial generalization than the state-based policy: in real-world tasks such as pick-and-place, challenging shirt-folding, and complex whole-body manipulation, spanning multiple robot embodiments, the average success rate improves from 0\% to 85\% in height generalization and from 6\% to 64\% in horizontal generalization. Furthermore, they also show advantages in data efficiency and cross-embodiment adaptation, enhancing their practicality for real-world deployment.</p> + https://arxiv.org/abs/2509.18644 + Tue, 23 Sep 2025 04:56:59 +0000 - MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers - https://arxiv.org/abs/2508.14704 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14704.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyang Luo, Zhiqi Shen, Wenzhuo Yang, Zirui Zhao, Prathyusha Jwalapuram, Amrita Saha, Doyen Sahoo, Silvio Savarese, Caiming Xiong, Junnan Li</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> The Model Context Protocol has emerged as a transformative standard for connecting large language models to external data sources and tools, rapidly gaining adoption across major AI providers and development platforms. However, existing benchmarks are overly simplistic and fail to capture real application challenges such as long-horizon reasoning and large, unfamiliar tool spaces. To address this critical gap, we introduce MCP-Universe, the first comprehensive benchmark specifically designed to evaluate LLMs in realistic and hard tasks through interaction with real-world MCP servers. Our benchmark encompasses 6 core domains spanning 11 different MCP servers: Location Navigation, Repository Management, Financial Analysis, 3D Design, Browser Automation, and Web Searching. To ensure rigorous evaluation, we implement execution-based evaluators, including format evaluators for agent format compliance, static evaluators for time-invariant content matching, and dynamic evaluators that automatically retrieve real-time ground truth for temporally sensitive tasks. Through extensive evaluation of leading LLMs, we find that even SOTA models such as GPT-5 (43.72%), Grok-4 (33.33%) and Claude-4.0-Sonnet (29.44%) exhibit significant performance limitations. In addition, our benchmark poses a significant long-context challenge for LLM agents, as the number of input tokens increases rapidly with the number of interaction steps. Moreover, it introduces an unknown-tools challenge, as LLM agents often lack familiarity with the precise usage of the MCP servers. Notably, enterprise-level agents like Cursor cannot achieve better performance than standard ReAct frameworks. Beyond evaluation, we open-source our extensible evaluation framework with UI support, enabling researchers and practitioners to seamlessly integrate new agents and MCP servers while fostering innovation in the rapidly evolving MCP ecosystem.</p> - https://arxiv.org/abs/2508.14704 - Wed, 20 Aug 2025 13:28:58 +0000 + Reinforcement Learning on Pre-Training Data + https://arxiv.org/abs/2509.19249 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19249.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Evander Yang, Kun Li, Haoyuan Wu, Jiajia Wu, Zihao Zheng, Chenchen Zhang, Kun Shi, Kyrierl Deng, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang Xu, Zheng Fang, Shuai Li, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bo Chao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Wayyt Wang, Bo Zhou, Di Wang</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we introduce Reinforcement Learning on Pre-Training data (RLPT), a new training-time scaling paradigm for optimizing LLMs. In contrast to prior approaches that scale training primarily through supervised learning, RLPT enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL). While existing RL strategies such as reinforcement learning from human feedback (RLHF) and reinforcement learning with verifiable rewards (RLVR) rely on human annotation for reward construction, RLPT eliminates this dependency by deriving reward signals directly from pre-training data. Specifically, it adopts a next-segment reasoning objective, rewarding the policy for accurately predicting subsequent text segments conditioned on the preceding context. This formulation allows RL to be scaled on pre-training data, encouraging the exploration of richer trajectories across broader contexts and thereby fostering more generalizable reasoning skills. Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of RLPT. For example, when applied to Qwen3-4B-Base, RLPT yields absolute improvements of 3.0, 5.1, 8.1, 6.0, 6.6, and 5.3 on MMLU, MMLU-Pro, GPQA-Diamond, KOR-Bench, AIME24, and AIME25, respectively. The results further demonstrate favorable scaling behavior, suggesting strong potential for continued gains with more compute. In addition, RLPT provides a solid foundation, extending the reasoning boundaries of LLMs and enhancing RLVR performance.</p> + https://arxiv.org/abs/2509.19249 + Tue, 23 Sep 2025 17:10:40 +0000 - Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization - https://arxiv.org/abs/2508.14811 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14811.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Canyu Zhao, Xiaoman Li, Tianjian Feng, Zhiyue Zhao, Hao Chen, Chunhua Shen</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> We introduce Tinker, a versatile framework for high-fidelity 3D editing that operates in both one-shot and few-shot regimes without any per-scene finetuning. Unlike prior techniques that demand extensive per-scene optimization to ensure multi-view consistency or to produce dozens of consistent edited input views, Tinker delivers robust, multi-view consistent edits from as few as one or two images. This capability stems from repurposing pretrained diffusion models, which unlocks their latent 3D awareness. To drive research in this space, we curate the first large-scale multi-view editing dataset and data pipeline, spanning diverse scenes and styles. Building on this dataset, we develop our framework capable of generating multi-view consistent edited views without per-scene training, which consists of two novel components: (1) Referring multi-view editor: Enables precise, reference-driven edits that remain coherent across all viewpoints. (2) Any-view-to-video synthesizer: Leverages spatial-temporal priors from video diffusion to perform high-quality scene completion and novel-view generation even from sparse inputs. Through extensive experiments, Tinker significantly reduces the barrier to generalizable 3D content creation, achieving state-of-the-art performance on editing, novel-view synthesis, and rendering enhancement tasks. We believe that Tinker represents a key step towards truly scalable, zero-shot 3D editing. Project webpage: https://aim-uofa.github.io/Tinker</p> - https://arxiv.org/abs/2508.14811 - Wed, 20 Aug 2025 16:02:59 +0000 + VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models + https://arxiv.org/abs/2509.19803 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guochao Jiang, Wenfeng Feng, Guofeng Quan, Chuzhan Hao, Yuewei Zhang, Guohua Liu, Hao Wang</p><p><b>Upvotes:</b> 113</p><p><b>Summary:</b> Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider LLMs' learning ability for samples of different difficulty levels, which is contrary to the human cognitive process of mathematical reasoning tasks from easy to difficult. Intuitively, we find that the variance of the rollout group's reward in RLVR partly reflects the difficulty of the current sample for LLMs. Samples that are too easy or too difficult have a lower variance, while samples with moderate difficulty have a higher variance. Based on this, we propose VCRL, a curriculum reinforcement learning framework that dynamically controls the difficulty of training samples based on the variance of group rewards. Experiments on five mathematical benchmarks and two models reveal the advantages of VCRL over the current LLM RL baselines.</p> + https://arxiv.org/abs/2509.19803 + Wed, 24 Sep 2025 06:38:58 +0000 - MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds - https://arxiv.org/abs/2508.14879 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.14879.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bingquan Dai, Li Ray Luo, Qihong Tang, Jie Wang, Xinyu Lian, Hao Xu, Minghan Qin, Xudong Xu, Bo Dai, Haoqian Wang, Zhaoyang Lyu, Jiangmiao Pang</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Reconstructing 3D objects into editable programs is pivotal for applications like reverse engineering and shape editing. However, existing methods often rely on limited domain-specific languages (DSLs) and small-scale datasets, restricting their ability to model complex geometries and structures. To address these challenges, we introduce MeshCoder, a novel framework that reconstructs complex 3D objects from point clouds into editable Blender Python scripts. We develop a comprehensive set of expressive Blender Python APIs capable of synthesizing intricate geometries. Leveraging these APIs, we construct a large-scale paired object-code dataset, where the code for each object is decomposed into distinct semantic parts. Subsequently, we train a multimodal large language model (LLM) that translates 3D point cloud into executable Blender Python scripts. Our approach not only achieves superior performance in shape-to-code reconstruction tasks but also facilitates intuitive geometric and topological editing through convenient code modifications. Furthermore, our code-based representation enhances the reasoning capabilities of LLMs in 3D shape understanding tasks. Together, these contributions establish MeshCoder as a powerful and flexible solution for programmatic 3D shape reconstruction and understanding.</p> - https://arxiv.org/abs/2508.14879 - Wed, 20 Aug 2025 17:50:15 +0000 + SIM-CoT: Supervised Implicit Chain-of-Thought + https://arxiv.org/abs/2509.20317 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20317.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xilin Wei, Xiaoran Liu, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Jiaqi Wang, Xipeng Qiu, Dahua Lin</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Implicit Chain-of-Thought (CoT) methods present a promising, token-efficient alternative to explicit CoT reasoning in Large Language Models (LLMs), but a persistent performance gap has limited the application of implicit CoT. We identify a core latent instability issue by scaling the computational budget of implicit CoT approaches: as we increase the number of implicit reasoning tokens to enhance performance, the training process often becomes unstable and collapses. Our analysis reveals that this instability arises from the latent representations becoming homogeneous and losing their semantic diversity, a failure caused by insufficient step-level supervision in existing implicit CoT approaches. To address this issue, we propose SIM-CoT, a plug-and-play training module that introduces step-level supervision to stabilize and enrich the latent reasoning space. Specifically, SIM-CoT employs an auxiliary decoder during training to align each implicit token with its corresponding explicit reasoning step, ensuring that latent states capture distinct and meaningful information. The proposed auxiliary decoder is removed during inference, preserving the computational efficiency of implicit CoT methods with no added overhead. In addition, the auxiliary decoder affords interpretability of implicit reasoning by projecting each latent token onto an explicit reasoning vocabulary, enabling per-step visualization of semantic roles and diagnosis. SIM-CoT significantly enhances both the in-domain accuracy and out-of-domain stability of various implicit CoT methods, boosting baselines like Coconut by +8.2% on GPT-2 and CODI by +3.0% on LLaMA-3.1 8B. Demonstrating strong scalability, SIM-CoT also surpasses the explicit CoT baseline on GPT-2 by 2.1% with 2.3\times greater token efficiency, while substantially closing the performance gap on larger models like LLaMA-3.1 8B.</p> + https://arxiv.org/abs/2509.20317 + Wed, 24 Sep 2025 17:01:32 +0000 - Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels - https://arxiv.org/abs/2508.17437 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.17437.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Long Le, Ryan Lucas, Chen Wang, Chuhao Chen, Dinesh Jayaraman, Eric Eaton, Lingjie Liu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Inferring the physical properties of 3D scenes from visual information is a critical yet challenging task for creating interactive and realistic virtual worlds. While humans intuitively grasp material characteristics such as elasticity or stiffness, existing methods often rely on slow, per-scene optimization, limiting their generalizability and application. To address this problem, we introduce PIXIE, a novel method that trains a generalizable neural network to predict physical properties across multiple scenes from 3D visual features purely using supervised losses. Once trained, our feed-forward network can perform fast inference of plausible material fields, which coupled with a learned static scene representation like Gaussian Splatting enables realistic physics simulation under external forces. To facilitate this research, we also collected PIXIEVERSE, one of the largest known datasets of paired 3D assets and physic material annotations. Extensive evaluations demonstrate that PIXIE is about 1.46-4.39x better and orders of magnitude faster than test-time optimization methods. By leveraging pretrained visual features like CLIP, our method can also zero-shot generalize to real-world scenes despite only ever been trained on synthetic data. https://pixie-3d.github.io/</p> - https://arxiv.org/abs/2508.17437 - Wed, 20 Aug 2025 19:24:04 +0000 + Video models are zero-shot learners and reasoners + https://arxiv.org/abs/2509.20328 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thaddäus Wiedemer, Yuxuan Li, Paul Vicol, Shixiang Shane Gu, Nick Matarese, Kevin Swersky, Been Kim, Priyank Jaini, Robert Geirhos</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models. This transformation emerged from simple primitives: large, generative models trained on web-scale data. Curiously, the same primitives apply to today's generative video models. Could video models be on a trajectory towards general-purpose vision understanding, much like LLMs developed general-purpose language understanding? We demonstrate that Veo 3 can solve a broad variety of tasks it wasn't explicitly trained for: segmenting objects, detecting edges, editing images, understanding physical properties, recognizing object affordances, simulating tool use, and more. These abilities to perceive, model, and manipulate the visual world enable early forms of visual reasoning like maze and symmetry solving. Veo's emergent zero-shot capabilities indicate that video models are on a path to becoming unified, generalist vision foundation models.</p> + https://arxiv.org/abs/2509.20328 + Wed, 24 Sep 2025 17:17:27 +0000 - Mobile-Agent-v3: Foundamental Agents for GUI Automation - https://arxiv.org/abs/2508.15144 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15144.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiabo Ye, Xi Zhang, Haiyang Xu, Haowei Liu, Junyang Wang, Zhaoqing Zhu, Ziwei Zheng, Feiyu Gao, Junjie Cao, Zhengxi Lu, Jitong Liao, Qi Zheng, Fei Huang, Jingren Zhou, Ming Yan</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> This paper introduces GUI-Owl, a foundational GUI agent model that achieves state-of-the-art performance among open-source end-to-end models on ten GUI benchmarks across desktop and mobile environments, covering grounding, question answering, planning, decision-making, and procedural knowledge. GUI-Owl-7B achieves 66.4 on AndroidWorld and 29.4 on OSWorld. Building on this, we propose Mobile-Agent-v3, a general-purpose GUI agent framework that further improves performance to 73.3 on AndroidWorld and 37.7 on OSWorld, setting a new state-of-the-art for open-source GUI agent frameworks. GUI-Owl incorporates three key innovations: (1) Large-scale Environment Infrastructure: a cloud-based virtual environment spanning Android, Ubuntu, macOS, and Windows, enabling our Self-Evolving GUI Trajectory Production framework. This generates high-quality interaction data via automated query generation and correctness validation, leveraging GUI-Owl to refine trajectories iteratively, forming a self-improving loop. It supports diverse data pipelines and reduces manual annotation. (2) Diverse Foundational Agent Capabilities: by integrating UI grounding, planning, action semantics, and reasoning patterns, GUI-Owl supports end-to-end decision-making and can act as a modular component in multi-agent systems. (3) Scalable Environment RL: we develop a scalable reinforcement learning framework with fully asynchronous training for real-world alignment. We also introduce Trajectory-aware Relative Policy Optimization (TRPO) for online RL, achieving 34.9 on OSWorld. GUI-Owl and Mobile-Agent-v3 are open-sourced at https://github.com/X-PLUG/MobileAgent.</p> - https://arxiv.org/abs/2508.15144 - Thu, 21 Aug 2025 00:39:12 +0000 + EmbeddingGemma: Powerful and Lightweight Text Representations + https://arxiv.org/abs/2509.20354 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Henrique Schechter Vera, Sahil Dua, Biao Zhang, Daniel Salz, Ryan Mullins, Sindhu Raghuram Panyam, Sara Smoot, Iftekhar Naim, Joe Zou, Feiyang Chen, Daniel Cer, Alice Lisak, Min Choi, Lucas Gonzalez, Omar Sanseviero, Glenn Cameron, Ian Ballantyne, Kat Black, Kaifeng Chen, Weiyi Wang, Zhe Li, Gus Martins, Jinhyuk Lee, Mark Sherwood, Juyeong Ji, Renjie Wu, Jingxiao Zheng, Jyotinder Singh, Abheesht Sharma, Divya Sreepat, Aashi Jain, Adham Elarabawy, AJ Co, Andreas Doumanoglou, Babak Samari, Ben Hora, Brian Potetz, Dahun Kim, Enrique Alfonseca, Fedor Moiseev, Feng Han, Frank Palma Gomez, Gustavo Hernández Ábrego, Hesen Zhang, Hui Hui, Jay Han, Karan Gill, Ke Chen, Koert Chen, Madhuri Shanbhogue, Michael Boratko, Paul Suganthan, Sai Meher Karthik Duddu, Sandeep Mariserla, Setareh Ariafar, Shanfeng Zhang, Shijie Zhang, Simon Baumgartner, Sonam Goenka, Steve Qiu, Tanmaya Dabral, Trevor Walker, Vikram Rao, Waleed Khawaja, Wenlei Zhou, Xiaoqi Ren, Ye Xia, Yichang Chen, Yi-Ting Chen, Zhe Dong, Zhongli Ding, Francesco Visin, Gaël Liu, Jiageng Zhang, Kathleen Kenealy, Michelle Casbon, Ravin Kumar, Thomas Mesnard, Zach Gleicher, Cormac Brick, Olivier Lacombe, Adam Roberts, Yunhsuan Sung, Raphael Hoffmann, Tris Warkentin, Armand Joulin, Tom Duerig, Mojtaba Seyedhosseini</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and geometric embedding distillation. We improve model robustness and expressiveness with a spread-out regularizer, and ensure generalizability by merging checkpoints from varied, optimized mixtures. Evaluated on the Massive Text Embedding Benchmark (MTEB) across multilingual, English, and code domains, EmbeddingGemma (300M) achieves state-of-the-art results. Notably, it outperforms prior top models, both proprietary and open, with fewer than 500M parameters, and provides performance comparable to models double its size, offering an exceptional performance-to-cost ratio. Remarkably, this lead persists when quantizing model weights or truncating embedding outputs. This makes EmbeddingGemma particularly well-suited for low-latency and high-throughput use cases such as on-device applications. We provide ablation studies exploring our key design choices. We release EmbeddingGemma to the community to promote further research.</p> + https://arxiv.org/abs/2509.20354 + Wed, 24 Sep 2025 17:56:51 +0000 - Deep Think with Confidence - https://arxiv.org/abs/2508.15260 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15260.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichao Fu, Xuewei Wang, Yuandong Tian, Jiawei Zhao</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> Large Language Models (LLMs) have shown great potential in reasoning tasks through test-time scaling methods like self-consistency with majority voting. However, this approach often leads to diminishing returns in accuracy and high computational overhead. To address these challenges, we introduce Deep Think with Confidence (DeepConf), a simple yet powerful method that enhances both reasoning efficiency and performance at test time. DeepConf leverages model-internal confidence signals to dynamically filter out low-quality reasoning traces during or after generation. It requires no additional model training or hyperparameter tuning and can be seamlessly integrated into existing serving frameworks. We evaluate DeepConf across a variety of reasoning tasks and the latest open-source models, including Qwen 3 and GPT-OSS series. Notably, on challenging benchmarks such as AIME 2025, DeepConf@512 achieves up to 99.9% accuracy and reduces generated tokens by up to 84.7% compared to full parallel thinking.</p> - https://arxiv.org/abs/2508.15260 - Thu, 21 Aug 2025 05:48:38 +0000 + Seedream 4.0: Toward Next-generation Multimodal Image Generation + https://arxiv.org/abs/2509.20427 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Team Seedream, Yunpeng Chen, Yu Gao, Lixue Gong, Meng Guo, Qiushan Guo, Zhiyao Guo, Xiaoxia Hou, Weilin Huang, Yixuan Huang, Xiaowen Jian, Huafeng Kuang, Zhichao Lai, Fanshi Li, Liang Li, Xiaochen Lian, Chao Liao, Liyang Liu, Wei Liu, Yanzuo Lu, Zhengxiong Luo, Tongtong Ou, Guang Shi, Yichun Shi, Shiqi Sun, Yu Tian, Zhi Tian, Peng Wang, Rui Wang, Xun Wang, Ye Wang, Guofeng Wu, Jie Wu, Wenxu Wu, Yonghui Wu, Xin Xia, Xuefeng Xiao, Shuang Xu, Xin Yan, Ceyuan Yang, Jianchao Yang, Zhonghua Zhai, Chenlin Zhang, Heng Zhang, Qi Zhang, Xinyu Zhang, Yuwei Zhang, Shijia Zhao, Wenliang Zhao, Wenjia Zhu</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> We introduce Seedream 4.0, an efficient and high-performance multimodal image generation system that unifies text-to-image (T2I) synthesis, image editing, and multi-image composition within a single framework. We develop a highly efficient diffusion transformer with a powerful VAE which also can reduce the number of image tokens considerably. This allows for efficient training of our model, and enables it to fast generate native high-resolution images (e.g., 1K-4K). Seedream 4.0 is pretrained on billions of text-image pairs spanning diverse taxonomies and knowledge-centric concepts. Comprehensive data collection across hundreds of vertical scenarios, coupled with optimized strategies, ensures stable and large-scale training, with strong generalization. By incorporating a carefully fine-tuned VLM model, we perform multi-modal post-training for training both T2I and image editing tasks jointly. For inference acceleration, we integrate adversarial distillation, distribution matching, and quantization, as well as speculative decoding. It achieves an inference time of up to 1.8 seconds for generating a 2K image (without a LLM/VLM as PE model). Comprehensive evaluations reveal that Seedream 4.0 can achieve state-of-the-art results on both T2I and multimodal image editing. In particular, it demonstrates exceptional multimodal capabilities in complex tasks, including precise image editing and in-context reasoning, and also allows for multi-image reference, and can generate multiple output images. This extends traditional T2I systems into an more interactive and multidimensional creative tool, pushing the boundary of generative AI for both creativity and professional applications. Seedream 4.0 is now accessible on https://www.volcengine.com/experience/ark?launch=seedream.</p> + https://arxiv.org/abs/2509.20427 + Wed, 24 Sep 2025 17:59:04 +0000 - Beyond Transcription: Mechanistic Interpretability in ASR - https://arxiv.org/abs/2508.15882 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15882.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Neta Glazer, Yael Segal-Feldman, Hilit Segev, Aviv Shamsian, Asaf Buchnick, Gill Hetz, Ethan Fetaya, Joseph Keshet, Aviv Navon</p><p><b>Upvotes:</b> 80</p><p><b>Summary:</b> Interpretability methods have recently gained significant attention, particularly in the context of large language models, enabling insights into linguistic representations, error detection, and model behaviors such as hallucinations and repetitions. However, these techniques remain underexplored in automatic speech recognition (ASR), despite their potential to advance both the performance and interpretability of ASR systems. In this work, we adapt and systematically apply established interpretability methods such as logit lens, linear probing, and activation patching, to examine how acoustic and semantic information evolves across layers in ASR systems. Our experiments reveal previously unknown internal dynamics, including specific encoder-decoder interactions responsible for repetition hallucinations and semantic biases encoded deep within acoustic representations. These insights demonstrate the benefits of extending and applying interpretability techniques to speech recognition, opening promising directions for future research on improving model transparency and robustness.</p> - https://arxiv.org/abs/2508.15882 - Thu, 21 Aug 2025 15:42:53 +0000 + Tree Search for LLM Agent Reinforcement Learning + https://arxiv.org/abs/2509.21240 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Ji, Ziyu Ma, Yong Wang, Guanhua Chen, Xiangxiang Chu, Liaoni Wu</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer from the problem of sparse supervision. To address the challenge, we propose Tree-based Group Relative Policy Optimization (Tree-GRPO), a grouped agent RL method based on tree search, where each tree node represents the complete agent interaction step. By sharing common prefixes, the tree search sampling increases the number of rollouts achievable within a fixed budget of tokens or tool calls. Moreover, we find that the tree-structured trajectory naturally allows the construction of step-wise process supervised signals even using only the outcome reward. Based on this, Tree-GRPO estimates the grouped relative advantages both on intra-tree and inter-tree levels. Through theoretical analysis, we demonstrate that the objective of intra-tree level group relative policy optimization is equivalent to that of step-level direct preference learning. Experiments across 11 datasets and 3 types of QA tasks demonstrate the superiority of the proposed tree-based RL over the chain-based RL method.</p> + https://arxiv.org/abs/2509.21240 + Thu, 25 Sep 2025 14:37:09 +0000 - LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries - https://arxiv.org/abs/2508.15760 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Yin, Dinghan Shen, Silei Xu, Jianbing Han, Sixun Dong, Mian Zhang, Yebowen Hu, Shujian Liu, Simin Ma, Song Wang, Sathish Reddy Indurthi, Xun Wang, Yiran Chen, Kaiqiang Song</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Tool calling has emerged as a critical capability for AI agents to interact with the real world and solve complex tasks. While the Model Context Protocol (MCP) provides a powerful standardized framework for tool integration, there is a significant gap in benchmarking how well AI agents can effectively solve multi-step tasks using diverse MCP tools in realistic, dynamic scenarios. In this work, we present LiveMCP-101, a benchmark of 101 carefully curated real-world queries, refined through iterative LLM rewriting and manual review, that require coordinated use of multiple MCP tools including web search, file operations, mathematical reasoning, and data analysis. Moreover, we introduce a novel evaluation approach that leverages ground-truth execution plans rather than raw API outputs, better reflecting the evolving nature of real-world environments. Experiments show that even frontier LLMs achieve a success rate below 60\%, highlighting major challenges in tool orchestration. Detailed ablations and error analysis further reveal distinct failure modes and inefficiencies in token usage, pointing to concrete directions for advancing current models. LiveMCP-101 sets a rigorous standard for evaluating real-world agent capabilities, advancing toward autonomous AI systems that reliably execute complex tasks through tool use.</p> - https://arxiv.org/abs/2508.15760 - Thu, 21 Aug 2025 17:55:54 +0000 + Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets + https://arxiv.org/abs/2509.21245 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21245.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Team Hunyuan3D, Bowen Zhang, Chunchao Guo, Haolin Liu, Hongyu Yan, Huiwen Shi, Jingwei Huang, Junlin Yu, Kunhong Li, Linus, Penghao Wang, Qingxiang Lin, Sicong Liu, Xianghui Yang, Yixuan Tang, Yunfei Zhao, Zeqiang Lai, Zhihao Liang, Zibo Zhao</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Recent advances in 3D-native generative models have accelerated asset creation for games, film, and design. However, most methods still rely primarily on image or text conditioning and lack fine-grained, cross-modal controls, which limits controllability and practical adoption. To address this gap, we present Hunyuan3D-Omni, a unified framework for fine-grained, controllable 3D asset generation built on Hunyuan3D 2.1. In addition to images, Hunyuan3D-Omni accepts point clouds, voxels, bounding boxes, and skeletal pose priors as conditioning signals, enabling precise control over geometry, topology, and pose. Instead of separate heads for each modality, our model unifies all signals in a single cross-modal architecture. We train with a progressive, difficulty-aware sampling strategy that selects one control modality per example and biases sampling toward harder signals (e.g., skeletal pose) while downweighting easier ones (e.g., point clouds), encouraging robust multi-modal fusion and graceful handling of missing inputs. Experiments show that these additional controls improve generation accuracy, enable geometry-aware transformations, and increase robustness for production workflows.</p> + https://arxiv.org/abs/2509.21245 + Thu, 25 Sep 2025 14:39:17 +0000 - Waver: Wave Your Way to Lifelike Video Generation - https://arxiv.org/abs/2508.15761 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15761.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifu Zhang, Hao Yang, Yuqi Zhang, Yifei Hu, Fengda Zhu, Chuang Lin, Xiaofeng Mei, Yi Jiang, Zehuan Yuan, Bingyue Peng</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> We present Waver, a high-performance foundation model for unified image and video generation. Waver can directly generate videos with durations ranging from 5 to 10 seconds at a native resolution of 720p, which are subsequently upscaled to 1080p. The model simultaneously supports text-to-video (T2V), image-to-video (I2V), and text-to-image (T2I) generation within a single, integrated framework. We introduce a Hybrid Stream DiT architecture to enhance modality alignment and accelerate training convergence. To ensure training data quality, we establish a comprehensive data curation pipeline and manually annotate and train an MLLM-based video quality model to filter for the highest-quality samples. Furthermore, we provide detailed training and inference recipes to facilitate the generation of high-quality videos. Building on these contributions, Waver excels at capturing complex motion, achieving superior motion amplitude and temporal consistency in video synthesis. Notably, it ranks among the Top 3 on both the T2V and I2V leaderboards at Artificial Analysis (data as of 2025-07-30 10:00 GMT+8), consistently outperforming existing open-source models and matching or surpassing state-of-the-art commercial solutions. We hope this technical report will help the community more efficiently train high-quality video generation models and accelerate progress in video generation technologies. Official page: https://github.com/FoundationVision/Waver.</p> - https://arxiv.org/abs/2508.15761 - Thu, 21 Aug 2025 17:56:10 +0000 + MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources + https://arxiv.org/abs/2509.21268 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sicong Leng, Jing Wang, Jiaxi Li, Hao Zhang, Zhiqiang Hu, Boqiang Zhang, Yuming Jiang, Hang Zhang, Xin Li, Lidong Bing, Deli Zhao, Wei Lu, Yu Rong, Aixin Sun, Shijian Lu</p><p><b>Upvotes:</b> 93</p><p><b>Summary:</b> Large multimodal reasoning models have achieved rapid progress, but their advancement is constrained by two major limitations: the absence of open, large-scale, high-quality long chain-of-thought (CoT) data, and the instability of reinforcement learning (RL) algorithms in post-training. Group Relative Policy Optimization (GRPO), the standard framework for RL fine-tuning, is prone to gradient vanishing when reward variance is low, which weakens optimization signals and impairs convergence. This work makes three contributions: (1) We propose Variance-Aware Sampling (VAS), a data selection strategy guided by Variance Promotion Score (VPS) that combines outcome variance and trajectory diversity to promote reward variance and stabilize policy optimization. (2) We release large-scale, carefully curated resources containing ~1.6M long CoT cold-start data and ~15k RL QA pairs, designed to ensure quality, difficulty, and diversity, along with a fully reproducible end-to-end training codebase. (3) We open-source a family of multimodal reasoning models in multiple scales, establishing standardized baselines for the community. Experiments across mathematical reasoning benchmarks demonstrate the effectiveness of both the curated data and the proposed VAS. Comprehensive ablation studies and analyses provide further insight into the contributions of each component. In addition, we theoretically establish that reward variance lower-bounds the expected policy gradient magnitude, with VAS serving as a practical mechanism to realize this guarantee. Our code, data, and checkpoints are available at https://github.com/LengSicong/MMR1.</p> + https://arxiv.org/abs/2509.21268 + Thu, 25 Sep 2025 14:58:29 +0000 - Intern-S1: A Scientific Multimodal Foundation Model - https://arxiv.org/abs/2508.15763 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.15763.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Bai, Zhongrui Cai, Maosong Cao, Weihan Cao, Chiyu Chen, Haojiong Chen, Kai Chen, Pengcheng Chen, Ying Chen, Yongkang Chen, Yu Cheng, Yu Cheng, Pei Chu, Tao Chu, Erfei Cui, Ganqu Cui, Long Cui, Ziyun Cui, Nianchen Deng, Ning Ding, Nanqin Dong, Peijie Dong, Shihan Dou, Sinan Du, Haodong Duan, Caihua Fan, Ben Gao, Changjiang Gao, Jianfei Gao, Songyang Gao, Yang Gao, Zhangwei Gao, Jiaye Ge, Qiming Ge, Lixin Gu, Yuzhe Gu, Aijia Guo, Qipeng Guo, Xu Guo, Conghui He, Junjun He, Yili Hong, Siyuan Hou, Caiyu Hu, Hanglei Hu, Jucheng Hu, Ming Hu, Zhouqi Hua, Haian Huang, Junhao Huang, Xu Huang, Zixian Huang, Zhe Jiang, Lingkai Kong, Linyang Li, Peiji Li, Pengze Li, Shuaibin Li, Tianbin Li, Wei Li, Yuqiang Li, Dahua Lin, Junyao Lin, Tianyi Lin, Zhishan Lin, Hongwei Liu, Jiangning Liu, Jiyao Liu, Junnan Liu, Kai Liu, Kaiwen Liu, Kuikun Liu, Shichun Liu, Shudong Liu, Wei Liu, Xinyao Liu, Yuhong Liu, Zhan Liu, Yinquan Lu, Haijun Lv, Hongxia Lv, Huijie Lv, Qidang Lv, Ying Lv, Chengqi Lyu, Chenglong Ma, Jianpeng Ma, Ren Ma, Runmin Ma, Runyuan Ma, Xinzhu Ma, Yichuan Ma, Zihan Ma, Sixuan Mi, Junzhi Ning, Wenchang Ning, Xinle Pang, Jiahui Peng, Runyu Peng, Yu Qiao, Jiantao Qiu, Xiaoye Qu, Yuan Qu, Yuchen Ren, Fukai Shang, Wenqi Shao, Junhao Shen, Shuaike Shen, Chunfeng Song, Demin Song, Diping Song, Chenlin Su, Weijie Su, Weigao Sun, Yu Sun, Qian Tan, Cheng Tang, Huanze Tang, Kexian Tang, Shixiang Tang, Jian Tong, Aoran Wang, Bin Wang, Dong Wang, Lintao Wang, Rui Wang, Weiyun Wang, Wenhai Wang, Yi Wang, Ziyi Wang, Ling-I Wu, Wen Wu, Yue Wu, Zijian Wu, Linchen Xiao, Shuhao Xing, Chao Xu, Huihui Xu, Jun Xu, Ruiliang Xu, Wanghan Xu, GanLin Yang, Yuming Yang, Haochen Ye, Jin Ye, Shenglong Ye, Jia Yu, Jiashuo Yu, Jing Yu, Fei Yuan, Bo Zhang, Chao Zhang, Chen Zhang, Hongjie Zhang, Jin Zhang, Qiaosheng Zhang, Qiuyinzhe Zhang, Songyang Zhang, Taolin Zhang, Wenlong Zhang, Wenwei Zhang, Yechen Zhang, Ziyang Zhang, Haiteng Zhao, Qian Zhao, Xiangyu Zhao, Xiangyu Zhao, Bowen Zhou, Dongzhan Zhou, Peiheng Zhou, Yuhao Zhou, Yunhua Zhou, Dongsheng Zhu, Lin Zhu, Yicheng Zou</p><p><b>Upvotes:</b> 242</p><p><b>Summary:</b> In recent years, a plethora of open-source foundation models have emerged, achieving remarkable progress in some widely attended fields, with performance being quite close to that of closed-source models. However, in high-value but more challenging scientific professional fields, either the fields still rely on expert models, or the progress of general foundation models lags significantly compared to those in popular areas, far from sufficient for transforming scientific research and leaving substantial gap between open-source models and closed-source models in these scientific domains. To mitigate this gap and explore a step further toward Artificial General Intelligence (AGI), we introduce Intern-S1, a specialized generalist equipped with general understanding and reasoning capabilities with expertise to analyze multiple science modal data. Intern-S1 is a multimodal Mixture-of-Experts (MoE) model with 28 billion activated parameters and 241 billion total parameters, continually pre-trained on 5T tokens, including over 2.5T tokens from scientific domains. In the post-training stage, Intern-S1 undergoes offline and then online reinforcement learning (RL) in InternBootCamp, where we propose Mixture-of-Rewards (MoR) to synergize the RL training on more than 1000 tasks simultaneously. Through integrated innovations in algorithms, data, and training systems, Intern-S1 achieved top-tier performance in online RL training.On comprehensive evaluation benchmarks, Intern-S1 demonstrates competitive performance on general reasoning tasks among open-source models and significantly outperforms open-source models in scientific domains, surpassing closed-source state-of-the-art models in professional tasks, such as molecular synthesis planning, reaction condition prediction, predicting thermodynamic stabilities for crystals. Our models are available at https://huggingface.co/internlm/Intern-S1.</p> - https://arxiv.org/abs/2508.15763 - Thu, 21 Aug 2025 17:58:00 +0000 + SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines + https://arxiv.org/abs/2509.21320 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizhou Wang, Chen Tang, Han Deng, Jiabei Xiao, Jiaqi Liu, Jianyu Wu, Jun Yao, Pengze Li, Encheng Su, Lintao Wang, Guohang Zhuang, Yuchen Ren, Ben Fei, Ming Hu, Xin Chen, Dongzhan Zhou, Junjun He, Xiangyu Yue, Zhenfei Yin, Jiamin Wu, Qihao Zheng, Yuhao Zhou, Huihui Xu, Chenglong Ma, Yan Lu, Wenlong Zhang, Chunfeng Song, Philip Torr, Shixiang Tang, Xinzhu Ma, Wanli Ouyang, Lei Bai</p><p><b>Upvotes:</b> 91</p><p><b>Summary:</b> We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanning scientific text, pure sequences, and sequence-text pairs, then aligned via SFT on 40M instructions, annealed cold-start bootstrapping to elicit long-form chain-of-thought, and reinforcement learning with task-specific reward shaping, which instills deliberate scientific reasoning. It supports four capability families, covering up to 103 tasks across workflows: (i) faithful translation between text and scientific formats, (ii) text/knowledge extraction, (iii) property prediction, (iv) property classification, (v) unconditional and conditional sequence generation and design. Compared with specialist systems, our approach broadens instruction coverage, improves cross-domain generalization, and enhances fidelity. We detail data curation and training and show that cross-discipline learning strengthens transfer and downstream reliability. The model, instruct tuning datasets and the evaluation code are open-sourced at https://huggingface.co/SciReason and https://github.com/open-sciencelab/SciReason.</p> + https://arxiv.org/abs/2509.21320 + Thu, 25 Sep 2025 17:52:06 +0000 - AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs - https://arxiv.org/abs/2508.16153 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.16153.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huichi Zhou, Yihang Chen, Siyuan Guo, Xue Yan, Kin Hei Lee, Zihan Wang, Ka Yiu Lee, Guchun Zhang, Kun Shao, Linyi Yang, Jun Wang</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> In this paper, we introduce a novel learning paradigm for adaptive Large Language Model (LLM) agents that eliminates the need for fine-tuning the underlying LLMs. Existing approaches are often either rigid, relying on static, handcrafted reflection workflows, or computationally intensive, requiring gradient updates of LLM model parameters. In contrast, our method enables low-cost continual adaptation via memory-based online reinforcement learning. We formalise this as a Memory-augmented Markov Decision Process (M-MDP), equipped with a neural case-selection policy to guide action decisions. Past experiences are stored in an episodic memory, either differentiable or non-parametric. The policy is continually updated based on environmental feedback through a memory rewriting mechanism, whereas policy improvement is achieved through efficient memory reading (retrieval). We instantiate our agent model in the deep research setting, namely AgentFly, which attains top-1 on GAIA validation (87.88% Pass@3) and 79.40% on the test set. It reaches 66.6% F1 and 80.4% PM on the DeepResearcher dataset, outperforming the state-of-the-art training-based method, while case-based memory adds 4.7% to 9.6% absolute points on out-of-distribution tasks. Our approach offers a scalable and efficient pathway for developing generalist LLM agents capable of continuous, real-time learning without gradient updates, advancing machine learning towards open-ended skill acquisition and deep research scenarios. The code is available at https://github.com/Agent-on-the-Fly/AgentFly.</p> - https://arxiv.org/abs/2508.16153 - Fri, 22 Aug 2025 07:25:30 +0000 + ReviewScore: Misinformed Peer Review Detection with Large Language Models + https://arxiv.org/abs/2509.21679 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21679.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyun Ryu, Doohyuk Jang, Hyemin S. Lee, Joonhyun Jeong, Gyeongman Kim, Donghyeon Cho, Gyouk Chu, Minyeong Hwang, Hyeongwon Jang, Changhun Kim, Haechan Kim, Jina Kim, Joowon Kim, Yoonjeon Kim, Kwanhyung Lee, Chanjae Park, Heecheol Yun, Gregor Betz, Eunho Yang</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Peer review serves as a backbone of academic research, but in most AI conferences, the review quality is degrading as the number of submissions explodes. To reliably detect low-quality reviews, we define misinformed review points as either "weaknesses" in a review that contain incorrect premises, or "questions" in a review that can be already answered by the paper. We verify that 15.2% of weaknesses and 26.4% of questions are misinformed and introduce ReviewScore indicating if a review point is misinformed. To evaluate the factuality of each premise of weaknesses, we propose an automated engine that reconstructs every explicit and implicit premise from a weakness. We build a human expert-annotated ReviewScore dataset to check the ability of LLMs to automate ReviewScore evaluation. Then, we measure human-model agreements on ReviewScore using eight current state-of-the-art LLMs and verify moderate agreements. We also prove that evaluating premise-level factuality shows significantly higher agreements than evaluating weakness-level factuality. A thorough disagreement analysis further supports a potential of fully automated ReviewScore evaluation.</p> + https://arxiv.org/abs/2509.21679 + Thu, 25 Sep 2025 22:55:05 +0000 - MV-RAG: Retrieval Augmented Multiview Diffusion - https://arxiv.org/abs/2508.16577 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.16577.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yosef Dayani, Omer Benishu, Sagie Benaim</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Text-to-3D generation approaches have advanced significantly by leveraging pretrained 2D diffusion priors, producing high-quality and 3D-consistent outputs. However, they often fail to produce out-of-domain (OOD) or rare concepts, yielding inconsistent or inaccurate results. To this end, we propose MV-RAG, a novel text-to-3D pipeline that first retrieves relevant 2D images from a large in-the-wild 2D database and then conditions a multiview diffusion model on these images to synthesize consistent and accurate multiview outputs. Training such a retrieval-conditioned model is achieved via a novel hybrid strategy bridging structured multiview data and diverse 2D image collections. This involves training on multiview data using augmented conditioning views that simulate retrieval variance for view-specific reconstruction, alongside training on sets of retrieved real-world 2D images using a distinctive held-out view prediction objective: the model predicts the held-out view from the other views to infer 3D consistency from 2D data. To facilitate a rigorous OOD evaluation, we introduce a new collection of challenging OOD prompts. Experiments against state-of-the-art text-to-3D, image-to-3D, and personalization baselines show that our approach significantly improves 3D consistency, photorealism, and text adherence for OOD/rare concepts, while maintaining competitive performance on standard benchmarks.</p> - https://arxiv.org/abs/2508.16577 - Fri, 22 Aug 2025 17:59:40 +0000 + MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing + https://arxiv.org/abs/2509.22186 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22186.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Yuanhong Zheng, Dongsheng Ma, Zirui Tang, Boyu Niu, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Jingzhou Chen, Fangdong Wang, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, Ruiliang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Keming Wang, Dechen Lin, Guanlin Shen, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Yu Qiao, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He</p><p><b>Upvotes:</b> 92</p><p><b>Summary:</b> We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition. In the first stage, the model performs efficient layout analysis on downsampled images to identify structural elements, circumventing the computational overhead of processing high-resolution inputs. In the second stage, guided by the global layout, it performs targeted content recognition on native-resolution crops extracted from the original image, preserving fine-grained details in dense text, complex formulas, and tables. To support this strategy, we developed a comprehensive data engine that generates diverse, large-scale training corpora for both pretraining and fine-tuning. Ultimately, MinerU2.5 demonstrates strong document parsing ability, achieving state-of-the-art performance on multiple benchmarks, surpassing both general-purpose and domain-specific models across various recognition tasks, while maintaining significantly lower computational overhead.</p> + https://arxiv.org/abs/2509.22186 + Fri, 26 Sep 2025 10:45:48 +0000 - TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling - https://arxiv.org/abs/2508.17445 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.17445.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizhi Li, Qingshui Gu, Zhoufutu Wen, Ziniu Li, Tianshun Xing, Shuyue Guo, Tianyu Zheng, Xin Zhou, Xingwei Qu, Wangchunshu Zhou, Zheng Zhang, Wei Shen, Qian Liu, Chenghua Lin, Jian Yang, Ge Zhang, Wenhao Huang</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> Recent advancements in aligning large language models via reinforcement learning have achieved remarkable gains in solving complex reasoning problems, but at the cost of expensive on-policy rollouts and limited exploration of diverse reasoning paths. In this work, we introduce TreePO, involving a self-guided rollout algorithm that views sequence generation as a tree-structured searching process. Composed of dynamic tree sampling policy and fixed-length segment decoding, TreePO leverages local uncertainty to warrant additional branches. By amortizing computation across common prefixes and pruning low-value paths early, TreePO essentially reduces the per-update compute burden while preserving or enhancing exploration diversity. Key contributions include: (1) a segment-wise sampling algorithm that alleviates the KV cache burden through contiguous segments and spawns new branches along with an early-stop mechanism; (2) a tree-based segment-level advantage estimation that considers both global and local proximal policy optimization. and (3) analysis on the effectiveness of probability and quality-driven dynamic divergence and fallback strategy. We empirically validate the performance gain of TreePO on a set reasoning benchmarks and the efficiency saving of GPU hours from 22\% up to 43\% of the sampling design for the trained models, meanwhile showing up to 40\% reduction at trajectory-level and 35\% at token-level sampling compute for the existing models. While offering a free lunch of inference efficiency, TreePO reveals a practical path toward scaling RL-based post-training with fewer samples and less compute. Home page locates at https://m-a-p.ai/TreePO.</p> - https://arxiv.org/abs/2508.17445 - Sun, 24 Aug 2025 16:52:37 +0000 + StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs + https://arxiv.org/abs/2509.22220 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22220.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhan Song, Linhao Zhang, Chuhan Wu, Aiwei Liu, Wei Jia, Houfeng Wang, Xiao Zhou</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust to meaning-irrelevant acoustic perturbations; even at high Signal-to-Noise Ratios (SNRs) where speech is perfectly intelligible, their output token sequences can change drastically, increasing the learning burden for downstream LLMs. This instability stems from two flaws: a brittle single-path quantization architecture and a distant training signal indifferent to intermediate token stability. To address this, we introduce StableToken, a tokenizer that achieves stability through a consensus-driven mechanism. Its multi-branch architecture processes audio in parallel, and these representations are merged via a powerful bit-wise voting mechanism to form a single, stable token sequence. StableToken sets a new state-of-the-art in token stability, drastically reducing Unit Edit Distance (UED) under diverse noise conditions. This foundational stability translates directly to downstream benefits, significantly improving the robustness of SpeechLLMs on a variety of tasks.</p> + https://arxiv.org/abs/2509.22220 + Fri, 26 Sep 2025 11:32:51 +0000 - Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation - https://arxiv.org/abs/2508.18032 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18032.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaqi Li, Peng Chen, Mingyang Han, Bu Pi, Haoxiang Shi, Runzhou Zhao, Yang Yao, Xuan Zhang, Jun Song</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Despite the promising progress of recent autoregressive models in text-to-image (T2I) generation, their ability to handle multi-attribute and ambiguous prompts remains limited. To address these limitations, existing works have applied chain-of-thought (CoT) to enable stage-aware visual synthesis and employed reinforcement learning (RL) to improve reasoning capabilities. However, most models provide reward signals only at the end of the generation stage. This monolithic final-only guidance makes it difficult to identify which stages contribute positively to the final outcome and may lead to suboptimal policies. To tackle this issue, we propose a Visual-Chain of Guidance (Visual-CoG) paradigm consisting of three stages: semantic reasoning, process refining, and outcome evaluation, with stage-aware rewards providing immediate guidance throughout the image generation pipeline. We further construct a visual cognition benchmark, VisCog-Bench, which comprises four subtasks to evaluate the effectiveness of semantic reasoning. Comprehensive evaluations on GenEval, T2I-CompBench, and the proposed VisCog-Bench show improvements of 15%, 5%, and 19%, respectively, demonstrating the superior performance of the proposed Visual-CoG. We will release all the resources soon.</p> - https://arxiv.org/abs/2508.18032 - Mon, 25 Aug 2025 13:53:02 +0000 + EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning + https://arxiv.org/abs/2509.22576 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22576.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xu Wujiang, Wentian Zhao, Zhenting Wang, Li Yu-Jhe, Jin Can, Jin Mingyu, Mei Kai, Wan Kun, Metaxas Dimitris</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> Training LLM agents in multi-turn environments with sparse rewards, where completing a single task requires 30+ turns of interaction within an episode, presents a fundamental challenge for reinforcement learning. We identify a critical failure mode unique to this setting: the exploration-exploitation cascade failure. This cascade begins with early-stage policy premature convergence, where sparse feedback causes agents to commit to flawed, low-entropy strategies. Subsequently, agents enter late-stage policy collapse, where conventional entropy regularization becomes counterproductive, promoting chaotic exploration that destabilizes training. We propose Entropy-regularized Policy Optimization (EPO), a general framework that breaks this failure cycle through three synergistic mechanisms: (1) adopting entropy regularization in multi-turn settings to enhance exploration, (2) an entropy smoothing regularizer that bounds policy entropy within historical averages to prevent abrupt fluctuations, and (3) adaptive phase-based weighting that balances exploration and exploitation across training. Our analysis justifies that EPO guarantees monotonically decreasing entropy variance while maintaining convergence. EPO achieves up to 152% performance improvement on ScienceWorld and up to 19.8% on ALFWorld. Our work demonstrates that multi-turn sparse-reward settings require fundamentally different entropy control than traditional RL, with broad implications for LLM agent training.</p> + https://arxiv.org/abs/2509.22576 + Fri, 26 Sep 2025 16:51:44 +0000 - CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics - https://arxiv.org/abs/2508.18124 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18124.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weida Wang, Dongchen Huang, Jiatong Li, Tengchao Yang, Ziyang Zheng, Di Zhang, Dong Han, Benteng Chen, Binzhao Luo, Zhiyu Liu, Kunling Liu, Zhiyuan Gao, Shiqi Geng, Wei Ma, Jiaming Su, Xin Li, Shuchen Pu, Yuhan Shui, Qianjia Cheng, Zhihao Dou, Dongfei Cui, Changyong He, Jin Zeng, Zeke Xie, Mao Su, Dongzhan Zhou, Yuqiang Li, Wanli Ouyang, Yunqi Cai, Xi Dai, Shufei Zhang, Lei Bai, Jinguang Cheng, Zhong Fang, Hongming Weng</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> We introduce CMPhysBench, designed to assess the proficiency of Large Language Models (LLMs) in Condensed Matter Physics, as a novel Benchmark. CMPhysBench is composed of more than 520 graduate-level meticulously curated questions covering both representative subfields and foundational theoretical frameworks of condensed matter physics, such as magnetism, superconductivity, strongly correlated systems, etc. To ensure a deep understanding of the problem-solving process,we focus exclusively on calculation problems, requiring LLMs to independently generate comprehensive solutions. Meanwhile, leveraging tree-based representations of expressions, we introduce the Scalable Expression Edit Distance (SEED) score, which provides fine-grained (non-binary) partial credit and yields a more accurate assessment of similarity between prediction and ground-truth. Our results show that even the best models, Grok-4, reach only 36 average SEED score and 28% accuracy on CMPhysBench, underscoring a significant capability gap, especially for this practical and frontier domain relative to traditional physics. The code anddataset are publicly available at https://github.com/CMPhysBench/CMPhysBench.</p> - https://arxiv.org/abs/2508.18124 - Mon, 25 Aug 2025 15:32:22 +0000 + Quantile Advantage Estimation for Entropy-Safe Reasoning + https://arxiv.org/abs/2509.22611 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both hazards to the mean baseline used in value-free RL (e.g., GRPO and DAPO), which improperly penalizes negative-advantage samples under reward outliers. We propose {Quantile Advantage Estimation} (QAE), replacing the mean with a group-wise K-quantile baseline. QAE induces a response-level, two-regime gate: on hard queries (p <= 1 - K) it reinforces rare successes, while on easy queries (p > 1 - K) it targets remaining failures. Under first-order softmax updates, we prove {two-sided entropy safety}, giving lower and upper bounds on one-step entropy change that curb explosion and prevent collapse. Empirically, this minimal modification stabilizes entropy, sparsifies credit assignment (with tuned K, roughly 80% of responses receive zero advantage), and yields sustained pass@1 gains on Qwen3-8B/14B-Base across AIME 2024/2025 and AMC 2023. These results identify {baseline design} -- rather than token-level heuristics -- as the primary mechanism for scaling RLVR.</p> + https://arxiv.org/abs/2509.22611 + Fri, 26 Sep 2025 17:37:52 +0000 - InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency - https://arxiv.org/abs/2508.18265 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18265.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weiyun Wang, Zhangwei Gao, Lixin Gu, Hengjun Pu, Long Cui, Xingguang Wei, Zhaoyang Liu, Linglin Jing, Shenglong Ye, Jie Shao, Zhaokai Wang, Zhe Chen, Hongjie Zhang, Ganlin Yang, Haomin Wang, Qi Wei, Jinhui Yin, Wenhao Li, Erfei Cui, Guanzhou Chen, Zichen Ding, Changyao Tian, Zhenyu Wu, Jingjing Xie, Zehao Li, Bowen Yang, Yuchen Duan, Xuehui Wang, Songze Li, Xiangyu Zhao, Haodong Duan, Nianchen Deng, Bin Fu, Yinan He, Yi Wang, Conghui He, Botian Shi, Junjun He, Yingtong Xiong, Han Lv, Lijun Wu, Wenqi Shao, Kaipeng Zhang, Huipeng Deng, Biqing Qi, Jiaye Ge, Qipeng Guo, Wenwei Zhang, Wanli Ouyang, Limin Wang, Min Dou, Xizhou Zhu, Tong Lu, Dahua Lin, Jifeng Dai, Bowen Zhou, Weijie Su, Kai Chen, Yu Qiao, Wenhai Wang, Gen Luo</p><p><b>Upvotes:</b> 165</p><p><b>Summary:</b> We introduce InternVL 3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0\% gain in overall reasoning performance and a 4.05times inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks -- narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.</p> - https://arxiv.org/abs/2508.18265 - Mon, 25 Aug 2025 17:58:17 +0000 + LongLive: Real-time Interactive Long Video Generation + https://arxiv.org/abs/2509.22622 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22622.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, Yuyang Zhao, Xianbang Wang, Muyang Li, Enze Xie, Yingcong Chen, Yao Lu, Song Han, Yukang Chen</p><p><b>Upvotes:</b> 157</p><p><b>Summary:</b> We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video generation presents challenges in both efficiency and quality. Diffusion and Diffusion-Forcing models can produce high-quality videos but suffer from low efficiency due to bidirectional attention. Causal attention AR models support KV caching for faster inference, but often degrade in quality on long videos due to memory challenges during long-video training. In addition, beyond static prompt-based generation, interactive capabilities, such as streaming prompt inputs, are critical for dynamic content creation, enabling users to guide narratives in real time. This interactive requirement significantly increases complexity, especially in ensuring visual consistency and semantic coherence during prompt transitions. To address these challenges, LongLive adopts a causal, frame-level AR design that integrates a KV-recache mechanism that refreshes cached states with new prompts for smooth, adherent switches; streaming long tuning to enable long video training and to align training and inference (train-long-test-long); and short window attention paired with a frame-level attention sink, shorten as frame sink, preserving long-range consistency while enabling faster generation. With these key designs, LongLive fine-tunes a 1.3B-parameter short-clip model to minute-long generation in just 32 GPU-days. At inference, LongLive sustains 20.7 FPS on a single NVIDIA H100, achieves strong performance on VBench in both short and long videos. LongLive supports up to 240-second videos on a single H100 GPU. LongLive further supports INT8-quantized inference with only marginal quality loss.</p> + https://arxiv.org/abs/2509.22622 + Fri, 26 Sep 2025 17:48:24 +0000 - UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning - https://arxiv.org/abs/2508.18756 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18756.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihao Huang, Yu Bao, Qiyang Min, Siyan Chen, Ran Guo, Hongzhi Huang, Defa Zhu, Yutao Zeng, Banggu Wu, Xun Zhou, Siyuan Qiao</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> While Mixture of Experts (MoE) models achieve remarkable efficiency by activating only subsets of parameters, they suffer from high memory access costs during inference. Memory-layer architectures offer an appealing alternative with very few memory access, but previous attempts like UltraMem have only matched the performance of 2-expert MoE models, falling significantly short of state-of-the-art 8-expert configurations. We present UltraMemV2, a redesigned memory-layer architecture that closes this performance gap. Our approach introduces five key improvements: integrating memory layers into every transformer block, simplifying value expansion with single linear projections, adopting FFN-based value processing from PEER, implementing principled parameter initialization, and rebalancing memory-to-FFN computation ratios. Through extensive evaluation, we demonstrate that UltraMemV2 achieves performance parity with 8-expert MoE models under same computation and parameters but significantly low memory access. Notably, UltraMemV2 shows superior performance on memory-intensive tasks, with improvements of +1.6 points on long-context memorization, +6.2 points on multi-round memorization, and +7.9 points on in-context learning. We validate our approach at scale with models up to 2.5B activated parameters from 120B total parameters, and establish that activation density has greater impact on performance than total sparse parameter count. Our work brings memory-layer architectures to performance parity with state-of-the-art MoE models, presenting a compelling alternative for efficient sparse computation.</p> - https://arxiv.org/abs/2508.18756 - Tue, 26 Aug 2025 07:33:11 +0000 + Variational Reasoning for Language Models + https://arxiv.org/abs/2509.22637 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22637.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a multi-trace objective for tighter bounds and propose a forward-KL formulation that stabilizes the training of the variational posterior. We further show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives, where an implicit weighting by model accuracy naturally arises from the derivation and reveals a previously unnoticed bias toward easier questions. We empirically validate our method on the Qwen 2.5 and Qwen 3 model families across a wide range of reasoning tasks. Overall, our work provides a principled probabilistic perspective that unifies variational inference with RL-style methods and yields stable objectives for improving the reasoning ability of language models. Our code is available at https://github.com/sail-sg/variational-reasoning.</p> + https://arxiv.org/abs/2509.22637 + Fri, 26 Sep 2025 17:58:10 +0000 - USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning - https://arxiv.org/abs/2508.18966 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.18966.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaojin Wu, Mengqi Huang, Yufeng Cheng, Wenxu Wu, Jiahe Tian, Yiming Luo, Fei Ding, Qian He</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Existing literature typically treats style-driven and subject-driven generation as two disjoint tasks: the former prioritizes stylistic similarity, whereas the latter insists on subject consistency, resulting in an apparent antagonism. We argue that both objectives can be unified under a single framework because they ultimately concern the disentanglement and re-composition of content and style, a long-standing theme in style-driven research. To this end, we present USO, a Unified Style-Subject Optimized customization model. First, we construct a large-scale triplet dataset consisting of content images, style images, and their corresponding stylized content images. Second, we introduce a disentangled learning scheme that simultaneously aligns style features and disentangles content from style through two complementary objectives, style-alignment training and content-style disentanglement training. Third, we incorporate a style reward-learning paradigm denoted as SRL to further enhance the model's performance. Finally, we release USO-Bench, the first benchmark that jointly evaluates style similarity and subject fidelity across multiple metrics. Extensive experiments demonstrate that USO achieves state-of-the-art performance among open-source models along both dimensions of subject consistency and style similarity. Code and model: https://github.com/bytedance/USO</p> - https://arxiv.org/abs/2508.18966 - Tue, 26 Aug 2025 12:10:24 +0000 + Language Models Can Learn from Verbal Feedback Without Scalar Rewards + https://arxiv.org/abs/2509.22638 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Renjie Luo, Zichen Liu, Xiangyan Liu, Chao Du, Min Lin, Wenhu Chen, Wei Lu, Tianyu Pang</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> LLMs are often trained with RL from human or AI feedback, yet such methods typically compress nuanced feedback into scalar rewards, discarding much of their richness and inducing scale imbalance. We propose treating verbal feedback as a conditioning signal. Inspired by language priors in text-to-image generation, which enable novel outputs from unseen prompts, we introduce the feedback-conditional policy (FCP). FCP learns directly from response-feedback pairs, approximating the feedback-conditional posterior through maximum likelihood training on offline data. We further develop an online bootstrapping stage where the policy generates under positive conditions and receives fresh feedback to refine itself. This reframes feedback-driven learning as conditional generation rather than reward optimization, offering a more expressive way for LLMs to directly learn from verbal feedback. Our code is available at https://github.com/sail-sg/feedback-conditional-policy.</p> + https://arxiv.org/abs/2509.22638 + Fri, 26 Sep 2025 17:58:27 +0000 - VibeVoice Technical Report - https://arxiv.org/abs/2508.19205 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.19205.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiliang Peng, Jianwei Yu, Wenhui Wang, Yaoyao Chang, Yutao Sun, Li Dong, Yi Zhu, Weijiang Xu, Hangbo Bao, Zehua Wang, Shaohan Huang, Yan Xia, Furu Wei</p><p><b>Upvotes:</b> 102</p><p><b>Summary:</b> This report presents VibeVoice, a novel model designed to synthesize long-form speech with multiple speakers by employing next-token diffusion, which is a unified method for modeling continuous data by autoregressively generating latent vectors via diffusion. To enable this, we introduce a novel continuous speech tokenizer that, when compared to the popular Encodec model, improves data compression by 80 times while maintaining comparable performance. The tokenizer effectively preserves audio fidelity while significantly boosting computational efficiency for processing long sequences. Thus, VibeVoice can synthesize long-form speech for up to 90 minutes (in a 64K context window length) with a maximum of 4 speakers, capturing the authentic conversational ``vibe'' and surpassing open-source and proprietary dialogue models.</p> - https://arxiv.org/abs/2508.19205 - Tue, 26 Aug 2025 17:09:12 +0000 + Multiplayer Nash Preference Optimization + https://arxiv.org/abs/2509.23102 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23102.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fang Wu, Xu Huang, Weihao Xuan, Zhiwei Zhang, Yijia Xiao, Guancheng Wan, Xiaomin Li, Bing Hu, Peng Xia, Jure Leskovec, Yejin Choi</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models (LLMs) with human preferences. However, reward-based methods built on the Bradley-Terry assumption struggle to capture the non-transitive and heterogeneous nature of real-world preferences. To address this, recent studies have reframed alignment as a two-player Nash game, giving rise to Nash learning from human feedback (NLHF). While this perspective has inspired algorithms such as INPO, ONPO, and EGPO with strong theoretical and empirical guarantees, they remain fundamentally restricted to two-player interactions, creating a single-opponent bias that fails to capture the full complexity of realistic preference structures. In this work, we introduce Multiplayer Nash Preference Optimization (MNPO), a novel framework that generalizes NLHF to the multiplayer regime. It formulates alignment as an n-player game, where each policy competes against a population of opponents while being regularized toward a reference model. Our framework establishes well-defined Nash equilibria in multiplayer settings and extends the concept of duality gap to quantify approximation quality. We demonstrate that MNPO inherits the equilibrium guarantees of two-player methods while enabling richer competitive dynamics and improved coverage of diverse preference structures. Through comprehensive empirical evaluation, we show that MNPO consistently outperforms existing NLHF baselines on instruction-following benchmarks, achieving superior alignment quality under heterogeneous annotator conditions and mixed-policy evaluation scenarios. Together, these results establish MNPO as a principled and scalable framework for aligning LLMs with complex, non-transitive human preferences. Code is available at https://github.com/smiles724/MNPO.</p> + https://arxiv.org/abs/2509.23102 + Sat, 27 Sep 2025 04:18:33 +0000 - OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation - https://arxiv.org/abs/2508.19209 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.19209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianwen Jiang, Weihong Zeng, Zerong Zheng, Jiaqi Yang, Chao Liang, Wang Liao, Han Liang, Yuan Zhang, Mingyuan Gao</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Existing video avatar models can produce fluid human animations, yet they struggle to move beyond mere physical likeness to capture a character's authentic essence. Their motions typically synchronize with low-level cues like audio rhythm, lacking a deeper semantic understanding of emotion, intent, or context. To bridge this gap, we propose a framework designed to generate character animations that are not only physically plausible but also semantically coherent and expressive. Our model, OmniHuman-1.5, is built upon two key technical contributions. First, we leverage Multimodal Large Language Models to synthesize a structured textual representation of conditions that provides high-level semantic guidance. This guidance steers our motion generator beyond simplistic rhythmic synchronization, enabling the production of actions that are contextually and emotionally resonant. Second, to ensure the effective fusion of these multimodal inputs and mitigate inter-modality conflicts, we introduce a specialized Multimodal DiT architecture with a novel Pseudo Last Frame design. The synergy of these components allows our model to accurately interpret the joint semantics of audio, images, and text, thereby generating motions that are deeply coherent with the character, scene, and linguistic content. Extensive experiments demonstrate that our model achieves leading performance across a comprehensive set of metrics, including lip-sync accuracy, video quality, motion naturalness and semantic consistency with textual prompts. Furthermore, our approach shows remarkable extensibility to complex scenarios, such as those involving multi-person and non-human subjects. Homepage: https://omnihuman-lab.github.io/v1_5/</p> - https://arxiv.org/abs/2508.19209 - Tue, 26 Aug 2025 17:15:26 +0000 + Democratizing AI scientists using ToolUniverse + https://arxiv.org/abs/2509.23426 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shanghua Gao, Richard Zhu, Pengwei Sui, Zhenglun Kong, Sufian Aldogom, Yepeng Huang, Ayush Noori, Reza Shamji, Krishna Parvataneni, Theodoros Tsiligkaridis, Marinka Zitnik</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because they are bespoke, tied to rigid workflows, and lack shared environments that unify tools, data, and analyses into a common ecosystem. In omics, unified ecosystems have transformed research by enabling interoperability, reuse, and community-driven development; AI scientists require comparable infrastructure. We present ToolUniverse, an ecosystem for building AI scientists from any language or reasoning model, whether open or closed. TOOLUNIVERSE standardizes how AI scientists identify and call tools, integrating more than 600 machine learning models, datasets, APIs, and scientific packages for data analysis, knowledge retrieval, and experimental design. It automatically refines tool interfaces for correct use by AI scientists, creates new tools from natural language descriptions, iteratively optimizes tool specifications, and composes tools into agentic workflows. In a case study of hypercholesterolemia, ToolUniverse was used to create an AI scientist to identify a potent analog of a drug with favorable predicted properties. The open-source ToolUniverse is available at https://aiscientist.tools.</p> + https://arxiv.org/abs/2509.23426 + Sat, 27 Sep 2025 17:38:53 +0000 - VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space - https://arxiv.org/abs/2508.19247 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.19247.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lin Li, Zehuan Huang, Haoran Feng, Gengxiong Zhuang, Rui Chen, Chunchao Guo, Lu Sheng</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> 3D local editing of specified regions is crucial for game industry and robot interaction. Recent methods typically edit rendered multi-view images and then reconstruct 3D models, but they face challenges in precisely preserving unedited regions and overall coherence. Inspired by structured 3D generative models, we propose VoxHammer, a novel training-free approach that performs precise and coherent editing in 3D latent space. Given a 3D model, VoxHammer first predicts its inversion trajectory and obtains its inverted latents and key-value tokens at each timestep. Subsequently, in the denoising and editing phase, we replace the denoising features of preserved regions with the corresponding inverted latents and cached key-value tokens. By retaining these contextual features, this approach ensures consistent reconstruction of preserved areas and coherent integration of edited parts. To evaluate the consistency of preserved regions, we constructed Edit3D-Bench, a human-annotated dataset comprising hundreds of samples, each with carefully labeled 3D editing regions. Experiments demonstrate that VoxHammer significantly outperforms existing methods in terms of both 3D consistency of preserved regions and overall quality. Our method holds promise for synthesizing high-quality edited paired data, thereby laying the data foundation for in-context 3D generation. See our project page at https://huanngzh.github.io/VoxHammer-Page/.</p> - https://arxiv.org/abs/2508.19247 - Tue, 26 Aug 2025 17:59:47 +0000 + Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR + https://arxiv.org/abs/2509.23808 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23808.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, Zhi Wang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> A prevailing view in Reinforcement Learning for Verifiable Rewards (RLVR) interprets recent progress through the lens of an exploration-exploitation trade-off, a perspective largely shaped by token-level metrics. We re-examine this perspective, proposing that this perceived trade-off may not be a fundamental constraint but rather an artifact of the measurement level. To investigate this, we shift the analysis to the semantically rich hidden-state space, adopting Effective Rank (ER) to quantify exploration and proposing its novel first- and second-order derivatives, named Effective Rank Velocity (ERV) and Effective Rank Acceleration (ERA), to capture exploitation dynamics. Our analysis reveals that at the hidden-state level, exploration and exploitation could be decoupled (Sec. 4). This finding reveals an opportunity to enhance both capacities simultaneously. This insight motivates our method, Velocity-Exploiting Rank-Learning (VERL), the first to operationalize the principle of synergistic exploration-exploitation enhancement by directly shaping the RL advantage function. The key innovation is leveraging the theoretically stable ERA as a predictive meta-controller to create a synergistic, dual-channel incentive structure. Instead of forcing a trade-off, VERL prospectively amplifies rewards for exploration to preempt overconfidence and reinforces exploitative gains to consolidate reasoning. Experiments across diverse LLMs and reasoning benchmarks show consistent gains, including up to 21.4% absolute accuracy improvement on the challenging Gaokao 2024 dataset.</p> + https://arxiv.org/abs/2509.23808 + Sun, 28 Sep 2025 11:14:58 +0000 - Self-Rewarding Vision-Language Model via Reasoning Decomposition - https://arxiv.org/abs/2508.19652 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.19652.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zongxia Li, Wenhao Yu, Chengsong Huang, Rui Liu, Zhenwen Liang, Fuxiao Liu, Jingxi Che, Dian Yu, Jordan Boyd-Graber, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> Vision-Language Models (VLMs) often suffer from visual hallucinations, saying things that are not actually in the image, and language shortcuts, where they skip the visual part and just rely on text priors. These issues arise because most post-training methods for VLMs rely on simple verifiable answer matching and supervise only final outputs, leaving intermediate visual reasoning without explicit guidance. As a result, VLMs receive sparse visual signals and often learn to prioritize language-based reasoning over visual perception. To mitigate this, some existing methods add visual supervision using human annotations or distilled labels from external large models. However, human annotations are labor-intensive and costly, and because external signals cannot adapt to the evolving policy, they cause distributional shifts that can lead to reward hacking. In this paper, we introduce Vision-SR1, a self-rewarding method that improves visual reasoning without relying on external visual supervisions via reinforcement learning. Vision-SR1 decomposes VLM reasoning into two stages: visual perception and language reasoning. The model is first prompted to produce self-contained visual perceptions that are sufficient to answer the question without referring back the input image. To validate this self-containment, the same VLM model is then re-prompted to perform language reasoning using only the generated perception as input to compute reward. This self-reward is combined with supervision on final outputs, providing a balanced training signal that strengthens both visual perception and language reasoning. Our experiments demonstrate that Vision-SR1 improves visual reasoning, mitigates visual hallucinations, and reduces reliance on language shortcuts across diverse vision-language tasks.</p> - https://arxiv.org/abs/2508.19652 - Wed, 27 Aug 2025 08:01:03 +0000 + SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention + https://arxiv.org/abs/2509.24006 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24006.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jintao Zhang, Haoxu Wang, Kai Jiang, Shuo Yang, Kaiwen Zheng, Haocheng Xi, Ziteng Wang, Hongzhou Zhu, Min Zhao, Ion Stoica, Joseph E. Gonzalez, Jun Zhu, Jianfei Chen</p><p><b>Upvotes:</b> 98</p><p><b>Summary:</b> In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We find that attention weights can be separated into two parts: a small fraction of large weights with high rank and the remaining weights with very low rank. This naturally suggests applying sparse acceleration to the first part and low-rank acceleration to the second. Based on this finding, we propose SLA (Sparse-Linear Attention), a trainable attention method that fuses sparse and linear attention to accelerate diffusion models. SLA classifies attention weights into critical, marginal, and negligible categories, applying O(N^2) attention to critical weights, O(N) attention to marginal weights, and skipping negligible ones. SLA combines these computations into a single GPU kernel and supports both forward and backward passes. With only a few fine-tuning steps using SLA, DiT models achieve a 20x reduction in attention computation, resulting in significant acceleration without loss of generation quality. Experiments show that SLA reduces attention computation by 95% without degrading end-to-end generation quality, outperforming baseline methods. In addition, we implement an efficient GPU kernel for SLA, which yields a 13.7x speedup in attention computation and a 2.2x end-to-end speedup in video generation on Wan2.1-1.3B.</p> + https://arxiv.org/abs/2509.24006 + Sun, 28 Sep 2025 17:58:59 +0000 - CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning - https://arxiv.org/abs/2508.20096 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20096.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyi Sun, Yuhang Cao, Jianze Liang, Qiushi Sun, Ziyu Liu, Zhixiong Zhang, Yuhang Zang, Xiaoyi Dong, Kai Chen, Dahua Lin, Jiaqi Wang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Autonomous agents for Graphical User Interfaces (GUIs) face significant challenges in specialized domains such as scientific computing, where both long-horizon planning and precise execution are required. Existing approaches suffer from a trade-off: generalist agents excel at planning but perform poorly in execution, while specialized agents demonstrate the opposite weakness. Recent compositional frameworks attempt to bridge this gap by combining a planner and an actor, but they are typically static and non-trainable, which prevents adaptation from experience. This is a critical limitation given the scarcity of high-quality data in scientific domains. To address these limitations, we introduce CODA, a novel and trainable compositional framework that integrates a generalist planner (Cerebrum) with a specialist executor (Cerebellum), trained via a dedicated two-stage pipeline. In the first stage, Specialization, we apply a decoupled GRPO approach to train an expert planner for each scientific application individually, bootstrapping from a small set of task trajectories. In the second stage, Generalization, we aggregate all successful trajectories from the specialized experts to build a consolidated dataset, which is then used for supervised fine-tuning of the final planner. This equips CODA with both robust execution and cross-domain generalization. Evaluated on four challenging applications from the ScienceBoard benchmark, CODA significantly outperforms baselines and establishes a new state of the art among open-source models.</p> - https://arxiv.org/abs/2508.20096 - Wed, 27 Aug 2025 17:59:50 +0000 + SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer + https://arxiv.org/abs/2509.24695 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24695.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation.</p> + https://arxiv.org/abs/2509.24695 + Mon, 29 Sep 2025 12:28:09 +0000 - MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers - https://arxiv.org/abs/2508.20453 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20453.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenting Wang, Qi Chang, Hemani Patel, Shashank Biju, Cheng-En Wu, Quan Liu, Aolin Ding, Alireza Rezazadeh, Ankit Shah, Yujia Bao, Eugene Siow</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> We introduce MCP-Bench, a benchmark for evaluating large language models (LLMs) on realistic, multi-step tasks that demand tool use, cross-tool coordination, precise parameter control, and planning/reasoning for solving tasks. Built on the Model Context Protocol (MCP), MCP-Bench connects LLMs to 28 representative live MCP servers spanning 250 tools across domains such as finance, traveling, scientific computing, and academic search. Unlike prior API-based benchmarks, each MCP server provides a set of complementary tools designed to work together, enabling the construction of authentic, multi-step tasks with rich input-output coupling. Tasks in MCP-Bench test agents' ability to retrieve relevant tools from fuzzy instructions without explicit tool names, plan multi-hop execution trajectories for complex objectives, ground responses in intermediate tool outputs, and orchestrate cross-domain workflows - capabilities not adequately evaluated by existing benchmarks that rely on explicit tool specifications, shallow few-step workflows, and isolated domain operations. We propose a multi-faceted evaluation framework covering tool-level schema understanding and usage, trajectory-level planning, and task completion. Experiments on 20 advanced LLMs reveal persistent challenges in MCP-Bench. Code and data: https://github.com/Accenture/mcp-bench.</p> - https://arxiv.org/abs/2508.20453 - Thu, 28 Aug 2025 05:58:57 +0000 + RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark + https://arxiv.org/abs/2509.24897 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24897.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Shi, Yuhao Dong, Yue Ding, Yuran Wang, Xuanyu Zhu, Sheng Zhou, Wenting Liu, Haochen Tian, Rundong Wang, Huanqian Wang, Zuyan Liu, Bohan Zeng, Ruizhe Chen, Qixun Wang, Zhuoran Zhang, Xinlong Chen, Chengzhuo Tong, Bozhou Li, Chaoyou Fu, Qiang Liu, Haotian Wang, Wenjing Yang, Yuanxing Zhang, Pengfei Wan, Yi-Fan Zhang, Ziwei Liu</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this architectural unification actually enable synergetic interaction between the constituent capabilities? Existing evaluation paradigms, which primarily assess understanding and generation in isolation, are insufficient for determining whether a unified model can leverage its understanding to enhance its generation, or use generative simulation to facilitate deeper comprehension. To address this critical gap, we introduce RealUnify, a benchmark specifically designed to evaluate bidirectional capability synergy. RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks. It is structured around two core axes: 1) Understanding Enhances Generation, which requires reasoning (e.g., commonsense, logic) to guide image generation, and 2) Generation Enhances Understanding, which necessitates mental simulation or reconstruction (e.g., of transformed or disordered visual inputs) to solve reasoning tasks. A key contribution is our dual-evaluation protocol, which combines direct end-to-end assessment with a diagnostic stepwise evaluation that decomposes tasks into distinct understanding and generation phases. This protocol allows us to precisely discern whether performance bottlenecks stem from deficiencies in core abilities or from a failure to integrate them. Through large-scale evaluations of 12 leading unified models and 6 specialized baselines, we find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient. These results highlight the need for new training strategies and inductive biases to fully unlock the potential of unified modeling.</p> + https://arxiv.org/abs/2509.24897 + Mon, 29 Sep 2025 15:07:28 +0000 - rStar2-Agent: Agentic Reasoning Technical Report - https://arxiv.org/abs/2508.20722 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20722.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ning Shang, Yifei Liu, Yi Zhu, Li Lyna Zhang, Weijiang Xu, Xinyu Guan, Buze Zhang, Bingcheng Dong, Xudong Zhou, Bowen Zhang, Ying Xin, Ziming Miao, Scarlett Li, Fan Yang, Mao Yang</p><p><b>Upvotes:</b> 67</p><p><b>Summary:</b> We introduce rStar2-Agent, a 14B math reasoning model trained with agentic reinforcement learning to achieve frontier-level performance. Beyond current long CoT, the model demonstrates advanced cognitive behaviors, such as thinking carefully before using Python coding tools and reflecting on code execution feedback to autonomously explore, verify, and refine intermediate steps in complex problem-solving. This capability is enabled through three key innovations that makes agentic RL effective at scale: (i) an efficient RL infrastructure with a reliable Python code environment that supports high-throughput execution and mitigates the high rollout costs, enabling training on limited GPU resources (64 MI300X GPUs); (ii) GRPO-RoC, an agentic RL algorithm with a Resample-on-Correct rollout strategy that addresses the inherent environment noises from coding tools, allowing the model to reason more effectively in a code environment; (iii) An efficient agent training recipe that starts with non-reasoning SFT and progresses through multi-RL stages, yielding advanced cognitive abilities with minimal compute cost. To this end, rStar2-Agent boosts a pre-trained 14B model to state of the art in only 510 RL steps within one week, achieving average pass@1 scores of 80.6% on AIME24 and 69.8% on AIME25, surpassing DeepSeek-R1 (671B) with significantly shorter responses. Beyond mathematics, rStar2-Agent-14B also demonstrates strong generalization to alignment, scientific reasoning, and agentic tool-use tasks. Code and training recipes are available at https://github.com/microsoft/rStar.</p> - https://arxiv.org/abs/2508.20722 - Thu, 28 Aug 2025 12:45:25 +0000 + OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing + https://arxiv.org/abs/2509.24900 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24900.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhihong Chen, Xuehai Bai, Yang Shi, Chaoyou Fu, Huanyu Zhang, Haotian Wang, Xiaoyan Sun, Zhang Zhang, Liang Wang, Yuanxing Zhang, Pengfei Wan, Yi-Fan Zhang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> The performance of unified multimodal models for image generation and editing is fundamentally constrained by the quality and comprehensiveness of their training data. While existing datasets have covered basic tasks like style transfer and simple object manipulation, they often lack the systematic structure and challenging scenarios required for real-world applications. To address this bottleneck, we introduce OpenGPT-4o-Image, a large-scale dataset constructed using a novel methodology that combines hierarchical task taxonomy with automated data generation. Our taxonomy not only includes fundamental capabilities such as text rendering and style control but also introduces highly practical yet challenging categories like scientific imagery for chemistry illustrations and complex instruction editing requiring simultaneous execution of multiple operations. Through an automated pipeline leveraging structured resource pools and GPT-4o, we generate 80k high-quality instruction-image pairs with controlled diversity, covering 11 major domains and 51 subtasks. Extensive experiments show that fine-tuning leading models on our dataset achieves significant performance gains across multiple benchmarks, with improvements of up to 18\% on editing tasks (UniWorld-V1 on ImgEdit-Bench) and 13% on generation tasks (Harmon on GenEval). Our work demonstrates that systematic data construction is key to advancing multimodal AI capabilities.</p> + https://arxiv.org/abs/2509.24900 + Mon, 29 Sep 2025 15:11:09 +0000 - Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning - https://arxiv.org/abs/2508.20751 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.20751.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibin Wang, Zhimin Li, Yuhang Zang, Yujie Zhou, Jiazi Bu, Chunyu Wang, Qinglin Lu, Cheng Jin, Jiaqi Wang</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods using pointwise reward models (RM) for scoring generated images are susceptible to reward hacking. We reveal that this happens when minimal score differences between images are amplified after normalization, creating illusory advantages that drive the model to over-optimize for trivial gains, ultimately destabilizing the image generation process. To address this, we propose Pref-GRPO, a pairwise preference reward-based GRPO method that shifts the optimization objective from score maximization to preference fitting, ensuring more stable training. In Pref-GRPO, images are pairwise compared within each group using preference RM, and the win rate is used as the reward signal. Extensive experiments demonstrate that PREF-GRPO differentiates subtle image quality differences, providing more stable advantages and mitigating reward hacking. Additionally, existing T2I benchmarks are limited by coarse evaluation criteria, hindering comprehensive model assessment. To solve this, we introduce UniGenBench, a unified T2I benchmark comprising 600 prompts across 5 main themes and 20 subthemes. It evaluates semantic consistency through 10 primary and 27 sub-criteria, leveraging MLLM for benchmark construction and evaluation. Our benchmarks uncover the strengths and weaknesses of both open and closed-source T2I models and validate the effectiveness of Pref-GRPO.</p> - https://arxiv.org/abs/2508.20751 - Thu, 28 Aug 2025 13:11:24 +0000 + Visual Jigsaw Post-Training Improves MLLMs + https://arxiv.org/abs/2509.25190 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25190.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Penghao Wu, Yushan Zhang, Haiwen Diao, Bo Li, Lewei Lu, Ziwei Liu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Reinforcement learning based post-training has recently emerged as a powerful paradigm for enhancing the alignment and reasoning capabilities of multimodal large language models (MLLMs). While vision-centric post-training is crucial for enhancing MLLMs' intrinsic understanding of visual signals, current post-training paradigms are predominantly text-centric, where dense visual inputs are only leveraged to extract sparse cues for text-based reasoning. There exist a few approaches in this direction, however, they often still rely on text as an intermediate mediator or introduce additional visual generative designs. In this work, we introduce Visual Jigsaw, a generic self-supervised post-training framework designed to strengthen visual understanding in MLLMs. Visual Jigsaw is formulated as a general ordering task: visual inputs are partitioned, shuffled, and the model must reconstruct the visual information by producing the correct permutation in natural language. This naturally aligns with reinforcement learning from verifiable rewards (RLVR), requires no additional visual generative components, and derives its supervisory signal automatically without any annotations. We instantiate Visual Jigsaw across three visual modalities, including images, videos, and 3D data. Extensive experiments demonstrate substantial improvements in fine-grained perception, temporal reasoning, and 3D spatial understanding. Our findings highlight the potential of self-supervised vision-centric tasks in post-training MLLMs and aim to inspire further research on vision-centric pretext designs. Project Page: https://penghao-wu.github.io/visual_jigsaw/</p> + https://arxiv.org/abs/2509.25190 + Mon, 29 Sep 2025 17:59:57 +0000