748 lines
222 KiB
XML
748 lines
222 KiB
XML
<?xml version='1.0' encoding='UTF-8'?>
|
||
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
|
||
<channel>
|
||
<title>Hugging Face Daily Papers</title>
|
||
<link>https://huggingface.co/papers</link>
|
||
<description>Daily research papers curated by the Hugging Face community.</description>
|
||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||
<generator>python-feedgen</generator>
|
||
<language>en</language>
|
||
<lastBuildDate>Mon, 19 Jan 2026 00:13:23 +0000</lastBuildDate>
|
||
<item>
|
||
<title>ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands</title>
|
||
<link>https://arxiv.org/abs/2512.24965</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24965.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Hu, Kevin Qinghong Lin, Mike Zheng Shou</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Building intelligent agents capable of dexterous manipulation is essential for achieving human-like automation in both robotics and digital environments. However, existing GUI agents rely on discrete click predictions (x,y), which prohibits free-form, closed-loop trajectories (e.g. dragging a progress bar) that require continuous, on-the-fly perception and adjustment. In this work, we develop ShowUI-π, the first flow-based generative model as GUI dexterous hand, featuring the following designs: (i) Unified Discrete-Continuous Actions, integrating discrete clicks and continuous drags within a shared model, enabling flexible adaptation across diverse interaction modes; (ii) Flow-based Action Generation for drag modeling, which predicts incremental cursor adjustments from continuous visual observations via a lightweight action expert, ensuring smooth and stable trajectories; (iii) Drag Training data and Benchmark, where we manually collect and synthesize 20K drag trajectories across five domains (e.g. PowerPoint, Adobe Premiere Pro), and introduce ScreenDrag, a benchmark with comprehensive online and offline evaluation protocols for assessing GUI agents' drag capabilities. Our experiments show that proprietary GUI agents still struggle on ScreenDrag (e.g. Operator scores 13.27, and the best Gemini-2.5-CUA reaches 22.18). In contrast, ShowUI-π achieves 26.98 with only 450M parameters, underscoring both the difficulty of the task and the effectiveness of our approach. We hope this work advances GUI agents toward human-like dexterous control in digital world. The code is available at https://github.com/showlab/showui-pi.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2512.24965</guid>
|
||
<pubDate>Wed, 31 Dec 2025 16:51:14 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving</title>
|
||
<link>https://arxiv.org/abs/2601.01528</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Zhou, Hao Shao, Letian Wang, Zhuofan Zong, Hongsheng Li, Steven L. Waslander</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Video generation models, as one form of world models, have emerged as one of the most exciting frontiers in AI, promising agents the ability to imagine the future by modeling the temporal evolution of complex scenes. In autonomous driving, this vision gives rise to driving world models: generative simulators that imagine ego and agent futures, enabling scalable simulation, safe testing of corner cases, and rich synthetic data generation. Yet, despite fast-growing research activity, the field lacks a rigorous benchmark to measure progress and guide priorities. Existing evaluations remain limited: generic video metrics overlook safety-critical imaging factors; trajectory plausibility is rarely quantified; temporal and agent-level consistency is neglected; and controllability with respect to ego conditioning is ignored. Moreover, current datasets fail to cover the diversity of conditions required for real-world deployment. To address these gaps, we present DrivingGen, the first comprehensive benchmark for generative driving world models. DrivingGen combines a diverse evaluation dataset curated from both driving datasets and internet-scale video sources, spanning varied weather, time of day, geographic regions, and complex maneuvers, with a suite of new metrics that jointly assess visual realism, trajectory plausibility, temporal coherence, and controllability. Benchmarking 14 state-of-the-art models reveals clear trade-offs: general models look better but break physics, while driving-specific ones capture motion realistically but lag in visual quality. DrivingGen offers a unified evaluation framework to foster reliable, controllable, and deployable driving world models, enabling scalable simulation, planning, and data-driven decision-making.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.01528</guid>
|
||
<pubDate>Sun, 04 Jan 2026 13:36:21 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>VIBE: Visual Instruction Based Editor</title>
|
||
<link>https://arxiv.org/abs/2601.02242</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02242.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Grigorii Alekseenko, Aleksandr Gordeev, Irina Tolstykh, Bulat Suleimanov, Vladimir Dokholyan, Georgii Fedorov, Sergey Yakubson, Aleksandra Tsybina, Mikhail Chernyshov, Maksim Kuprashevich</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> Instruction-based image editing is among the fastest developing areas in generative AI. Over the past year, the field has reached a new level, with dozens of open-source models released alongside highly capable commercial systems. However, only a limited number of open-source approaches currently achieve real-world quality. In addition, diffusion backbones, the dominant choice for these pipelines, are often large and computationally expensive for many deployments and research settings, with widely used variants typically containing 6B to 20B parameters. This paper presents a compact, high-throughput instruction-based image editing pipeline that uses a modern 2B-parameter Qwen3-VL model to guide the editing process and the 1.6B-parameter diffusion model Sana1.5 for image generation. Our design decisions across architecture, data processing, training configuration, and evaluation target low-cost inference and strict source consistency while maintaining high quality across the major edit categories feasible at this scale. Evaluated on the ImgEdit and GEdit benchmarks, the proposed method matches or exceeds the performance of substantially heavier baselines, including models with several times as many parameters and higher inference cost, and is particularly strong on edits that require preserving the input image, such as an attribute adjustment, object removal, background edits, and targeted replacement. The model fits within 24 GB of GPU memory and generates edited images at up to 2K resolution in approximately 4 seconds on an NVIDIA H100 in BF16, without additional inference optimizations or distillation.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.02242</guid>
|
||
<pubDate>Mon, 05 Jan 2026 16:17:20 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>AnyDepth: Depth Estimation Made Easy</title>
|
||
<link>https://arxiv.org/abs/2601.02760</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyu Ren, Zeyu Zhang, Wukai Li, Qingxiang Liu, Hao Tang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Monocular depth estimation aims to recover the depth information of 3D scenes from 2D images. Recent work has made significant progress, but its reliance on large-scale datasets and complex decoders has limited its efficiency and generalization ability. In this paper, we propose a lightweight and data-centric framework for zero-shot monocular depth estimation. We first adopt DINOv3 as the visual encoder to obtain high-quality dense features. Secondly, to address the inherent drawbacks of the complex structure of the DPT, we design the Simple Depth Transformer (SDT), a compact transformer-based decoder. Compared to the DPT, it uses a single-path feature fusion and upsampling process to reduce the computational overhead of cross-scale feature fusion, achieving higher accuracy while reducing the number of parameters by approximately 85%-89%. Furthermore, we propose a quality-based filtering strategy to filter out harmful samples, thereby reducing dataset size while improving overall training quality. Extensive experiments on five benchmarks demonstrate that our framework surpasses the DPT in accuracy. This work highlights the importance of balancing model design and data quality for achieving efficient and generalizable zero-shot depth estimation. Code: https://github.com/AIGeeksGroup/AnyDepth. Website: https://aigeeksgroup.github.io/AnyDepth.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.02760</guid>
|
||
<pubDate>Tue, 06 Jan 2026 06:51:35 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MMFormalizer: Multimodal Autoformalization in the Wild</title>
|
||
<link>https://arxiv.org/abs/2601.03017</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03017.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jing Xiong, Qi Han, Yunta Hsieh, Hui Shen, Huajian Xin, Chaofan Tao, Chenyang Zhao, Hengyuan Zhang, Taiqiang Wu, Zhen Zhang, Haochen Wang, Zhongwei Wan, Lingpeng Kong, Ngai Wong</p><p><b>Upvotes:</b> 102</p><p><b>Summary:</b> Autoformalization, which translates natural language mathematics into formal statements to enable machine reasoning, faces fundamental challenges in the wild due to the multimodal nature of the physical world, where physics requires inferring hidden constraints (e.g., mass or energy) from visual elements. To address this, we propose MMFormalizer, which extends autoformalization beyond text by integrating adaptive grounding with entities from real-world mathematical and physical domains. MMFormalizer recursively constructs formal propositions from perceptually grounded primitives through recursive grounding and axiom composition, with adaptive recursive termination ensuring that every abstraction is supported by visual evidence and anchored in dimensional or axiomatic grounding. We evaluate MMFormalizer on a new benchmark, PhyX-AF, comprising 115 curated samples from MathVerse, PhyX, Synthetic Geometry, and Analytic Geometry, covering diverse multimodal autoformalization tasks. Results show that frontier models such as GPT-5 and Gemini-3-Pro achieve the highest compile and semantic accuracy, with GPT-5 excelling in physical reasoning, while geometry remains the most challenging domain. Overall, MMFormalizer provides a scalable framework for unified multimodal autoformalization, bridging perception and formal reasoning. To the best of our knowledge, this is the first multimodal autoformalization method capable of handling classical mechanics (derived from the Hamiltonian), as well as relativity, quantum mechanics, and thermodynamics. More details are available on our project page: MMFormalizer.github.io</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.03017</guid>
|
||
<pubDate>Tue, 06 Jan 2026 13:42:51 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>CaricatureGS: Exaggerating 3D Gaussian Splatting Faces With Gaussian Curvature</title>
|
||
<link>https://arxiv.org/abs/2601.03319</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03319.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Eldad Matmon, Amit Bracha, Noam Rotstein, Ron Kimmel</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> A photorealistic and controllable 3D caricaturization framework for faces is introduced. We start with an intrinsic Gaussian curvature-based surface exaggeration technique, which, when coupled with texture, tends to produce over-smoothed renders. To address this, we resort to 3D Gaussian Splatting (3DGS), which has recently been shown to produce realistic free-viewpoint avatars. Given a multiview sequence, we extract a FLAME mesh, solve a curvature-weighted Poisson equation, and obtain its exaggerated form. However, directly deforming the Gaussians yields poor results, necessitating the synthesis of pseudo-ground-truth caricature images by warping each frame to its exaggerated 2D representation using local affine transformations. We then devise a training scheme that alternates real and synthesized supervision, enabling a single Gaussian collection to represent both natural and exaggerated avatars. This scheme improves fidelity, supports local edits, and allows continuous control over the intensity of the caricature. In order to achieve real-time deformations, an efficient interpolation between the original and exaggerated surfaces is introduced. We further analyze and show that it has a bounded deviation from closed-form solutions. In both quantitative and qualitative evaluations, our results outperform prior work, delivering photorealistic, geometry-controlled caricature avatars.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.03319</guid>
|
||
<pubDate>Tue, 06 Jan 2026 13:56:28 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models</title>
|
||
<link>https://arxiv.org/abs/2601.06165</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06165.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dasol Choi, Guijin Son, Hanwool Lee, Minhyuk Kim, Hyunwoo Ko, Teabin Lim, Ahn Eungyeol, Jungwhan Kim, Seunghyeok Hong, Youngsook Song</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Current vision-language benchmarks predominantly feature well-structured questions with clear, explicit prompts. However, real user queries are often informal and underspecified. Users naturally leave much unsaid, relying on images to convey context. We introduce HAERAE-Vision, a benchmark of 653 real-world visual questions from Korean online communities (0.76% survival from 86K candidates), each paired with an explicit rewrite, yielding 1,306 query variants in total. Evaluating 39 VLMs, we find that even state-of-the-art models (GPT-5, Gemini 2.5 Pro) achieve under 50% on the original queries. Crucially, query explicitation alone yields 8 to 22 point improvements, with smaller models benefiting most. We further show that even with web search, under-specified queries underperform explicit queries without search, revealing that current retrieval cannot compensate for what users leave unsaid. Our findings demonstrate that a substantial portion of VLM difficulty stem from natural query under-specification instead of model capability, highlighting a critical gap between benchmark evaluation and real-world deployment.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06165</guid>
|
||
<pubDate>Wed, 07 Jan 2026 02:33:03 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection</title>
|
||
<link>https://arxiv.org/abs/2601.03928</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03928.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingyu Ouyang, Kevin Qinghong Lin, Mike Zheng Shou, Hwee Tou Ng</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Vision-Language Models (VLMs) have shown remarkable performance in User Interface (UI) grounding tasks, driven by their ability to process increasingly high-resolution screenshots. However, screenshots are tokenized into thousands of visual tokens (e.g., about 4700 for 2K resolution), incurring significant computational overhead and diluting attention. In contrast, humans typically focus on regions of interest when interacting with UI. In this work, we pioneer the task of efficient UI grounding. Guided by practical analysis of the task's characteristics and challenges, we propose FocusUI, an efficient UI grounding framework that selects patches most relevant to the instruction while preserving positional continuity for precise grounding. FocusUI addresses two key challenges: (1) Eliminating redundant tokens in visual encoding. We construct patch-level supervision by fusing an instruction-conditioned score with a rule-based UI-graph score that down-weights large homogeneous regions to select distinct and instruction-relevant visual tokens. (2) Preserving positional continuity during visual token selection. We find that general visual token pruning methods suffer from severe accuracy degradation on UI grounding tasks due to broken positional information. We introduce a novel PosPad strategy, which compresses each contiguous sequence of dropped visual tokens into a single special marker placed at the sequence's last index to preserve positional continuity. Comprehensive experiments on four grounding benchmarks demonstrate that FocusUI surpasses GUI-specific baselines. On the ScreenSpot-Pro benchmark, FocusUI-7B achieves a performance improvement of 3.7% over GUI-Actor-7B. Even with only 30% visual token retention, FocusUI-7B drops by only 3.2% while achieving up to 1.44x faster inference and 17% lower peak GPU memory.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.03928</guid>
|
||
<pubDate>Wed, 07 Jan 2026 13:48:12 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization</title>
|
||
<link>https://arxiv.org/abs/2601.04582</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04582.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mizanur Rahman, Mohammed Saidul Islam, Md Tahmid Rahman Laskar, Shafiq Joty, Enamul Hoque</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Text-to-Visualization (Text2Vis) systems translate natural language queries over tabular data into concise answers and executable visualizations. While closed-source LLMs generate functional code, the resulting charts often lack semantic alignment and clarity, qualities that can only be assessed post-execution. Open-source models struggle even more, frequently producing non-executable or visually poor outputs. Although supervised fine-tuning can improve code executability, it fails to enhance overall visualization quality, as traditional SFT loss cannot capture post-execution feedback. To address this gap, we propose RL-Text2Vis, the first reinforcement learning framework for Text2Vis generation. Built on Group Relative Policy Optimization (GRPO), our method uses a novel multi-objective reward that jointly optimizes textual accuracy, code validity, and visualization quality using post-execution feedback. By training Qwen2.5 models (7B and 14B), RL-Text2Vis achieves a 22% relative improvement in chart quality over GPT-4o on the Text2Vis benchmark and boosts code execution success from 78% to 97% relative to its zero-shot baseline. Our models significantly outperform strong zero-shot and supervised baselines and also demonstrate robust generalization to out-of-domain datasets like VIS-Eval and NVBench. These results establish GRPO as an effective strategy for structured, multimodal reasoning in visualization generation. We release our code at https://github.com/vis-nlp/RL-Text2Vis.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.04582</guid>
|
||
<pubDate>Thu, 08 Jan 2026 04:29:07 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning</title>
|
||
<link>https://arxiv.org/abs/2601.04698</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04698.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinuo Wang, Mining Tan, Wenxiang Jiao, Xiaoxi Li, Hao Wang, Xuanyu Zhang, Yuan Lu, Weiming Dong</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Travel planning is a sophisticated decision-making process that requires synthesizing multifaceted information to construct itineraries. However, existing travel planning approaches face several challenges: (1) Pruning candidate points of interest (POIs) while maintaining a high recall rate; (2) A single reasoning path restricts the exploration capability within the feasible solution space for travel planning; (3) Simultaneously optimizing hard constraints and soft constraints remains a significant difficulty. To address these challenges, we propose TourPlanner, a comprehensive framework featuring multi-path reasoning and constraint-gated reinforcement learning. Specifically, we first introduce a Personalized Recall and Spatial Optimization (PReSO) workflow to construct spatially-aware candidate POIs' set. Subsequently, we propose Competitive consensus Chain-of-Thought (CCoT), a multi-path reasoning paradigm that improves the ability of exploring the feasible solution space. To further refine the plan, we integrate a sigmoid-based gating mechanism into the reinforcement learning stage, which dynamically prioritizes soft-constraint satisfaction only after hard constraints are met. Experimental results on travel planning benchmarks demonstrate that TourPlanner achieves state-of-the-art performance, significantly surpassing existing methods in both feasibility and user-preference alignment.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.04698</guid>
|
||
<pubDate>Thu, 08 Jan 2026 08:08:35 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking</title>
|
||
<link>https://arxiv.org/abs/2601.04720</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04720.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingxin Li, Yanzhao Zhang, Dingkun Long, Keqin Chen, Sibo Song, Shuai Bai, Zhibo Yang, Pengjun Xie, An Yang, Dayiheng Liu, Jingren Zhou, Junyang Lin</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> In this report, we introduce the Qwen3-VL-Embedding and Qwen3-VL-Reranker model series, the latest extensions of the Qwen family built on the Qwen3-VL foundation model. Together, they provide an end-to-end pipeline for high-precision multimodal search by mapping diverse modalities, including text, images, document images, and video, into a unified representation space. The Qwen3-VL-Embedding model employs a multi-stage training paradigm, progressing from large-scale contrastive pre-training to reranking model distillation, to generate semantically rich high-dimensional vectors. It supports Matryoshka Representation Learning, enabling flexible embedding dimensions, and handles inputs up to 32k tokens. Complementing this, Qwen3-VL-Reranker performs fine-grained relevance estimation for query-document pairs using a cross-encoder architecture with cross-attention mechanisms. Both model series inherit the multilingual capabilities of Qwen3-VL, supporting more than 30 languages, and are released in 2B and 8B parameter sizes to accommodate diverse deployment requirements. Empirical evaluations demonstrate that the Qwen3-VL-Embedding series achieves state-of-the-art results across diverse multimodal embedding evaluation benchmarks. Specifically, Qwen3-VL-Embedding-8B attains an overall score of 77.8 on MMEB-V2, ranking first among all models (as of January 8, 2025). This report presents the architecture, training methodology, and practical capabilities of the series, demonstrating their effectiveness on various multimodal retrieval tasks, including image-text retrieval, visual question answering, and video-text matching.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.04720</guid>
|
||
<pubDate>Thu, 08 Jan 2026 08:36:06 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions</title>
|
||
<link>https://arxiv.org/abs/2601.04745</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04745.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tingyu Wu, Zhisheng Chen, Ziyan Weng, Shuhe Wang, Chenglong Li, Shuo Zhang, Sen Hu, Silin Wu, Qizhen Lan, Huacan Wang, Ronghao Chen</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> Existing long-horizon memory benchmarks mostly use multi-turn dialogues or synthetic user histories, which makes retrieval performance an imperfect proxy for person understanding. We present \BenchName, a publicly releasable benchmark built from long-form autobiographical narratives, where actions, context, and inner thoughts provide dense evidence for inferring stable motivations and decision principles. \BenchName~reconstructs each narrative into a flashback-aware, time-anchored stream and evaluates models with evidence-linked questions spanning factual recall, subjective state attribution, and principle-level reasoning. Across diverse narrative sources, retrieval-augmented systems mainly improve factual accuracy, while errors persist on temporally grounded explanations and higher-level inferences, highlighting the need for memory mechanisms beyond retrieval. Our data is in KnowMeBench{https://github.com/QuantaAlpha/KnowMeBench}.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.04745</guid>
|
||
<pubDate>Thu, 08 Jan 2026 09:11:33 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>AgentOCR: Reimagining Agent History via Optical Self-Compression</title>
|
||
<link>https://arxiv.org/abs/2601.04786</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lang Feng, Fuchao Yang, Feng Chen, Xin Cheng, Haiyang Xu, Zhenglin Wan, Ming Yan, Bo An</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction trajectories, but practical deployment is bottlenecked by rapidly growing textual histories that inflate token budgets and memory usage. We introduce AgentOCR, a framework that exploits the superior information density of visual tokens by representing the accumulated observation-action history as a compact rendered image. To make multi-turn rollouts scalable, AgentOCR proposes segment optical caching. By decomposing history into hashable segments and maintaining a visual cache, this mechanism eliminates redundant re-rendering. Beyond fixed rendering, AgentOCR introduces agentic self-compression, where the agent actively emits a compression rate and is trained with compression-aware reward to adaptively balance task success and token efficiency. We conduct extensive experiments on challenging agentic benchmarks, ALFWorld and search-based QA. Remarkably, results demonstrate that AgentOCR preserves over 95\% of text-based agent performance while substantially reducing token consumption (>50\%), yielding consistent token and memory efficiency. Our further analysis validates a 20x rendering speedup from segment optical caching and the effective strategic balancing of self-compression.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.04786</guid>
|
||
<pubDate>Thu, 08 Jan 2026 10:10:20 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SmartSearch: Process Reward-Guided Query Refinement for Search Agents</title>
|
||
<link>https://arxiv.org/abs/2601.04888</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04888.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tongyu Wen, Guanting Dong, Zhicheng Dou</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of search agents, yet the quality of intermediate search queries during reasoning remains overlooked. As a result, the generated queries often remain inaccurate, leading to unexpected retrieval results and ultimately limiting search agents' overall effectiveness. To mitigate this issue, we introduce SmartSearch, a framework built upon two key mechanisms: (1) Process rewards, which provide fine-grained supervision for the quality of each intermediate search query through Dual-Level Credit Assessment. (2) Query refinement, which promotes the optimization of query generation by selectively refining low-quality search queries and regenerating subsequent search rounds based on these refinements. To enable the search agent to progressively internalize the ability to improve query quality under the guidance of process rewards, we design a three-stage curriculum learning framework. This framework guides the agent through a progression from imitation, to alignment, and ultimately to generalization. Experimental results show that SmartSearch consistently surpasses existing baselines, and additional quantitative analyses further confirm its significant gains in both search efficiency and query quality. The code is available at https://github.com/MYVAE/SmartSearch.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.04888</guid>
|
||
<pubDate>Thu, 08 Jan 2026 12:39:05 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction</title>
|
||
<link>https://arxiv.org/abs/2601.05107</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05107.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Muzhao Tian, Zisu Huang, Xiaohua Wang, Jingwen Xu, Zhengkang Guo, Qi Qian, Yuanzhe Shen, Kaitao Song, Jiakang Yuan, Changze Lv, Xiaoqing Zheng</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to memory usage: incorporating all relevant past information can lead to Memory Anchoring, where the agent is trapped by past interactions, while excluding memory entirely results in under-utilization and the loss of important interaction history. We show that an agent's reliance on memory can be modeled as an explicit and user-controllable dimension. We first introduce a behavioral metric of memory dependence to quantify the influence of past interactions on current outputs. We then propose Steerable Memory Agent, SteeM, a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history. Experiments across different scenarios demonstrate that our approach consistently outperforms conventional prompting and rigid memory masking strategies, yielding a more nuanced and effective control for personalized human-agent collaboration.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05107</guid>
|
||
<pubDate>Thu, 08 Jan 2026 16:54:30 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts</title>
|
||
<link>https://arxiv.org/abs/2601.05110</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05110.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenhao Zeng, Xuteng Zhang, Yuling Shi, Chao Hu, Yuting Chen, Beijun Shen, Xiaodong Gu</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Large Reasoning Models (LRMs) achieve remarkable performance by explicitly generating multi-step chains of thought, but this capability incurs substantial inference latency and computational cost. Collaborative inference offers a promising solution by selectively allocating work between lightweight and large models, yet a fundamental challenge remains: determining when a reasoning step requires the capacity of a large model or the efficiency of a small model. Existing routing strategies either rely on local token probabilities or post-hoc verification, introducing significant inference overhead. In this work, we propose a novel perspective on step-wise collaboration: the difficulty of a reasoning step can be inferred from its very first token. Inspired by the "Aha Moment" phenomenon in LRMs, we show that the entropy of the initial token serves as a strong predictor of step difficulty. Building on this insight, we introduce GlimpRouter, a training-free step-wise collaboration framework. GlimpRouter employs a lightweight model to generate only the first token of each reasoning step and routes the step to a larger model only when the initial token entropy exceeds a threshold. Experiments on multiple benchmarks demonstrate that our approach significantly reduces inference latency while preserving accuracy. For instance, GlimpRouter attains a substantial 10.7% improvement in accuracy while reducing inference latency by 25.9% compared to a standalone large model on AIME25. These results suggest a simple yet effective mechanism for reasoning: allocating computation based on a glimpse of thought rather than full-step evaluation.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05110</guid>
|
||
<pubDate>Thu, 08 Jan 2026 16:58:07 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection</title>
|
||
<link>https://arxiv.org/abs/2601.05403</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05403.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiwei Liu, Yupen Cao, Yuechen Jiang, Mohsinul Kabir, Polydoros Giannouris, Chen Xu, Ziyang Xu, Tianlei Zhu, Tariquzzaman Faisal, Triantafillos Papadopoulos, Yan Wang, Lingfei Qian, Xueqing Peng, Zhuohan Xie, Ye Yuan, Saeed Almheiri, Abdulrazzaq Alnajjar, Mingbin Chen, Harry Stuart, Paul Thompson, Prayag Tiwari, Alejandro Lopez-Lira, Xue Liu, Jimin Huang, Sophia Ananiadou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large language models (LLMs) have been widely applied across various domains of finance. Since their training data are largely derived from human-authored corpora, LLMs may inherit a range of human biases. Behavioral biases can lead to instability and uncertainty in decision-making, particularly when processing financial information. However, existing research on LLM bias has mainly focused on direct questioning or simplified, general-purpose settings, with limited consideration of the complex real-world financial environments and high-risk, context-sensitive, multilingual financial misinformation detection tasks (\mfmd). In this work, we propose \mfmdscen, a comprehensive benchmark for evaluating behavioral biases of LLMs in \mfmd across diverse economic scenarios. In collaboration with financial experts, we construct three types of complex financial scenarios: (i) role- and personality-based, (ii) role- and region-based, and (iii) role-based scenarios incorporating ethnicity and religious beliefs. We further develop a multilingual financial misinformation dataset covering English, Chinese, Greek, and Bengali. By integrating these scenarios with misinformation claims, \mfmdscen enables a systematic evaluation of 22 mainstream LLMs. Our findings reveal that pronounced behavioral biases persist across both commercial and open-source models. This project will be available at https://github.com/lzw108/FMD.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05403</guid>
|
||
<pubDate>Thu, 08 Jan 2026 22:00:32 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization</title>
|
||
<link>https://arxiv.org/abs/2601.05432</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05432.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Ji, Yong Wang, Ziyu Ma, Yiming Hu, Hailang Huang, Xuecai Hu, Guanhua Chen, Liaoni Wu, Xiangxiang Chu</p><p><b>Upvotes:</b> 159</p><p><b>Summary:</b> The image geolocalization task aims to predict the location where an image was taken anywhere on Earth using visual clues. Existing large vision-language model (LVLM) approaches leverage world knowledge, chain-of-thought reasoning, and agentic capabilities, but overlook a common strategy used by humans -- using maps. In this work, we first equip the model Thinking with Map ability and formulate it as an agent-in-the-map loop. We develop a two-stage optimization scheme for it, including agentic reinforcement learning (RL) followed by parallel test-time scaling (TTS). The RL strengthens the agentic capability of model to improve sampling efficiency, and the parallel TTS enables the model to explore multiple candidate paths before making the final prediction, which is crucial for geolocalization. To evaluate our method on up-to-date and in-the-wild images, we further present MAPBench, a comprehensive geolocalization training and evaluation benchmark composed entirely of real-world images. Experimental results show that our method outperforms existing open- and closed-source models on most metrics, specifically improving Acc@500m from 8.0\% to 22.1\% compared to Gemini-3-Pro with Google Search/Map grounded mode.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05432</guid>
|
||
<pubDate>Thu, 08 Jan 2026 23:47:30 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Orient Anything V2: Unifying Orientation and Rotation Understanding</title>
|
||
<link>https://arxiv.org/abs/2601.05573</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05573.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zehan Wang, Ziang Zhang, Jiayang Xu, Jialei Wang, Tianyu Pang, Chao Du, HengShuang Zhao, Zhou Zhao</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> This work presents Orient Anything V2, an enhanced foundation model for unified understanding of object 3D orientation and rotation from single or paired images. Building upon Orient Anything V1, which defines orientation via a single unique front face, V2 extends this capability to handle objects with diverse rotational symmetries and directly estimate relative rotations. These improvements are enabled by four key innovations: 1) Scalable 3D assets synthesized by generative models, ensuring broad category coverage and balanced data distribution; 2) An efficient, model-in-the-loop annotation system that robustly identifies 0 to N valid front faces for each object; 3) A symmetry-aware, periodic distribution fitting objective that captures all plausible front-facing orientations, effectively modeling object rotational symmetry; 4) A multi-frame architecture that directly predicts relative object rotations. Extensive experiments show that Orient Anything V2 achieves state-of-the-art zero-shot performance on orientation estimation, 6DoF pose estimation, and object symmetry recognition across 11 widely used benchmarks. The model demonstrates strong generalization, significantly broadening the applicability of orientation estimation in diverse downstream tasks.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05573</guid>
|
||
<pubDate>Fri, 09 Jan 2026 06:43:59 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.05593</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05593.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Daxin Jiang, Xiangyu Zhang, Heung-Yeung Shum</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> We introduce Parallel Coordinated Reasoning (PaCoRe), a training-and-inference framework designed to overcome a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window. PaCoRe departs from the traditional sequential paradigm by driving TTC through massive parallel exploration coordinated via a message-passing architecture in multiple rounds. Each round launches many parallel reasoning trajectories, compacts their findings into context-bounded messages, and synthesizes these messages to guide the next round and ultimately produce the final answer. Trained end-to-end with large-scale, outcome-based reinforcement learning, the model masters the synthesis abilities required by PaCoRe and scales to multi-million-token effective TTC without exceeding context limits. The approach yields strong improvements across diverse domains, and notably pushes reasoning beyond frontier systems in mathematics: an 8B model reaches 94.5% on HMMT 2025, surpassing GPT-5's 93.2% by scaling effective TTC to roughly two million tokens. We open-source model checkpoints, training data, and the full inference pipeline to accelerate follow-up work.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05593</guid>
|
||
<pubDate>Fri, 09 Jan 2026 07:24:43 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis</title>
|
||
<link>https://arxiv.org/abs/2601.05808</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05808.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoshuai Song, Haofei Chang, Guanting Dong, Yutao Zhu, Zhicheng Dou, Ji-Rong Wen</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Large language models (LLMs) are expected to be trained to act as agents in various real-world environments, but this process relies on rich and varied tool-interaction sandboxes. However, access to real systems is often restricted; LLM-simulated environments are prone to hallucinations and inconsistencies; and manually built sandboxes are hard to scale. In this paper, we propose EnvScaler, an automated framework for scalable tool-interaction environments via programmatic synthesis. EnvScaler comprises two components. First, SkelBuilder constructs diverse environment skeletons through topic mining, logic modeling, and quality evaluation. Then, ScenGenerator generates multiple task scenarios and rule-based trajectory validation functions for each environment. With EnvScaler, we synthesize 191 environments and about 7K scenarios, and apply them to Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) for Qwen3 series models. Results on three benchmarks show that EnvScaler significantly improves LLMs' ability to solve tasks in complex environments involving multi-turn, multi-tool interactions. We release our code and data at https://github.com/RUC-NLPIR/EnvScaler.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05808</guid>
|
||
<pubDate>Fri, 09 Jan 2026 14:32:06 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Boosting Latent Diffusion Models via Disentangled Representation Alignment</title>
|
||
<link>https://arxiv.org/abs/2601.05823</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05823.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> John Page, Xuesong Niu, Kai Wu, Kun Gai</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Latent Diffusion Models (LDMs) generate high-quality images by operating in a compressed latent space, typically obtained through image tokenizers such as Variational Autoencoders (VAEs). In pursuit of a generation-friendly VAE, recent studies have explored leveraging Vision Foundation Models (VFMs) as representation alignment targets for VAEs, mirroring the approach commonly adopted for LDMs. Although this yields certain performance gains, using the same alignment target for both VAEs and LDMs overlooks their fundamentally different representational requirements. We advocate that while LDMs benefit from latents retaining high-level semantic concepts, VAEs should excel in semantic disentanglement, enabling encoding of attribute-level information in a structured way. To address this, we propose the Semantic disentangled VAE (Send-VAE), explicitly optimized for disentangled representation learning through aligning its latent space with the semantic hierarchy of pre-trained VFMs. Our approach employs a non-linear mapper network to transform VAE latents, aligning them with VFMs to bridge the gap between attribute-level disentanglement and high-level semantics, facilitating effective guidance for VAE learning. We evaluate semantic disentanglement via linear probing on attribute prediction tasks, showing strong correlation with improved generation performance. Finally, using Send-VAE, we train flow-based transformers SiTs; experiments show Send-VAE significantly speeds up training and achieves a state-of-the-art FID of 1.21 and 1.75 with and without classifier-free guidance on ImageNet 256x256.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05823</guid>
|
||
<pubDate>Fri, 09 Jan 2026 14:54:30 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals</title>
|
||
<link>https://arxiv.org/abs/2601.05848</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nate Gillman, Yinghua Zhou, Zitian Tang, Evan Luo, Arjan Chakravarthy, Daksh Aggarwal, Michael Freeman, Charles Herrmann, Chen Sun</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text instructions are often too abstract to capture physical nuances, while target images are frequently infeasible to specify for dynamic tasks. To address this, we introduce Goal Force, a novel framework that allows users to define goals via explicit force vectors and intermediate dynamics, mirroring how humans conceptualize physical tasks. We train a video generation model on a curated dataset of synthetic causal primitives-such as elastic collisions and falling dominos-teaching it to propagate forces through time and space. Despite being trained on simple physics data, our model exhibits remarkable zero-shot generalization to complex, real-world scenarios, including tool manipulation and multi-object causal chains. Our results suggest that by grounding video generation in fundamental physical interactions, models can emerge as implicit neural physics simulators, enabling precise, physics-aware planning without reliance on external engines. We release all datasets, code, model weights, and interactive video demos at our project page.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05848</guid>
|
||
<pubDate>Fri, 09 Jan 2026 15:23:36 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift</title>
|
||
<link>https://arxiv.org/abs/2601.05882</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05882.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Preference tuning aligns pretrained language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Prior work has shown that preference-tuning degrades performance and reduces helpfulness when evaluated outside the training domain. However, the extent to which adaptation strategies mitigate this domain shift remains unexplored. We address this challenge by conducting a comprehensive and systematic study of alignment generalization under domain shift. We compare five popular alignment objectives and various adaptation strategies from source to target, including target-domain supervised fine-tuning and pseudo-labeling, across summarization and question-answering helpfulness tasks. Our findings reveal systematic differences in generalization across alignment objectives under domain shift. We show that adaptation strategies based on pseudo-labeling can substantially reduce domain-shift degradation</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05882</guid>
|
||
<pubDate>Fri, 09 Jan 2026 15:56:55 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency</title>
|
||
<link>https://arxiv.org/abs/2601.05905</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05905.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoming Xu, Ningyuan Zhao, Yunzhi Yao, Weihong Xu, Hongru Wang, Xinle Deng, Shumin Deng, Jeff Z. Pan, Huajun Chen, Ningyu Zhang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual perturbations. Existing evaluations largely rely on point-wise confidence like Self-Consistency, which can mask brittle belief. We show that even facts answered with perfect self-consistency can rapidly collapse under mild contextual interference. To address this gap, we propose Neighbor-Consistency Belief (NCB), a structural measure of belief robustness that evaluates response coherence across a conceptual neighborhood. To validate the efficiency of NCB, we introduce a new cognitive stress-testing protocol that probes outputs stability under contextual interference. Experiments across multiple LLMs show that the performance of high-NCB data is relatively more resistant to interference. Finally, we present Structure-Aware Training (SAT), which optimizes context-invariant belief structure and reduces long-tail knowledge brittleness by approximately 30%. Code will be available at https://github.com/zjunlp/belief.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05905</guid>
|
||
<pubDate>Fri, 09 Jan 2026 16:23:21 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Can We Predict Before Executing Machine Learning Agents?</title>
|
||
<link>https://arxiv.org/abs/2601.05930</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05930.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingsheng Zheng, Jintian Zhang, Yujie Luo, Yuren Mao, Yunjun Gao, Lun Du, Huajun Chen, Ningyu Zhang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrained by a Generate-Execute-Feedback paradigm. Previous approaches suffer from a severe Execution Bottleneck, as hypothesis evaluation relies strictly on expensive physical execution. To bypass these physical constraints, we internalize execution priors to substitute costly runtime checks with instantaneous predictive reasoning, drawing inspiration from World Models. In this work, we formalize the task of Data-centric Solution Preference and construct a comprehensive corpus of 18,438 pairwise comparisons. We demonstrate that LLMs exhibit significant predictive capabilities when primed with a Verified Data Analysis Report, achieving 61.5% accuracy and robust confidence calibration. Finally, we instantiate this framework in FOREAGENT, an agent that employs a Predict-then-Verify loop, achieving a 6x acceleration in convergence while surpassing execution-based baselines by +6%. Our code and dataset will be publicly available soon at https://github.com/zjunlp/predict-before-execute.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05930</guid>
|
||
<pubDate>Fri, 09 Jan 2026 16:44:17 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction</title>
|
||
<link>https://arxiv.org/abs/2601.05966</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05966.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Longbin Ji, Xiaoxiong Liu, Junyuan Shang, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first large-scale Visual Autoregressive (VAR) framework for video generation that combines multi-scale next-frame prediction with autoregressive modeling. VideoAR disentangles spatial and temporal dependencies by integrating intra-frame VAR modeling with causal next-frame prediction, supported by a 3D multi-scale tokenizer that efficiently encodes spatio-temporal dynamics. To improve long-term consistency, we propose Multi-scale Temporal RoPE, Cross-Frame Error Correction, and Random Frame Mask, which collectively mitigate error propagation and stabilize temporal coherence. Our multi-stage pretraining pipeline progressively aligns spatial and temporal learning across increasing resolutions and durations. Empirically, VideoAR achieves new state-of-the-art results among autoregressive models, improving FVD on UCF-101 from 99.5 to 88.6 while reducing inference steps by over 10x, and reaching a VBench score of 81.74-competitive with diffusion-based models an order of magnitude larger. These results demonstrate that VideoAR narrows the performance gap between autoregressive and diffusion paradigms, offering a scalable, efficient, and temporally consistent foundation for future video generation research.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.05966</guid>
|
||
<pubDate>Fri, 09 Jan 2026 17:34:59 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.06002</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06002.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiguang Chen, Yantao Du, Ziniu Li, Jinhao Liu, Songyao Duan, Jiarui Guo, Minghao Liu, Jiaheng Liu, Tong Yang, Ge Zhang, Libo Qin, Wanxiang Che, Wenhao Huang</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Large language models (LLMs) often fail to learn effective long chain-of-thought (Long CoT) reasoning from human or non-Long-CoT LLMs imitation. To understand this, we propose that effective and learnable Long CoT trajectories feature stable molecular-like structures in unified view, which are formed by three interaction types: Deep-Reasoning (covalent-like), Self-Reflection (hydrogen-bond-like), and Self-Exploration (van der Waals-like). Analysis of distilled trajectories reveals these structures emerge from Long CoT fine-tuning, not keyword imitation. We introduce Effective Semantic Isomers and show that only bonds promoting fast entropy convergence support stable Long CoT learning, while structural competition impairs training. Drawing on these findings, we present Mole-Syn, a distribution-transfer-graph method that guides synthesis of effective Long CoT structures, boosting performance and RL stability across benchmarks.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06002</guid>
|
||
<pubDate>Fri, 09 Jan 2026 18:39:01 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards</title>
|
||
<link>https://arxiv.org/abs/2601.06021</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06021.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiajie Zhang, Xin Lv, Ling Feng, Lei Hou, Juanzi Li</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Reinforcement learning (RL) has emerged as a critical technique for enhancing LLM-based deep search agents. However, existing approaches primarily rely on binary outcome rewards, which fail to capture the comprehensiveness and factuality of agents' reasoning process, and often lead to undesirable behaviors such as shortcut exploitation and hallucinations. To address these limitations, we propose Citation-aware Rubric Rewards (CaRR), a fine-grained reward framework for deep search agents that emphasizes reasoning comprehensiveness, factual grounding, and evidence connectivity. CaRR decomposes complex questions into verifiable single-hop rubrics and requires agents to satisfy these rubrics by explicitly identifying hidden entities, supporting them with correct citations, and constructing complete evidence chains that link to the predicted answer. We further introduce Citation-aware Group Relative Policy Optimization (C-GRPO), which combines CaRR and outcome rewards for training robust deep search agents. Experiments show that C-GRPO consistently outperforms standard outcome-based RL baselines across multiple deep search benchmarks. Our analysis also validates that C-GRPO effectively discourages shortcut exploitation, promotes comprehensive, evidence-grounded reasoning, and exhibits strong generalization to open-ended deep research tasks. Our code and data are available at https://github.com/THUDM/CaRR.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06021</guid>
|
||
<pubDate>Fri, 09 Jan 2026 18:57:53 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>RigMo: Unifying Rig and Motion Learning for Generative Animation</title>
|
||
<link>https://arxiv.org/abs/2601.06378</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06378.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Zhang, Jiahao Luo, Bohui Wan, Yizhou Zhao, Zongrui Li, Michael Vasilkovsky, Chaoyang Wang, Jian Wang, Narendra Ahuja, Bing Zhou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Despite significant progress in 4D generation, rig and motion, the core structural and dynamic components of animation are typically modeled as separate problems. Existing pipelines rely on ground-truth skeletons and skinning weights for motion generation and treat auto-rigging as an independent process, undermining scalability and interpretability. We present RigMo, a unified generative framework that jointly learns rig and motion directly from raw mesh sequences, without any human-provided rig annotations. RigMo encodes per-vertex deformations into two compact latent spaces: a rig latent that decodes into explicit Gaussian bones and skinning weights, and a motion latent that produces time-varying SE(3) transformations. Together, these outputs define an animatable mesh with explicit structure and coherent motion, enabling feed-forward rig and motion inference for deformable objects. Beyond unified rig-motion discovery, we introduce a Motion-DiT model operating in RigMo's latent space and demonstrate that these structure-aware latents can naturally support downstream motion generation tasks. Experiments on DeformingThings4D, Objaverse-XL, and TrueBones demonstrate that RigMo learns smooth, interpretable, and physically plausible rigs, while achieving superior reconstruction and category-level generalization compared to existing auto-rigging and deformation baselines. RigMo establishes a new paradigm for unified, structure-aware, and scalable dynamic 3D modeling.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06378</guid>
|
||
<pubDate>Sat, 10 Jan 2026 01:26:28 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>BizFinBench.v2: A Unified Dual-Mode Bilingual Benchmark for Expert-Level Financial Capability Alignment</title>
|
||
<link>https://arxiv.org/abs/2601.06401</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06401.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Guo, Rongjunchen Zhang, Guilong Lu, Xuntao Guo, Shuai Jia, Zhi Yang, Liwen Zhang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large language models have undergone rapid evolution, emerging as a pivotal technology for intelligence in financial operations. However, existing benchmarks are often constrained by pitfalls such as reliance on simulated or general-purpose samples and a focus on singular, offline static scenarios. Consequently, they fail to align with the requirements for authenticity and real-time responsiveness in financial services, leading to a significant discrepancy between benchmark performance and actual operational efficacy. To address this, we introduce BizFinBench.v2, the first large-scale evaluation benchmark grounded in authentic business data from both Chinese and U.S. equity markets, integrating online assessment. We performed clustering analysis on authentic user queries from financial platforms, resulting in eight fundamental tasks and two online tasks across four core business scenarios, totaling 29,578 expert-level Q&A pairs. Experimental results demonstrate that ChatGPT-5 achieves a prominent 61.5% accuracy in main tasks, though a substantial gap relative to financial experts persists; in online tasks, DeepSeek-R1 outperforms all other commercial LLMs. Error analysis further identifies the specific capability deficiencies of existing models within practical financial business contexts. BizFinBench.v2 transcends the limitations of current benchmarks, achieving a business-level deconstruction of LLM financial capabilities and providing a precise basis for evaluating efficacy in the widespread deployment of LLMs within the financial domain. The data and code are available at https://github.com/HiThink-Research/BizFinBench.v2.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06401</guid>
|
||
<pubDate>Sat, 10 Jan 2026 02:51:53 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>LSRIF: Logic-Structured Reinforcement Learning for Instruction Following</title>
|
||
<link>https://arxiv.org/abs/2601.06431</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06431.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyu Ren, Qianyu He, Jingwen Chang, Jie Zeng, Jiaqing Liang, Yanghua Xiao, Han Xia, Zeye Sun, Fei Yu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Instruction-following is critical for large language models, but real-world instructions often contain logical structures such as sequential dependencies and conditional branching. Existing methods typically construct datasets with parallel constraints and optimize average rewards, ignoring logical dependencies and yielding noisy signals. We propose a logic-structured training framework LSRIF that explicitly models instruction logic. We first construct a dataset LSRInstruct with constraint structures such as parallel, sequential, and conditional types, and then design structure-aware rewarding method LSRIF including average aggregation for parallel structures, failure-penalty propagation for sequential structures, and selective rewards for conditional branches. Experiments show LSRIF brings significant improvements in instruction-following (in-domain and out-of-domain) and general reasoning. Analysis reveals that learning with explicit logic structures brings parameter updates in attention layers and sharpens token-level attention to constraints and logical operators.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06431</guid>
|
||
<pubDate>Sat, 10 Jan 2026 05:11:38 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking</title>
|
||
<link>https://arxiv.org/abs/2601.06487</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06487.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiang Zhang, Boli Chen, Fanrui Zhang, Ruixue Ding, Shihang Wang, Qiuchen Wang, Yinfeng Huang, Haonan Zhang, Rongxiang Zhu, Pengyong Wang, Ailin Ren, Xin Li, Pengjun Xie, Jiawei Liu, Ning Guo, Jingren Zhou, Zheng-Jun Zha</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.g., complex travel planning). Due to the absence of objective ground-truth for these tasks, current RL algorithms largely rely on reward models that assign scalar scores to individual responses. We contend that such pointwise scoring suffers from an inherent discrimination collapse: the reward model struggles to distinguish subtle advantages among different trajectories, resulting in scores within a group being compressed into a narrow range. Consequently, the effective reward signal becomes dominated by noise from the reward model, leading to optimization stagnation. To address this, we propose ArenaRL, a reinforcement learning paradigm that shifts from pointwise scalar scoring to intra-group relative ranking. ArenaRL introduces a process-aware pairwise evaluation mechanism, employing multi-level rubrics to assign fine-grained relative scores to trajectories. Additionally, we construct an intra-group adversarial arena and devise a tournament-based ranking scheme to obtain stable advantage signals. Empirical results confirm that the built seeded single-elimination scheme achieves nearly equivalent advantage estimation accuracy to full pairwise comparisons with O(N^2) complexity, while operating with only O(N) complexity, striking an optimal balance between efficiency and precision. Furthermore, to address the lack of full-cycle benchmarks for open-ended agents, we build Open-Travel and Open-DeepResearch, two high-quality benchmarks featuring a comprehensive pipeline covering SFT, RL training, and multi-dimensional evaluation. Extensive experiments show that ArenaRL substantially outperforms standard RL baselines, enabling LLM agents to generate more robust solutions for complex real-world tasks.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06487</guid>
|
||
<pubDate>Sat, 10 Jan 2026 08:43:07 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>BabyVision: Visual Reasoning Beyond Language</title>
|
||
<link>https://arxiv.org/abs/2601.06521</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06521.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liang Chen, Weichu Xie, Yiyan Liang, Hongfeng He, Hans Zhao, Zhibo Yang, Zhiqi Huang, Haoning Wu, Haoyu Lu, Y. charles, Yiping Bao, Yuantao Fan, Guopeng Li, Haiyang Shen, Xuanzhong Chen, Wendong Xu, Shuzheng Si, Zefan Cai, Wenhao Chai, Ziqi Huang, Fangfu Liu, Tianyu Liu, Baobao Chang, Xiaobo Hu, Kaiyuan Chen, Yixin Ren, Yang Liu, Yuan Gong, Kuan Li</p><p><b>Upvotes:</b> 182</p><p><b>Summary:</b> While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06521</guid>
|
||
<pubDate>Sat, 10 Jan 2026 10:42:44 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity</title>
|
||
<link>https://arxiv.org/abs/2601.06596</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06596.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongjun An, Yiliang Song, Jiangan Chen, Jiawei Shao, Chi Zhang, Xuelong Li</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Large Language Model (LLM) training often optimizes for preference alignment, rewarding outputs that are perceived as helpful and interaction-friendly. However, this preference-oriented objective can be exploited: manipulative prompts can steer responses toward user-appeasing agreement and away from truth-oriented correction. In this work, we investigate whether aligned models are vulnerable to Preference-Undermining Attacks (PUA), a class of manipulative prompting strategies designed to exploit the model's desire to please user preferences at the expense of truthfulness. We propose a diagnostic methodology that provides a finer-grained and more directive analysis than aggregate benchmark scores, using a factorial evaluation framework to decompose prompt-induced shifts into interpretable effects of system objectives (truth- vs. preference-oriented) and PUA-style dialogue factors (directive control, personal derogation, conditional approval, reality denial) within a controlled 2 times 2^4 design. Surprisingly, more advanced models are sometimes more susceptible to manipulative prompts. Beyond the dominant reality-denial factor, we observe model-specific sign reversals and interactions with PUA-style factors, suggesting tailored defenses rather than uniform robustness. These findings offer a novel, reproducible factorial evaluation methodology that provides finer-grained diagnostics for post-training processes like RLHF, enabling better trade-offs in the product iteration of LLMs by offering a more nuanced understanding of preference alignment risks and the impact of manipulative prompts.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06596</guid>
|
||
<pubDate>Sat, 10 Jan 2026 15:16:23 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs</title>
|
||
<link>https://arxiv.org/abs/2601.06786</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jewon Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park, Taesup Kim</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Improving the reasoning abilities of large language models (LLMs) has largely relied on iterative self-training with model-generated data. While effective at boosting accuracy, existing approaches primarily reinforce successful reasoning paths, incurring a substantial calibration cost: models become overconfident and lose the ability to represent uncertainty. This failure has been characterized as a form of model collapse in alignment, where predictive distributions degenerate toward low-variance point estimates. We address this issue by reframing reasoning training as an epistemic learning problem, in which models must learn not only how to reason, but also when their reasoning should be trusted. We propose epistemically-calibrated reasoning (EpiCaR) as a training objective that jointly optimizes reasoning performance and calibration, and instantiate it within an iterative supervised fine-tuning framework using explicit self-evaluation signals. Experiments on Llama-3 and Qwen-3 families demonstrate that our approach achieves Pareto-superiority over standard baselines in both accuracy and calibration, particularly in models with sufficient reasoning capacity (e.g., 3B+). This framework generalizes effectively to OOD mathematical reasoning (GSM8K) and code generation (MBPP). Ultimately, our approach enables a 3X reduction in inference compute, matching the K=30 performance of STaR with only K=10 samples in capable models.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06786</guid>
|
||
<pubDate>Sun, 11 Jan 2026 06:21:13 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences</title>
|
||
<link>https://arxiv.org/abs/2601.06789</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06789.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qihao Wang, Ziming Cheng, Shuo Zhang, Fan Liu, Rui Xu, Heng Lian, Kunyi Wang, Xiaoming Yu, Jianghao Yin, Sen Hu, Yue Hu, Shaolei Zhang, Yanbing Liu, Ronghao Chen, Huacan Wang</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> While autonomous software engineering (SWE) agents are reshaping programming paradigms, they currently suffer from a "closed-world" limitation: they attempt to fix bugs from scratch or solely using local context, ignoring the immense historical human experience available on platforms like GitHub. Accessing this open-world experience is hindered by the unstructured and fragmented nature of real-world issue-tracking data. In this paper, we introduce MemGovern, a framework designed to govern and transform raw GitHub data into actionable experiential memory for agents. MemGovern employs experience governance to convert human experience into agent-friendly experience cards and introduces an agentic experience search strategy that enables logic-driven retrieval of human expertise. By producing 135K governed experience cards, MemGovern achieves a significant performance boost, improving resolution rates on the SWE-bench Verified by 4.65%. As a plug-in approach, MemGovern provides a solution for agent-friendly memory infrastructure.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06789</guid>
|
||
<pubDate>Sun, 11 Jan 2026 06:41:26 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Forest Before Trees: Latent Superposition for Efficient Visual Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.06803</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yubo Wang, Juntian Zhang, Yichen Wu, Yankai Lin, Nils Lukas, Yuhan Liu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandwidth bottleneck, where continuous visual details are discarded during discrete tokenization. Recent latent reasoning methods attempt to address this challenge, but often fall prey to premature semantic collapse due to rigid autoregressive objectives. In this paper, we propose Laser, a novel paradigm that reformulates visual deduction via Dynamic Windowed Alignment Learning (DWAL). Instead of forcing a point-wise prediction, Laser aligns the latent state with a dynamic validity window of future semantics. This mechanism enforces a "Forest-before-Trees" cognitive hierarchy, enabling the model to maintain a probabilistic superposition of global features before narrowing down to local details. Crucially, Laser maintains interpretability via decodable trajectories while stabilizing unconstrained learning via Self-Refined Superposition. Extensive experiments on 6 benchmarks demonstrate that Laser achieves state-of-the-art performance among latent reasoning methods, surpassing the strong baseline Monet by 5.03% on average. Notably, it achieves these gains with extreme efficiency, reducing inference tokens by more than 97%, while demonstrating robust generalization to out-of-distribution domains.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06803</guid>
|
||
<pubDate>Sun, 11 Jan 2026 08:30:49 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration</title>
|
||
<link>https://arxiv.org/abs/2601.06860</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06860.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifei Chen, Guanting Dong, Zhicheng Dou</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Large Language Models (LLMs) can extend their parameter knowledge limits by adopting the Tool-Integrated Reasoning (TIR) paradigm. However, existing LLM-based agent training framework often focuses on answers' accuracy, overlooking specific alignment for behavior patterns. Consequently, agent often exhibits ineffective actions during TIR tasks, such as redundant and insufficient tool calls. How to calibrate erroneous behavioral patterns when executing TIR tasks, thereby exploring effective trajectories, remains an open-ended problem. In this paper, we propose ET-Agent, a training framework for calibrating agent's tool-use behavior through two synergistic perspectives: Self-evolving Data Flywheel and Behavior Calibration Training. Specifically, we introduce a self-evolutionary data flywheel to generate enhanced data, used to fine-tune LLM to improve its exploration ability. Based on this, we implement an two-phases behavior-calibration training framework. It is designed to progressively calibrate erroneous behavioral patterns to optimal behaviors. Further in-depth experiments confirm the superiority of across multiple dimensions, including correctness, efficiency, reasoning conciseness, and tool execution accuracy. Our ET-Agent framework provides practical insights for research in the TIR field. Codes can be found in https://github.com/asilverlight/ET-Agent</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06860</guid>
|
||
<pubDate>Sun, 11 Jan 2026 11:05:26 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.06943</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengwen Liu, Xiaomin Yu, Zhuoyue Chang, Zhe Huang, Shuo Zhang, Heng Lian, Kunyi Wang, Rui Xu, Sen Hu, Jianheng Hou, Hao Peng, Chengwei Qin, Xiaobin Hu, Hong Peng, Ronghao Chen, Huacan Wang</p><p><b>Upvotes:</b> 202</p><p><b>Summary:</b> In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative retrieval, and multi-hop reasoning-based verification. To bridge this gap, we construct the first video deep research benchmark, VideoDR. VideoDR centers on video-conditioned open-domain video question answering, requiring cross-frame visual anchor extraction, interactive web retrieval, and multi-hop reasoning over joint video-web evidence; through rigorous human annotation and quality control, we obtain high-quality video deep research samples spanning six semantic domains. We evaluate multiple closed-source and open-source multimodal large language models under both the Workflow and Agentic paradigms, and the results show that Agentic is not consistently superior to Workflow: its gains depend on a model's ability to maintain the initial video anchors over long retrieval chains. Further analysis indicates that goal drift and long-horizon consistency are the core bottlenecks. In sum, VideoDR provides a systematic benchmark for studying video agents in open-web settings and reveals the key challenges for next-generation video deep research agents.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06943</guid>
|
||
<pubDate>Sun, 11 Jan 2026 15:07:37 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests</title>
|
||
<link>https://arxiv.org/abs/2601.06953</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06953.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Wu, Haoling Li, Xin Zhang, Jiani Guo, Jane Luo, Steven Liu, Yangyu Huang, Ruihang Chu, Scarlett Li, Yujiu Yang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Competitive programming presents great challenges for Code LLMs due to its intensive reasoning demands and high logical complexity. However, current Code LLMs still rely heavily on real-world data, which limits their scalability. In this paper, we explore a fully synthetic approach: training Code LLMs with entirely generated tasks, solutions, and test cases, to empower code reasoning models without relying on real-world data. To support this, we leverage feature-based synthesis to propose a novel data synthesis pipeline called SynthSmith. SynthSmith shows strong potential in producing diverse and challenging tasks, along with verified solutions and tests, supporting both supervised fine-tuning and reinforcement learning. Based on the proposed synthetic SFT and RL datasets, we introduce the X-Coder model series, which achieves a notable pass rate of 62.9 avg@8 on LiveCodeBench v5 and 55.8 on v6, outperforming DeepCoder-14B-Preview and AReal-boba2-14B despite having only 7B parameters. In-depth analysis reveals that scaling laws hold on our synthetic dataset, and we explore which dimensions are more effective to scale. We further provide insights into code-centric reinforcement learning and highlight the key factors that shape performance through detailed ablations and analysis. Our findings demonstrate that scaling high-quality synthetic data and adopting staged training can greatly advance code reasoning, while mitigating reliance on real-world coding data.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06953</guid>
|
||
<pubDate>Sun, 11 Jan 2026 15:22:33 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction</title>
|
||
<link>https://arxiv.org/abs/2601.06966</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06966.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haonan Bian, Zhiyuan Yao, Sen Hu, Zishan Xu, Shaolei Zhang, Yifu Guo, Ziliang Yang, Xueran Han, Huacan Wang, Ronghao Chen</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> As Large Language Models (LLMs) evolve from static dialogue interfaces to autonomous general agents, effective memory is paramount to ensuring long-term consistency. However, existing benchmarks primarily focus on casual conversation or task-oriented dialogue, failing to capture **"long-term project-oriented"** interactions where agents must track evolving goals. To bridge this gap, we introduce **RealMem**, the first benchmark grounded in realistic project scenarios. RealMem comprises over 2,000 cross-session dialogues across eleven scenarios, utilizing natural user queries for evaluation. We propose a synthesis pipeline that integrates Project Foundation Construction, Multi-Agent Dialogue Generation, and Memory and Schedule Management to simulate the dynamic evolution of memory. Experiments reveal that current memory systems face significant challenges in managing the long-term project states and dynamic context dependencies inherent in real-world projects. Our code and datasets are available at [https://github.com/AvatarMemory/RealMemBench](https://github.com/AvatarMemory/RealMemBench).</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.06966</guid>
|
||
<pubDate>Sun, 11 Jan 2026 15:49:36 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Solar Open Technical Report</title>
|
||
<link>https://arxiv.org/abs/2601.07022</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07022.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sungrae Park, Sanghoon Kim, Jungho Cho, Gyoungjin Gim, Dawoon Jung, Mikyoung Cha, Eunhae Choo, Taekgyu Hong, Minbyul Jeong, SeHwan Joo, Minsoo Khang, Eunwon Kim, Minjeong Kim, Sujeong Kim, Yunsu Kim, Hyeonju Lee, Seunghyun Lee, Sukyung Lee, Siyoung Park, Gyungin Shin, Inseo Song, Wonho Song, Seonghoon Yang, Seungyoun Yi, Sanghoon Yoon, Jeonghyun Ko, Seyoung Song, Keunwoo Choi, Hwalsuk Lee, Sunghun Kim, Du-Seong Chang, Kyunghyun Cho, Junsuk Choe, Hwaran Lee, Jae-Gil Lee, KyungTae Lim, Alice Oh</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> We introduce Solar Open, a 102B-parameter bilingual Mixture-of-Experts language model for underserved languages. Solar Open demonstrates a systematic methodology for building competitive LLMs by addressing three interconnected challenges. First, to train effectively despite data scarcity for underserved languages, we synthesize 4.5T tokens of high-quality, domain-specific, and RL-oriented data. Second, we coordinate this data through a progressive curriculum jointly optimizing composition, quality thresholds, and domain coverage across 20 trillion tokens. Third, to enable reasoning capabilities through scalable RL, we apply our proposed framework SnapPO for efficient optimization. Across benchmarks in English and Korean, Solar Open achieves competitive performance, demonstrating the effectiveness of this methodology for underserved language AI development.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.07022</guid>
|
||
<pubDate>Sun, 11 Jan 2026 18:33:09 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Dr. Zero: Self-Evolving Search Agents without Training Data</title>
|
||
<link>https://arxiv.org/abs/2601.07055</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenrui Yue, Kartikeya Upasani, Xianjun Yang, Suyu Ge, Shaoliang Nie, Yuning Mao, Zhe Liu, Dong Wang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> As high-quality data becomes increasingly difficult to obtain, data-free self-evolution has emerged as a promising paradigm. This approach allows large language models (LLMs) to autonomously generate and solve complex problems, thereby improving their reasoning capabilities. However, multi-turn search agents struggle in data-free self-evolution due to the limited question diversity and the substantial compute required for multi-step reasoning and tool using. In this work, we introduce Dr. Zero, a framework enabling search agents to effectively self-evolve without any training data. In particular, we design a self-evolution feedback loop where a proposer generates diverse questions to train a solver initialized from the same base model. As the solver evolves, it incentivizes the proposer to produce increasingly difficult yet solvable tasks, thus establishing an automated curriculum to refine both agents. To enhance training efficiency, we also introduce hop-grouped relative policy optimization (HRPO). This method clusters structurally similar questions to construct group-level baselines, effectively minimizing the sampling overhead in evaluating each query's individual difficulty and solvability. Consequently, HRPO significantly reduces the compute requirements for solver training without compromising performance or stability. Extensive experiment results demonstrate that the data-free Dr. Zero matches or surpasses fully supervised search agents, proving that complex reasoning and search capabilities can emerge solely through self-evolution.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.07055</guid>
|
||
<pubDate>Sun, 11 Jan 2026 20:27:55 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Lost in the Noise: How Reasoning Models Fail with Contextual Distractors</title>
|
||
<link>https://arxiv.org/abs/2601.07226</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07226.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seongyun Lee, Yongrae Jo, Minju Seo, Moontae Lee, Minjoon Seo</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Recent advances in reasoning models and agentic AI systems have led to an increased reliance on diverse external information. However, this shift introduces input contexts that are inherently noisy, a reality that current sanitized benchmarks fail to capture. We introduce NoisyBench, a comprehensive benchmark that systematically evaluates model robustness across 11 datasets in RAG, reasoning, alignment, and tool-use tasks against diverse noise types, including random documents, irrelevant chat histories, and hard negative distractors. Our evaluation reveals a catastrophic performance drop of up to 80% in state-of-the-art models when faced with contextual distractors. Crucially, we find that agentic workflows often amplify these errors by over-trusting noisy tool outputs, and distractors can trigger emergent misalignment even without adversarial intent. We find that prompting, context engineering, SFT, and outcome-reward only RL fail to ensure robustness; in contrast, our proposed Rationale-Aware Reward (RARE) significantly strengthens resilience by incentivizing the identification of helpful information within noise. Finally, we uncover an inverse scaling trend where increased test-time computation leads to worse performance in noisy settings and demonstrate via attention visualization that models disproportionately focus on distractor tokens, providing vital insights for building the next generation of robust, reasoning-capable agents.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.07226</guid>
|
||
<pubDate>Mon, 12 Jan 2026 05:43:51 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents</title>
|
||
<link>https://arxiv.org/abs/2601.07264</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07264.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weihao Xuan, Qingcheng Zeng, Heli Qi, Yunze Xiao, Junjue Wang, Naoto Yokoya</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Autonomous agents based on large language models (LLMs) are rapidly evolving to handle multi-turn tasks, but ensuring their trustworthiness remains a critical challenge. A fundamental pillar of this trustworthiness is calibration, which refers to an agent's ability to express confidence that reliably reflects its actual performance. While calibration is well-established for static models, its dynamics in tool-integrated agentic workflows remain underexplored. In this work, we systematically investigate verbalized calibration in tool-use agents, revealing a fundamental confidence dichotomy driven by tool type. Specifically, our pilot study identifies that evidence tools (e.g., web search) systematically induce severe overconfidence due to inherent noise in retrieved information, while verification tools (e.g., code interpreters) can ground reasoning through deterministic feedback and mitigate miscalibration. To robustly improve calibration across tool types, we propose a reinforcement learning (RL) fine-tuning framework that jointly optimizes task accuracy and calibration, supported by a holistic benchmark of reward designs. We demonstrate that our trained agents not only achieve superior calibration but also exhibit robust generalization from local training environments to noisy web settings and to distinct domains such as mathematical reasoning. Our results highlight the necessity of domain-specific calibration strategies for tool-use agents. More broadly, this work establishes a foundation for building self-aware agents that can reliably communicate uncertainty in high-stakes, real-world deployments.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.07264</guid>
|
||
<pubDate>Mon, 12 Jan 2026 07:10:35 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Controlled Self-Evolution for Algorithmic Code Optimization</title>
|
||
<link>https://arxiv.org/abs/2601.07348</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07348.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tu Hu, Ronghao Chen, Shuo Zhang, Jianghao Yin, Mou Xiao Feng, Jingping Liu, Shaolei Zhang, Wenqi Jiang, Yuqi Fang, Sen Hu, Yi Xu, Huacan Wang</p><p><b>Upvotes:</b> 106</p><p><b>Summary:</b> Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discover solutions with superior complexity within limited budgets. This inefficiency stems from initialization bias trapping evolution in poor solution regions, uncontrolled stochastic operations lacking feedback guidance, and insufficient experience utilization across tasks. To address these bottlenecks, we propose Controlled Self-Evolution (CSE), which consists of three key components. Diversified Planning Initialization generates structurally distinct algorithmic strategies for broad solution space coverage. Genetic Evolution replaces stochastic operations with feedback-guided mechanisms, enabling targeted mutation and compositional crossover. Hierarchical Evolution Memory captures both successful and failed experiences at inter-task and intra-task levels. Experiments on EffiBench-X demonstrate that CSE consistently outperforms all baselines across various LLM backbones. Furthermore, CSE achieves higher efficiency from early generations and maintains continuous improvement throughout evolution. Our code is publicly available at https://github.com/QuantaAlpha/EvoControl.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.07348</guid>
|
||
<pubDate>Mon, 12 Jan 2026 09:23:13 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models</title>
|
||
<link>https://arxiv.org/abs/2601.07351</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07351.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linhao Zhong, Linyu Wu, Bozhen Fang, Tianjian Feng, Chenchen Jing, Wen Wang, Jiaheng Zhang, Hao Chen, Chunhua Shen</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Diffusion Language Models (DLMs) offer a promising alternative for language modeling by enabling parallel decoding through iterative refinement. However, most DLMs rely on hard binary masking and discrete token assignments, which hinder the revision of early decisions and underutilize intermediate probabilistic representations. In this paper, we propose EvoToken-DLM, a novel diffusion-based language modeling approach that replaces hard binary masks with evolving soft token distributions. EvoToken-DLM enables a progressive transition from masked states to discrete outputs, supporting revisable decoding. To effectively support this evolution, we introduce continuous trajectory supervision, which aligns training objectives with iterative probabilistic updates. Extensive experiments across multiple benchmarks show that EvoToken-DLM consistently achieves superior performance, outperforming strong diffusion-based and masked DLM baselines. Project webpage: https://aim-uofa.github.io/EvoTokenDLM.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.07351</guid>
|
||
<pubDate>Mon, 12 Jan 2026 09:25:14 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era</title>
|
||
<link>https://arxiv.org/abs/2601.07526</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07526.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Zhang, Mouxiang Chen, Ruisheng Cao, Jiawei Chen, Fan Zhou, Yiheng Xu, Jiaxi Yang, Liang Chen, Changwei Luo, Kai Zhang, Fan Yan, KaShun Shum, Jiajun Zhang, Zeyu Cui, Hu Feng, Junyang Lin, Binyuan Hui, Min Yang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> The rapid development of interactive and autonomous AI systems signals our entry into the agentic era. Training and evaluating agents on complex agentic tasks such as software engineering and computer use requires not only efficient model computation but also sophisticated infrastructure capable of coordinating vast agent-environment interactions. However, no open-source infrastructure can effectively support large-scale training and evaluation on such complex agentic tasks. To address this challenge, we present MegaFlow, a large-scale distributed orchestration system that enables efficient scheduling, resource allocation, and fine-grained task management for agent-environment workloads. MegaFlow abstracts agent training infrastructure into three independent services (Model Service, Agent Service, and Environment Service) that interact through unified interfaces, enabling independent scaling and flexible resource allocation across diverse agent-environment configurations. In our agent training deployments, MegaFlow successfully orchestrates tens of thousands of concurrent agent tasks while maintaining high system stability and achieving efficient resource utilization. By enabling such large-scale agent training, MegaFlow addresses a critical infrastructure gap in the emerging agentic AI landscape.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.07526</guid>
|
||
<pubDate>Mon, 12 Jan 2026 13:25:33 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts</title>
|
||
<link>https://arxiv.org/abs/2601.08881</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Xu, Hongbin Yan, Juan Cao, Yiji Cheng, Tiankai Hang, Runze He, Zijin Yin, Shiyi Zhang, Yuxin Zhang, Jintao Li, Chunyu Wang, Qinglin Lu, Tong-Yee Lee, Fan Tang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Unified image generation and editing models suffer from severe task interference in dense diffusion transformers architectures, where a shared parameter space must compromise between conflicting objectives (e.g., local editing v.s. subject-driven generation). While the sparse Mixture-of-Experts (MoE) paradigm is a promising solution, its gating networks remain task-agnostic, operating based on local features, unaware of global task intent. This task-agnostic nature prevents meaningful specialization and fails to resolve the underlying task interference. In this paper, we propose a novel framework to inject semantic intent into MoE routing. We introduce a Hierarchical Task Semantic Annotation scheme to create structured task descriptors (e.g., scope, type, preservation). We then design Predictive Alignment Regularization to align internal routing decisions with the task's high-level semantics. This regularization evolves the gating network from a task-agnostic executor to a dispatch center. Our model effectively mitigates task interference, outperforming dense baselines in fidelity and quality, and our analysis shows that experts naturally develop clear and semantically correlated specializations.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08881</guid>
|
||
<pubDate>Mon, 12 Jan 2026 14:52:45 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.07641</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07641.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxuan Lu, Ziyu Kong, Yemin Wang, Rong Fu, Haiyuan Wan, Cheng Yang, Wenjie Lou, Haoran Sun, Lilong Wang, Yankai Jiang, Xiaosong Wang, Xiao Sun, Dongzhan Zhou</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on static, pre-defined tool libraries, a paradigm that fundamentally fails in scientific domains where tools are sparse, heterogeneous, and intrinsically incomplete. In this paper, we propose Test-Time Tool Evolution (TTE), a new paradigm that enables agents to synthesize, verify, and evolve executable tools during inference. By transforming tools from fixed resources into problem-driven artifacts, TTE overcomes the rigidity and long-tail limitations of static tool libraries. To facilitate rigorous evaluation, we introduce SciEvo, a benchmark comprising 1,590 scientific reasoning tasks supported by 925 automatically evolved tools. Extensive experiments show that TTE achieves state-of-the-art performance in both accuracy and tool efficiency, while enabling effective cross-domain adaptation of computational tools. The code and benchmark have been released at https://github.com/lujiaxuan0520/Test-Time-Tool-Evol.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.07641</guid>
|
||
<pubDate>Mon, 12 Jan 2026 15:22:51 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent</title>
|
||
<link>https://arxiv.org/abs/2601.07779</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07779.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Qingyun Li, Yian Wang, Yu Qiao, Zun Wang, Zichen Ding</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> While Vision-Language Models (VLMs) have significantly advanced Computer-Using Agents (CUAs), current frameworks struggle with robustness in long-horizon workflows and generalization in novel domains. These limitations stem from a lack of granular control over historical visual context curation and the absence of visual-aware tutorial retrieval. To bridge these gaps, we introduce OS-Symphony, a holistic framework that comprises an Orchestrator coordinating two key innovations for robust automation: (1) a Reflection-Memory Agent that utilizes milestone-driven long-term memory to enable trajectory-level self-correction, effectively mitigating visual context loss in long-horizon tasks; (2) Versatile Tool Agents featuring a Multimodal Searcher that adopts a SeeAct paradigm to navigate a browser-based sandbox to synthesize live, visually aligned tutorials, thereby resolving fidelity issues in unseen scenarios. Experimental results demonstrate that OS-Symphony delivers substantial performance gains across varying model scales, establishing new state-of-the-art results on three online benchmarks, notably achieving 65.84% on OSWorld.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.07779</guid>
|
||
<pubDate>Mon, 12 Jan 2026 17:55:51 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head</title>
|
||
<link>https://arxiv.org/abs/2601.07832</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07832.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kewei Zhang, Ye Huang, Yufan Deng, Jincheng Yu, Junsong Chen, Huan Ling, Enze Xie, Daquan Zhou</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades performance, with existing fixes typically re-introducing computational overhead through extra modules (e.g., depthwise separable convolution) that defeat the original purpose. In this work, we identify a key failure mode in these methods: global context collapse, where the model loses representational diversity. To address this, we propose Multi-Head Linear Attention (MHLA), which preserves this diversity by computing attention within divided heads along the token dimension. We prove that MHLA maintains linear complexity while recovering much of the expressive power of softmax attention, and verify its effectiveness across multiple domains, achieving a 3.6\% improvement on ImageNet classification, a 6.3\% gain on NLP, a 12.6\% improvement on image generation, and a 41\% enhancement on video generation under the same time complexity.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.07832</guid>
|
||
<pubDate>Mon, 12 Jan 2026 18:59:18 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MemoBrain: Executive Memory as an Agentic Brain for Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.08079</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08079.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongjin Qian, Zhao Cao, Zheng Liu</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working context of large language models. Without explicit memory mechanisms, such accumulation disrupts logical continuity and undermines task alignment. This positions memory not as an auxiliary efficiency concern, but as a core component for sustaining coherent, goal-directed reasoning over long horizons. We propose MemoBrain, an executive memory model for tool-augmented agents that constructs a dependency-aware memory over reasoning steps, capturing salient intermediate states and their logical relations. Operating as a co-pilot alongside the reasoning agent, MemoBrain organizes reasoning progress without blocking execution and actively manages the working context. Specifically, it prunes invalid steps, folds completed sub-trajectories, and preserves a compact, high-salience reasoning backbone under a fixed context budget. Together, these mechanisms enable explicit cognitive control over reasoning trajectories rather than passive context accumulation. We evaluate MemoBrain on challenging long-horizon benchmarks, including GAIA, WebWalker, and BrowseComp-Plus, demonstrating consistent improvements over strong baselines.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08079</guid>
|
||
<pubDate>Mon, 12 Jan 2026 23:44:59 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios</title>
|
||
<link>https://arxiv.org/abs/2601.08173</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08173.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daocheng Fu, Jianbiao Mei, Rong Wu, Xuemeng Yang, Jia Xu, Ding Wang, Pinlong Cai, Yong Liu, Licheng Wen, Botian Shi</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world deployment. We identify three key challenges: dynamic task scheduling, active exploration under uncertainty, and continuous learning from experience. To bridge this gap, we introduce , a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting. Unlike traditional benchmarks, evaluates agents along three dimensions: (1) context-aware scheduling for streaming tasks with varying priorities; (2) prudent information acquisition to reduce hallucination via active exploration; and (3) continuous evolution by distilling generalized strategies from rule-based, dynamically generated tasks. Experiments show that cutting-edge agents have significant deficiencies in dynamic environments, especially in active exploration and continual learning. Our work establishes a framework for assessing agent reliability, shifting evaluation from static tests to realistic, production-oriented scenarios. Our codes are available at https://github.com/KnowledgeXLab/EvoEnv</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08173</guid>
|
||
<pubDate>Tue, 13 Jan 2026 03:09:18 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale</title>
|
||
<link>https://arxiv.org/abs/2601.08225</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08225.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jungho Cho, Minbyul Jeong, Sungrae Park</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> The recent paradigm shift toward large reasoning models (LRMs) as autonomous agents has intensified the demand for sophisticated, multi-turn tool-use capabilities. Yet, existing datasets and data-generation approaches are limited by static, predefined toolsets that cannot scale to the complexity of open-ended human-agent collaboration. To address this, we initially developed a framework for automated task-oriented multi-turn dialogue generation at scale, utilizing an LRM-based simulator to dynamically generate high-value, domain-specific tools to solve specified tasks. However, we observe that a purely task-oriented design often results in "solely task-solving" trajectories, where the agent completes the objective with minimal interaction, failing to generate the high turn-count conversations seen in realistic scenarios. To bridge this gap, we shift toward a user-oriented simulation paradigm. By decoupling task generation from a dedicated user simulator that mimics human behavioral rules - such as incremental request-making and turn-by-turn feedback - we facilitate more authentic, extended multi-turn dialogues that reflect the iterative nature of real-world problem solving. Our generation pipeline operates as a versatile, plug-and-play module capable of initiating generation from any state, ensuring high scalability in producing extended tool-use data. Furthermore, by facilitating multiple task completions within a single trajectory, it yields a high-density dataset that reflects the multifaceted demands of real-world human-agent interaction.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08225</guid>
|
||
<pubDate>Tue, 13 Jan 2026 05:14:09 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices</title>
|
||
<link>https://arxiv.org/abs/2601.08303</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08303.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongting Hu, Aarush Gupta, Magzhan Gabidolla, Arpit Sahni, Huseyin Coskun, Yanyu Li, Yerlan Idelbayev, Ahsan Mahmood, Aleksei Lebedev, Dishani Lahiri, Anujraaj Goyal, Ju Hu, Mingming Gong, Sergey Tulyakov, Anil Kag</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT framework tailored for mobile and edge devices that achieves transformer-level generation quality under strict resource constraints. Our design combines three key components. First, we propose a compact DiT architecture with an adaptive global-local sparse attention mechanism that balances global context modeling and local detail preservation. Second, we propose an elastic training framework that jointly optimizes sub-DiTs of varying capacities within a unified supernetwork, allowing a single model to dynamically adjust for efficient inference across different hardware. Finally, we develop Knowledge-Guided Distribution Matching Distillation, a step-distillation pipeline that integrates the DMD objective with knowledge transfer from few-step teacher models, producing high-fidelity and low-latency generation (e.g., 4-step) suitable for real-time on-device use. Together, these contributions enable scalable, efficient, and high-quality diffusion models for deployment on diverse hardware.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08303</guid>
|
||
<pubDate>Tue, 13 Jan 2026 07:46:46 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>UM-Text: A Unified Multimodal Model for Image Understanding</title>
|
||
<link>https://arxiv.org/abs/2601.08321</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08321.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lichen Ma, Xiaolong Fu, Gaojing Zhou, Zipeng Guo, Ting Zhu, Yichun Liu, Yu Shi, Jason Li, Junshi Huang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to fully understand the instruction and reference image, and thus generate visual text that is style-consistent with the image. Previous methods often involve complex steps of specifying the text content and attributes, such as font size, color, and layout, without considering the stylistic consistency with the reference image. To address this, we propose UM-Text, a unified multimodal model for context understanding and visual text editing by natural language instructions. Specifically, we introduce a Visual Language Model (VLM) to process the instruction and reference image, so that the text content and layout can be elaborately designed according to the context information. To generate an accurate and harmonious visual text image, we further propose the UM-Encoder to combine the embeddings of various condition information, where the combination is automatically configured by VLM according to the input instruction. During training, we propose a regional consistency loss to offer more effective supervision for glyph generation on both latent and RGB space, and design a tailored three-stage training strategy to further enhance model performance. In addition, we contribute the UM-DATA-200K, a large-scale visual text image dataset on diverse scenes for model training. Extensive qualitative and quantitative results on multiple public benchmarks demonstrate that our method achieves state-of-the-art performance.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08321</guid>
|
||
<pubDate>Tue, 13 Jan 2026 08:18:49 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>JudgeRLVR: Judge First, Generate Second for Efficient Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.08468</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08468.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiangshan Duo, Hanyu Li, Hailin Zhang, Yudong Wang, Sujian Li, Liang Zhao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard paradigm for reasoning in Large Language Models. However, optimizing solely for final-answer correctness often drives models into aimless, verbose exploration, where they rely on exhaustive trial-and-error tactics rather than structured planning to reach solutions. While heuristic constraints like length penalties can reduce verbosity, they often truncate essential reasoning steps, creating a difficult trade-off between efficiency and verification. In this paper, we argue that discriminative capability is a prerequisite for efficient generation: by learning to distinguish valid solutions, a model can internalize a guidance signal that prunes the search space. We propose JudgeRLVR, a two-stage judge-then-generate paradigm. In the first stage, we train the model to judge solution responses with verifiable answers. In the second stage, we fine-tune the same model with vanilla generating RLVR initialized from the judge. Compared to Vanilla RLVR using the same math-domain training data, JudgeRLVR achieves a better quality--efficiency trade-off for Qwen3-30B-A3B: on in-domain math, it delivers about +3.7 points average accuracy gain with -42\% average generation length; on out-of-domain benchmarks, it delivers about +4.5 points average accuracy improvement, demonstrating enhanced generalization.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08468</guid>
|
||
<pubDate>Tue, 13 Jan 2026 11:47:42 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Ministral 3</title>
|
||
<link>https://arxiv.org/abs/2601.08584</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08584.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexander H. Liu, Kartik Khandelwal, Sandeep Subramanian, Victor Jouault, Abhinav Rastogi, Adrien Sadé, Alan Jeffares, Albert Jiang, Alexandre Cahill, Alexandre Gavaudan, Alexandre Sablayrolles, Amélie Héliou, Amos You, Andy Ehrenberg, Andy Lo, Anton Eliseev, Antonia Calvi, Avinash Sooriyarachchi, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Clémence Lanfranchi, Corentin Barreau, Cyprien Courtot, Daniele Grattarola, Darius Dabert, Diego de las Casas, Elliot Chane-Sane, Faruk Ahmed, Gabrielle Berrada, Gaëtan Ecrepont, Gauthier Guinet, Georgii Novikov, Guillaume Kunsch, Guillaume Lample, Guillaume Martin, Gunshi Gupta, Jan Ludziejewski, Jason Rute, Joachim Studnia, Jonas Amar, Joséphine Delas, Josselin Somerville Roberts, Karmesh Yadav, Khyathi Chandu, Kush Jain, Laurence Aitchison, Laurent Fainsin, Léonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Maarten Buyl, Margaret Jennings, Marie Pellat, Mark Prins, Mathieu Poirée, Mathilde Guillaumin, Matthieu Dinot, Matthieu Futeral, Maxime Darrin, Maximilian Augustin, Mia Chiquier, Michel Schimpf, Nathan Grinsztajn, Neha Gupta, Nikhil Raghuraman, Olivier Bousquet, Olivier Duchenne, Patricia Wang, Patrick von Platen, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Pavankumar Reddy Muddireddy, Philomène Chagniot, Pierre Stock, Pravesh Agrawal, Quentin Torroba, Romain Sauvestre, Roman Soletskyi, Rupert Menneer, Sagar Vaze, Samuel Barry, Sanchit Gandhi, Siddhant Waghjale, Siddharth Gandhi, Soham Ghosh, Srijan Mishra, Sumukh Aithal, Szymon Antoniak, Teven Le Scao, Théo Cachet, Theo Simon Sorg, Thibaut Lavril, Thiziri Nait Saada, Thomas Chabal, Thomas Foubert, Thomas Robert, Thomas Wang, Tim Lawson, Tom Bewley, Tom Bewley, Tom Edwards, Umar Jamil, Umberto Tomasini, Valeriia Nemychnikova, Van Phung, Vincent Maladière, Virgile Richard, Wassim Bouaziz, Wen-Ding Li, William Marshall, Xinghui Li, Xinyu Yang, Yassine El Ouahidi, Yihan Wang, Yunhao Tang, Zaccharie Ramzi</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> We introduce the Ministral 3 series, a family of parameter-efficient dense language models designed for compute and memory constrained applications, available in three model sizes: 3B, 8B, and 14B parameters. For each model size, we release three variants: a pretrained base model for general-purpose use, an instruction finetuned, and a reasoning model for complex problem-solving. In addition, we present our recipe to derive the Ministral 3 models through Cascade Distillation, an iterative pruning and continued training with distillation technique. Each model comes with image understanding capabilities, all under the Apache 2.0 license.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08584</guid>
|
||
<pubDate>Tue, 13 Jan 2026 14:06:03 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>End-to-End Video Character Replacement without Structural Guidance</title>
|
||
<link>https://arxiv.org/abs/2601.08587</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08587.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengbo Xu, Jie Ma, Ziheng Wang, Zhan Peng, Jun Liang, Jing Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Controllable video character replacement with a user-provided identity remains a challenging problem due to the lack of paired video data. Prior works have predominantly relied on a reconstruction-based paradigm that requires per-frame segmentation masks and explicit structural guidance (e.g., skeleton, depth). This reliance, however, severely limits their generalizability in complex scenarios involving occlusions, character-object interactions, unusual poses, or challenging illumination, often leading to visual artifacts and temporal inconsistencies. In this paper, we propose MoCha, a pioneering framework that bypasses these limitations by requiring only a single arbitrary frame mask. To effectively adapt the multi-modal input condition and enhance facial identity, we introduce a condition-aware RoPE and employ an RL-based post-training stage. Furthermore, to overcome the scarcity of qualified paired-training data, we propose a comprehensive data construction pipeline. Specifically, we design three specialized datasets: a high-fidelity rendered dataset built with Unreal Engine 5 (UE5), an expression-driven dataset synthesized by current portrait animation techniques, and an augmented dataset derived from existing video-mask pairs. Extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches. We will release the code to facilitate further research. Please refer to our project page for more details: orange-3dv-team.github.io/MoCha</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08587</guid>
|
||
<pubDate>Tue, 13 Jan 2026 14:10:34 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ExpSeek: Self-Triggered Experience Seeking for Web Agents</title>
|
||
<link>https://arxiv.org/abs/2601.08605</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, Yongbin Li</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Experience intervention in web agents emerges as a promising technical paradigm, enhancing agent interaction capabilities by providing valuable insights from accumulated experiences. However, existing methods predominantly inject experience passively as global context before task execution, struggling to adapt to dynamically changing contextual observations during agent-environment interaction. We propose ExpSeek, which shifts experience toward step-level proactive seeking: (1) estimating step-level entropy thresholds to determine intervention timing using the model's intrinsic signals; (2) designing step-level tailor-designed experience content. Experiments on Qwen3-8B and 32B models across four challenging web agent benchmarks demonstrate that ExpSeek achieves absolute improvements of 9.3% and 7.5%, respectively. Our experiments validate the feasibility and advantages of entropy as a self-triggering signal, reveal that even a 4B small-scale experience model can significantly boost the performance of larger agent models.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08605</guid>
|
||
<pubDate>Tue, 13 Jan 2026 14:48:34 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios</title>
|
||
<link>https://arxiv.org/abs/2601.08620</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08620.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> António Loison, Quentin Macé, Antoine Edy, Victor Xing, Tom Balough, Gabriel Moreira, Bo Liu, Manuel Faysse, Céline Hudelot, Gautier Viaud</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) pipelines must address challenges beyond simple single-document retrieval, such as interpreting visual elements (tables, charts, images), synthesizing information across documents, and providing accurate source grounding. Existing benchmarks fail to capture this complexity, often focusing on textual data, single-document comprehension, or evaluating retrieval and generation in isolation. We introduce ViDoRe v3, a comprehensive multimodal RAG benchmark featuring multi-type queries over visually rich document corpora. It covers 10 datasets across diverse professional domains, comprising ~26,000 document pages paired with 3,099 human-verified queries, each available in 6 languages. Through 12,000 hours of human annotation effort, we provide high-quality annotations for retrieval relevance, bounding box localization, and verified reference answers. Our evaluation of state-of-the-art RAG pipelines reveals that visual retrievers outperform textual ones, late-interaction models and textual reranking substantially improve performance, and hybrid or purely visual contexts enhance answer generation quality. However, current models still struggle with non-textual elements, open-ended queries, and fine-grained visual grounding. To encourage progress in addressing these challenges, the benchmark is released under a commercially permissive license at https://hf.co/vidore.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08620</guid>
|
||
<pubDate>Tue, 13 Jan 2026 15:00:33 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory</title>
|
||
<link>https://arxiv.org/abs/2601.08665</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08665.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaoan Wang, Yuanfei Luo, Xingyu Chen, Aocheng Luo, Dongyue Li, Chang Liu, Sheng Chen, Yangang Zhang, Junzhi Yu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> VLA models have shown promising potential in embodied navigation by unifying perception and planning while inheriting the strong generalization abilities of large VLMs. However, most existing VLA models rely on reactive mappings directly from observations to actions, lacking the explicit reasoning capabilities and persistent memory required for complex, long-horizon navigation tasks. To address these challenges, we propose VLingNav, a VLA model for embodied navigation grounded in linguistic-driven cognition. First, inspired by the dual-process theory of human cognition, we introduce an adaptive chain-of-thought mechanism, which dynamically triggers explicit reasoning only when necessary, enabling the agent to fluidly switch between fast, intuitive execution and slow, deliberate planning. Second, to handle long-horizon spatial dependencies, we develop a visual-assisted linguistic memory module that constructs a persistent, cross-modal semantic memory, enabling the agent to recall past observations to prevent repetitive exploration and infer movement trends for dynamic environments. For the training recipe, we construct Nav-AdaCoT-2.9M, the largest embodied navigation dataset with reasoning annotations to date, enriched with adaptive CoT annotations that induce a reasoning paradigm capable of adjusting both when to think and what to think about. Moreover, we incorporate an online expert-guided reinforcement learning stage, enabling the model to surpass pure imitation learning and to acquire more robust, self-explored navigation behaviors. Extensive experiments demonstrate that VLingNav achieves state-of-the-art performance across a wide range of embodied navigation benchmarks. Notably, VLingNav transfers to real-world robotic platforms in a zero-shot manner, executing various navigation tasks and demonstrating strong cross-domain and cross-task generalization.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08665</guid>
|
||
<pubDate>Tue, 13 Jan 2026 15:43:43 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Parallel Context-of-Experts Decoding for Retrieval Augmented Generation</title>
|
||
<link>https://arxiv.org/abs/2601.08670</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08670.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Giulio Corallo, Paolo Papotti</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Retrieval Augmented Generation faces a trade-off: concatenating documents in a long prompt enables multi-document reasoning but creates prefill bottlenecks, while encoding document KV caches separately offers speed but breaks cross-document interaction. We propose Parallel Context-of-Experts Decoding (Pced), a training-free framework that shifts evidence aggregation from the attention mechanism to the decoding. Pced treats retrieved documents as isolated "experts", synchronizing their predictions via a novel retrieval-aware contrastive decoding rule that weighs expert logits against the model prior. This approach recovers cross-document reasoning capabilities without constructing a shared attention across documents.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08670</guid>
|
||
<pubDate>Tue, 13 Jan 2026 15:46:59 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs</title>
|
||
<link>https://arxiv.org/abs/2601.08763</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08763.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Hu, Yucheng Wang, Yufei He, Jiaying Wu, Yilun Zhao, See-Kiong Ng, Cynthia Breazeal, Anh Tuan Luu, Hae Won Park, Bryan Hooi</p><p><b>Upvotes:</b> 125</p><p><b>Summary:</b> Reinforcement learning (RL) has become a central paradigm for post-training large language models (LLMs), particularly for complex reasoning tasks, yet it often suffers from exploration collapse: policies prematurely concentrate on a small set of dominant reasoning patterns, improving pass@1 while limiting rollout-level diversity and gains in pass@k. We argue that this failure stems from regularizing local token behavior rather than diversity over sets of solutions. To address this, we propose Uniqueness-Aware Reinforcement Learning, a rollout-level objective that explicitly rewards correct solutions that exhibit rare high-level strategies. Our method uses an LLM-based judge to cluster rollouts for the same problem according to their high-level solution strategies, ignoring superficial variations, and reweights policy advantages inversely with cluster size. As a result, correct but novel strategies receive higher rewards than redundant ones. Across mathematics, physics, and medical reasoning benchmarks, our approach consistently improves pass@k across large sampling budgets and increases the area under the pass@k curve (AUC@K) without sacrificing pass@1, while sustaining exploration and uncovering more diverse solution strategies at scale.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08763</guid>
|
||
<pubDate>Tue, 13 Jan 2026 17:48:43 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Motion Attribution for Video Generation</title>
|
||
<link>https://arxiv.org/abs/2601.08828</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08828.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xindi Wu, Despoina Paschalidou, Jun Gao, Antonio Torralba, Laura Leal-Taixé, Olga Russakovsky, Sanja Fidler, Jonathan Lorraine</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework that scales to modern, large, high-quality video datasets and models. We use this to study which fine-tuning clips improve or degrade temporal dynamics. Motive isolates temporal dynamics from static appearance via motion-weighted loss masks, yielding efficient and scalable motion-specific influence computation. On text-to-video models, Motive identifies clips that strongly affect motion and guides data curation that improves temporal consistency and physical plausibility. With Motive-selected high-influence data, our method improves both motion smoothness and dynamic degree on VBench, achieving a 74.1% human preference win rate compared with the pretrained base model. To our knowledge, this is the first framework to attribute motion rather than visual appearance in video generative models and to use it to curate fine-tuning data.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08828</guid>
|
||
<pubDate>Tue, 13 Jan 2026 18:59:09 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>3AM: Segment Anything with Geometric Consistency in Videos</title>
|
||
<link>https://arxiv.org/abs/2601.08831</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08831.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang-Che Sun, Cheng Sun, Chin-Yang Lin, Fu-En Yang, Min-Hung Chen, Yen-Yu Lin, Yu-Lun Liu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Video object segmentation methods like SAM2 achieve strong performance through memory-based architectures but struggle under large viewpoint changes due to reliance on appearance features. Traditional 3D instance segmentation methods address viewpoint consistency but require camera poses, depth maps, and expensive preprocessing. We introduce 3AM, a training-time enhancement that integrates 3D-aware features from MUSt3R into SAM2. Our lightweight Feature Merger fuses multi-level MUSt3R features that encode implicit geometric correspondence. Combined with SAM2's appearance features, the model achieves geometry-consistent recognition grounded in both spatial position and visual similarity. We propose a field-of-view aware sampling strategy ensuring frames observe spatially consistent object regions for reliable 3D correspondence learning. Critically, our method requires only RGB input at inference, with no camera poses or preprocessing. On challenging datasets with wide-baseline motion (ScanNet++, Replica), 3AM substantially outperforms SAM2 and extensions, achieving 90.6% IoU and 71.7% Positive IoU on ScanNet++'s Selected Subset, improving over state-of-the-art VOS methods by +15.9 and +30.4 points. Project page: https://jayisaking.github.io/3AM-Page/</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08831</guid>
|
||
<pubDate>Tue, 13 Jan 2026 18:59:54 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models</title>
|
||
<link>https://arxiv.org/abs/2601.08955</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08955.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youwei Liu, Jian Wang, Hanlin Wang, Beichen Guo, Wenjie Li</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Recent advances in world models have shown promise for modeling future dynamics of environmental states, enabling agents to reason and act without accessing real environments. Current methods mainly perform single-step or fixed-horizon rollouts, leaving their potential for complex task planning under-exploited. We propose Imagine-then-Plan (ITP), a unified framework for agent learning via lookahead imagination, where an agent's policy model interacts with the learned world model, yielding multi-step ``imagined'' trajectories. Since the imagination horizon may vary by tasks and stages, we introduce a novel adaptive lookahead mechanism by trading off the ultimate goal and task progress. The resulting imagined trajectories provide rich signals about future consequences, such as achieved progress and potential conflicts, which are fused with current observations, formulating a partially observable and imaginable Markov decision process to guide policy learning. We instantiate ITP with both training-free and reinforcement-trained variants. Extensive experiments across representative agent benchmarks demonstrate that ITP significantly outperforms competitive baselines. Further analyses validate that our adaptive lookahead largely enhances agents' reasoning capability, providing valuable insights into addressing broader, complex tasks.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.08955</guid>
|
||
<pubDate>Tue, 13 Jan 2026 19:49:58 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>TranslateGemma Technical Report</title>
|
||
<link>https://arxiv.org/abs/2601.09012</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09012.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mara Finkelstein, Isaac Caswell, Tobias Domhan, Jan-Thorsten Peter, Juraj Juraska, Parker Riley, Daniel Deutsch, Cole Dilanni, Colin Cherry, Eleftheria Briakou, Elizabeth Nielsen, Jiaming Luo, Kat Black, Ryan Mullins, Sweta Agrawal, Wenda Xu, Erin Kats, Stephane Jaskiewicz, Markus Freitag, David Vilar</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We present TranslateGemma, a suite of open machine translation models based on the Gemma 3 foundation models. To enhance the inherent multilingual capabilities of Gemma 3 for the translation task, we employ a two-stage fine-tuning process. First, supervised fine-tuning is performed using a rich mixture of high-quality large-scale synthetic parallel data generated via state-of-the-art models and human-translated parallel data. This is followed by a reinforcement learning phase, where we optimize translation quality using an ensemble of reward models, including MetricX-QE and AutoMQM, targeting translation quality. We demonstrate the effectiveness of TranslateGemma with human evaluation on the WMT25 test set across 10 language pairs and with automatic evaluation on the WMT24++ benchmark across 55 language pairs. Automatic metrics show consistent and substantial gains over the baseline Gemma 3 models across all sizes. Notably, smaller TranslateGemma models often achieve performance comparable to larger baseline models, offering improved efficiency. We also show that TranslateGemma models retain strong multimodal capabilities, with enhanced performance on the Vistra image translation benchmark. The release of the open TranslateGemma models aims to provide the research community with powerful and adaptable tools for machine translation.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09012</guid>
|
||
<pubDate>Tue, 13 Jan 2026 22:23:24 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG</title>
|
||
<link>https://arxiv.org/abs/2601.09028</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09028.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fengran Mo, Zhan Su, Yuchen Hui, Jinghan Zhang, Jia Ao Sun, Zheyuan Liu, Chao Zhang, Tetsuya Sakai, Jian-Yun Nie</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> The development of large language models (LLMs) has achieved superior performance in a range of downstream tasks, including LLM-based retrieval-augmented generation (RAG). The quality of generated content heavily relies on the usefulness of the retrieved information and the capacity of LLMs' internal information processing mechanism to incorporate it in answer generation. It is generally assumed that the retrieved information is relevant to the question. However, the retrieved information may have a variable degree of relevance and usefulness, depending on the question and the document collection. It is important to take into account the relevance of the retrieved information in answer generation. In this paper, we propose OpenDecoder, a new approach that leverages explicit evaluation of the retrieved information as quality indicator features for generation. We aim to build a RAG model that is more robust to varying levels of noisy context. Three types of explicit evaluation information are considered: relevance score, ranking score, and QPP (query performance prediction) score. The experimental results on five benchmark datasets demonstrate the effectiveness and better robustness of OpenDecoder by outperforming various baseline methods. Importantly, this paradigm is flexible to be integrated with the post-training of LLMs for any purposes and incorporated with any type of external indicators.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09028</guid>
|
||
<pubDate>Tue, 13 Jan 2026 23:26:30 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.09088</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09088.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaotian Yan, Kaiyuan Liu, Chen Shen, Bing Wang, Sinan Fan, Jun Zhang, Yue Wu, Zheng Wang, Jieping Ye</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> In this report, we introduce DASD-4B-Thinking, a lightweight yet highly capable, fully open-source reasoning model. It achieves SOTA performance among open-source models of comparable scale across challenging benchmarks in mathematics, scientific reasoning, and code generation -- even outperforming several larger models. We begin by critically reexamining a widely adopted distillation paradigm in the community: SFT on teacher-generated responses, also known as sequence-level distillation. Although a series of recent works following this scheme have demonstrated remarkable efficiency and strong empirical performance, they are primarily grounded in the SFT perspective. Consequently, these approaches focus predominantly on designing heuristic rules for SFT data filtering, while largely overlooking the core principle of distillation itself -- enabling the student model to learn the teacher's full output distribution so as to inherit its generalization capability. Specifically, we identify three critical limitations in current practice: i) Inadequate representation of the teacher's sequence-level distribution; ii) Misalignment between the teacher's output distribution and the student's learning capacity; and iii) Exposure bias arising from teacher-forced training versus autoregressive inference. In summary, these shortcomings reflect a systemic absence of explicit teacher-student interaction throughout the distillation process, leaving the essence of distillation underexploited. To address these issues, we propose several methodological innovations that collectively form an enhanced sequence-level distillation training pipeline. Remarkably, DASD-4B-Thinking obtains competitive results using only 448K training samples -- an order of magnitude fewer than those employed by most existing open-source efforts. To support community research, we publicly release our models and the training dataset.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09088</guid>
|
||
<pubDate>Wed, 14 Jan 2026 02:43:17 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SkinFlow: Efficient Information Transmission for Open Dermatological Diagnosis via Dynamic Visual Encoding and Staged RL</title>
|
||
<link>https://arxiv.org/abs/2601.09136</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09136.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lijun Liu, Linwei Chen, Zhishou Zhang, Meng Tian, Hengfu Cui, Ruiyang Li, Zhaocheng Liu, Qiang Ju, Qianxi Li, Hong-Yu Zhou</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> General-purpose Large Vision-Language Models (LVLMs), despite their massive scale, often falter in dermatology due to "diffuse attention" - the inability to disentangle subtle pathological lesions from background noise. In this paper, we challenge the assumption that parameter scaling is the only path to medical precision. We introduce SkinFlow, a framework that treats diagnosis as an optimization of visual information transmission efficiency. Our approach utilizes a Virtual-Width Dynamic Vision Encoder (DVE) to "unfold" complex pathological manifolds without physical parameter expansion, coupled with a two-stage Reinforcement Learning strategy. This strategy sequentially aligns explicit medical descriptions (Stage I) and reconstructs implicit diagnostic textures (Stage II) within a constrained semantic space. Furthermore, we propose a clinically grounded evaluation protocol that prioritizes diagnostic safety and hierarchical relevance over rigid label matching. Empirical results are compelling: our 7B model establishes a new state-of-the-art on the Fitzpatrick17k benchmark, achieving a +12.06% gain in Top-1 accuracy and a +28.57% boost in Top-6 accuracy over the massive general-purpose models (e.g., Qwen3VL-235B and GPT-5.2). These findings demonstrate that optimizing geometric capacity and information flow yields superior diagnostic reasoning compared to raw parameter scaling.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09136</guid>
|
||
<pubDate>Wed, 14 Jan 2026 04:21:07 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>EvasionBench: Detecting Evasive Answers in Financial Q&A via Multi-Model Consensus and LLM-as-Judge</title>
|
||
<link>https://arxiv.org/abs/2601.09142</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09142.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijian Ma, Yan Lin, Yi Yang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Detecting evasive answers in earnings calls is critical for financial transparency, yet progress is hindered by the lack of large-scale benchmarks. We introduce EvasionBench, comprising 30,000 training samples and 1,000 human-annotated test samples (Cohen's Kappa 0.835) across three evasion levels. Our key contribution is a multi-model annotation framework leveraging a core insight: disagreement between frontier LLMs signals hard examples most valuable for training. We mine boundary cases where two strong annotators conflict, using a judge to resolve labels. This approach outperforms single-model distillation by 2.4 percent, with judge-resolved samples improving generalization despite higher training loss (0.421 vs 0.393) - evidence that disagreement mining acts as implicit regularization. Our trained model Eva-4B (4B parameters) achieves 81.3 percent accuracy, outperforming its base by 25 percentage points and approaching frontier LLM performance at a fraction of inference cost.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09142</guid>
|
||
<pubDate>Wed, 14 Jan 2026 04:26:43 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Geometric Stability: The Missing Axis of Representations</title>
|
||
<link>https://arxiv.org/abs/2601.09173</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09173.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Prashant C. Raju</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Analysis of learned representations has a blind spot: it focuses on similarity, measuring how closely embeddings align with external references, but similarity reveals only what is represented, not whether that structure is robust. We introduce geometric stability, a distinct dimension that quantifies how reliably representational geometry holds under perturbation, and present Shesha, a framework for measuring it. Across 2,463 configurations in seven domains, we show that stability and similarity are empirically uncorrelated (ρapprox 0.01) and mechanistically distinct: similarity metrics collapse after removing the top principal components, while stability retains sensitivity to fine-grained manifold structure. This distinction yields actionable insights: for safety monitoring, stability acts as a functional geometric canary, detecting structural drift nearly 2times more sensitively than CKA while filtering out the non-functional noise that triggers false alarms in rigid distance metrics; for controllability, supervised stability predicts linear steerability (ρ= 0.89-0.96); for model selection, stability dissociates from transferability, revealing a geometric tax that transfer optimization incurs. Beyond machine learning, stability predicts CRISPR perturbation coherence and neural-behavioral coupling. By quantifying how reliably systems maintain structure, geometric stability provides a necessary complement to similarity for auditing representations across biological and computational systems.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09173</guid>
|
||
<pubDate>Wed, 14 Jan 2026 05:15:22 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MAXS: Meta-Adaptive Exploration with LLM Agents</title>
|
||
<link>https://arxiv.org/abs/2601.09259</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jian Zhang, Zhiyuan Wang, Zhangqi Wang, Yu He, Haoran Luo, li yuan, Lingling Zhang, Rui Mao, Qika Lin, Jun Liu</p><p><b>Upvotes:</b> 88</p><p><b>Summary:</b> Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools. However, during agent inference, existing methods often suffer from (i) locally myopic generation, due to the absence of lookahead, and (ii) trajectory instability, where minor early errors can escalate into divergent reasoning paths. These issues make it difficult to balance global effectiveness and computational efficiency. To address these two issues, we propose meta-adaptive exploration with LLM agents https://github.com/exoskeletonzj/MAXS, a meta-adaptive reasoning framework based on LLM Agents that flexibly integrates tool execution and reasoning planning. MAXS employs a lookahead strategy to extend reasoning paths a few steps ahead, estimating the advantage value of tool usage, and combines step consistency variance and inter-step trend slopes to jointly select stable, consistent, and high-value reasoning steps. Additionally, we introduce a trajectory convergence mechanism that controls computational cost by halting further rollouts once path consistency is achieved, enabling a balance between resource efficiency and global effectiveness in multi-tool reasoning. We conduct extensive empirical studies across three base models (MiMo-VL-7B, Qwen2.5-VL-7B, Qwen2.5-VL-32B) and five datasets, demonstrating that MAXS consistently outperforms existing methods in both performance and inference efficiency. Further analysis confirms the effectiveness of our lookahead strategy and tool usage.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09259</guid>
|
||
<pubDate>Wed, 14 Jan 2026 07:48:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation</title>
|
||
<link>https://arxiv.org/abs/2601.09274</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09274.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jian Zhang, Yu He, Zhiyuan Wang, Zhangqi Wang, Kai He, Fangzhi Xu, Qika Lin, Jun Liu</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> Scientific reasoning relies not only on logical inference but also on activating prior knowledge and experiential structures. Memory can efficiently reuse knowledge and enhance reasoning consistency and stability. However, existing benchmarks mainly evaluate final answers or step-by-step coherence, overlooking the memory-driven mechanisms that underlie human reasoning, which involves activating anchors and attractors, then integrating them into multi-step inference. To address this gap, we propose A^3-Bench~ https://a3-bench.github.io, a benchmark designed to evaluate scientific reasoning through dual-scale memory-driven activation, grounded in Anchor and Attractor Activation. First, we annotate 2,198 science reasoning problems across domains using the SAPM process(subject, anchor & attractor, problem, and memory developing). Second, we introduce a dual-scale memory evaluation framework utilizing anchors and attractors, along with the AAUI(Anchor--Attractor Utilization Index) metric to measure memory activation rates. Finally, through experiments with various base models and paradigms, we validate A^3-Bench and analyze how memory activation impacts reasoning performance, providing insights into memory-driven scientific reasoning.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09274</guid>
|
||
<pubDate>Wed, 14 Jan 2026 08:17:41 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines</title>
|
||
<link>https://arxiv.org/abs/2601.09465</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09465.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuo Zhang, Chaofa Yuan, Ryan Guo, Xiaomin Yu, Rui Xu, Zhangquan Chen, Zinuo Li, Zhi Yang, Shuhao Guan, Zhenheng Tang, Sen Hu, Liwen Zhang, Ronghao Chen, Huacan Wang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> While LLM-based agents have shown promise for deep research, most existing approaches rely on fixed workflows that struggle to adapt to real-world, open-ended queries. Recent work therefore explores self-evolution by allowing agents to rewrite their own code or prompts to improve problem-solving ability, but unconstrained optimization often triggers instability, hallucinations, and instruction drift. We propose EvoFSM, a structured self-evolving framework that achieves both adaptability and control by evolving an explicit Finite State Machine (FSM) instead of relying on free-form rewriting. EvoFSM decouples the optimization space into macroscopic Flow (state-transition logic) and microscopic Skill (state-specific behaviors), enabling targeted improvements under clear behavioral boundaries. Guided by a critic mechanism, EvoFSM refines the FSM through a small set of constrained operations, and further incorporates a self-evolving memory that distills successful trajectories as reusable priors and failure patterns as constraints for future queries. Extensive evaluations on five multi-hop QA benchmarks demonstrate the effectiveness of EvoFSM. In particular, EvoFSM reaches 58.0% accuracy on the DeepSearch benchmark. Additional results on interactive decision-making tasks further validate its generalization.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09465</guid>
|
||
<pubDate>Wed, 14 Jan 2026 13:19:13 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>V-DPM: 4D Video Reconstruction with Dynamic Point Maps</title>
|
||
<link>https://arxiv.org/abs/2601.09499</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09499.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Edgar Sucar, Eldar Insafutdinov, Zihang Lai, Andrea Vedaldi</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Powerful 3D representations such as DUSt3R invariant point maps, which encode 3D shape and camera parameters, have significantly advanced feed forward 3D reconstruction. While point maps assume static scenes, Dynamic Point Maps (DPMs) extend this concept to dynamic 3D content by additionally representing scene motion. However, existing DPMs are limited to image pairs and, like DUSt3R, require post processing via optimization when more than two views are involved. We argue that DPMs are more useful when applied to videos and introduce V-DPM to demonstrate this. First, we show how to formulate DPMs for video input in a way that maximizes representational power, facilitates neural prediction, and enables reuse of pretrained models. Second, we implement these ideas on top of VGGT, a recent and powerful 3D reconstructor. Although VGGT was trained on static scenes, we show that a modest amount of synthetic data is sufficient to adapt it into an effective V-DPM predictor. Our approach achieves state of the art performance in 3D and 4D reconstruction for dynamic scenes. In particular, unlike recent dynamic extensions of VGGT such as P3, DPMs recover not only dynamic depth but also the full 3D motion of every point in the scene.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09499</guid>
|
||
<pubDate>Wed, 14 Jan 2026 14:03:42 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding</title>
|
||
<link>https://arxiv.org/abs/2601.09575</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09575.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sheng-Yu Huang, Jaesung Choe, Yu-Chiang Frank Wang, Cheng Sun</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> We propose OpenVoxel, a training-free algorithm for grouping and captioning sparse voxels for the open-vocabulary 3D scene understanding tasks. Given the sparse voxel rasterization (SVR) model obtained from multi-view images of a 3D scene, our OpenVoxel is able to produce meaningful groups that describe different objects in the scene. Also, by leveraging powerful Vision Language Models (VLMs) and Multi-modal Large Language Models (MLLMs), our OpenVoxel successfully build an informative scene map by captioning each group, enabling further 3D scene understanding tasks such as open-vocabulary segmentation (OVS) or referring expression segmentation (RES). Unlike previous methods, our method is training-free and does not introduce embeddings from a CLIP/BERT text encoder. Instead, we directly proceed with text-to-text search using MLLMs. Through extensive experiments, our method demonstrates superior performance compared to recent studies, particularly in complex referring expression segmentation (RES) tasks. The code will be open.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09575</guid>
|
||
<pubDate>Wed, 14 Jan 2026 15:45:57 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.09667</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09667.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Hu, Yunhai Hu, Juncheng Liu, Shuyue Stella Li, Yucheng Wang, Zhen Xu, See-Kiong Ng, Anh Tuan Luu, Xinxing Xu, Bryan Hooi, Cynthia Breazeal, Hae Won Park</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting teammates induce non-stationarity, and rewards are often sparse and high-variance. Therefore, we introduce Multi-Agent Test-Time Reinforcement Learning (MATTRL), a framework that injects structured textual experience into multi-agent deliberation at inference time. MATTRL forms a multi-expert team of specialists for multi-turn discussions, retrieves and integrates test-time experiences, and reaches consensus for final decision-making. We also study credit assignment for constructing a turn-level experience pool, then reinjecting it into the dialogue. Across challenging benchmarks in medicine, math, and education, MATTRL improves accuracy by an average of 3.67\% over a multi-agent baseline, and by 8.67\% over comparable single-agent baselines. Ablation studies examine different credit-assignment schemes and provide a detailed comparison of how they affect training outcomes. MATTRL offers a stable, effective and efficient path to distribution-shift-robust multi-agent reasoning without tuning.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09667</guid>
|
||
<pubDate>Wed, 14 Jan 2026 17:57:43 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>STEP3-VL-10B Technical Report</title>
|
||
<link>https://arxiv.org/abs/2601.09668</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09668.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ailin Huang, Chengyuan Yao, Chunrui Han, Fanqi Wan, Hangyu Guo, Haoran Lv, Hongyu Zhou, Jia Wang, Jian Zhou, Jianjian Sun, Jingcheng Hu, Kangheng Lin, Liang Zhao, Mitt Huang, Song Yuan, Wenwen Qu, Xiangfeng Wang, Yanlin Lai, Yingxiu Zhao, Yinmin Zhang, Yukang Shi, Yuyang Chen, Zejia Weng, Ziyang Meng, Ang Li, Aobo Kong, Bo Dong, Changyi Wan, David Wang, Di Qi, Dingming Li, En Yu, Guopeng Li, Haiquan Yin, Han Zhou, Hanshan Zhang, Haolong Yan, Hebin Zhou, Hongbo Peng, Jiaran Zhang, Jiashu Lv, Jiayi Fu, Jie Cheng, Jie Zhou, Jisheng Yin, Jingjing Xie, Jingwei Wu, Jun Zhang, Junfeng Liu, Kaijun Tan, Kaiwen Yan, Liangyu Chen, Lina Chen, Mingliang Li, Qian Zhao, Quan Sun, Shaoliang Pang, Shengjie Fan, Shijie Shang, Siyuan Zhang, Tianhao You, Wei Ji, Wuxun Xie, Xiaobo Yang, Xiaojie Hou, Xiaoran Jiao, Xiaoxiao Ren, Xiangwen Kong, Xin Huang, Xin Wu, Xing Chen, Xinran Wang, Xuelin Zhang, Yana Wei, Yang Li, Yanming Xu, Yeqing Shen, Yuang Peng, Yue Peng, Yu Zhou, Yusheng Li, Yuxiang Yang, Yuyang Zhang, Zhe Xie, Zhewei Huang, Zhenyi Lu, Zhimin Fan, Zihui Cheng, Daxin Jiang, Qi Han, Xiangyu Zhang, Yibo Zhu, Zheng Ge</p><p><b>Upvotes:</b> 161</p><p><b>Summary:</b> We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-VL-10B is realized through two strategic shifts: first, a unified, fully unfrozen pre-training strategy on 1.2T multimodal tokens that integrates a language-aligned Perception Encoder with a Qwen3-8B decoder to establish intrinsic vision-language synergy; and second, a scaled post-training pipeline featuring over 1k iterations of reinforcement learning. Crucially, we implement Parallel Coordinated Reasoning (PaCoRe) to scale test-time compute, allocating resources to scalable perceptual reasoning that explores and synthesizes diverse visual hypotheses. Consequently, despite its compact 10B footprint, STEP3-VL-10B rivals or surpasses models 10times-20times larger (e.g., GLM-4.6V-106B, Qwen3-VL-235B) and top-tier proprietary flagships like Gemini 2.5 Pro and Seed-1.5-VL. Delivering best-in-class performance, it records 92.2% on MMBench and 80.11% on MMMU, while excelling in complex reasoning with 94.43% on AIME2025 and 75.95% on MathVision. We release the full model suite to provide the community with a powerful, efficient, and reproducible baseline.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09668</guid>
|
||
<pubDate>Wed, 14 Jan 2026 17:58:24 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation</title>
|
||
<link>https://arxiv.org/abs/2601.09688</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09688.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibo Wang, Lei Wang, Yue Deng, Keming Wu, Yao Xiao, Huanjin Yao, Liwei Kang, Hai Ye, Yongcheng Jing, Lidong Bing</p><p><b>Upvotes:</b> 109</p><p><b>Summary:</b> Deep research systems are widely used for multi-step web research, analysis, and cross-source synthesis, yet their evaluation remains challenging. Existing benchmarks often require annotation-intensive task construction, rely on static evaluation dimensions, or fail to reliably verify facts when citations are missing. To bridge these gaps, we introduce DeepResearchEval, an automated framework for deep research task construction and agentic evaluation. For task construction, we propose a persona-driven pipeline generating realistic, complex research tasks anchored in diverse user profiles, applying a two-stage filter Task Qualification and Search Necessity to retain only tasks requiring multi-source evidence integration and external retrieval. For evaluation, we propose an agentic pipeline with two components: an Adaptive Point-wise Quality Evaluation that dynamically derives task-specific evaluation dimensions, criteria, and weights conditioned on each generated task, and an Active Fact-Checking that autonomously extracts and verifies report statements via web search, even when citations are missing.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09688</guid>
|
||
<pubDate>Wed, 14 Jan 2026 18:38:31 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering</title>
|
||
<link>https://arxiv.org/abs/2601.09697</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09697.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jieying Chen, Jeffrey Hu, Joan Lasenby, Ayush Tewari</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of GPU time for just a few seconds of video. This inefficiency poses a critical barrier to deploying generative video in applications that require real-time interactions, such as embodied AI and VR/AR. This paper explores a new strategy for camera-conditioned video generation of static scenes: using diffusion-based generative models to generate a sparse set of keyframes, and then synthesizing the full video through 3D reconstruction and rendering. By lifting keyframes into a 3D representation and rendering intermediate views, our approach amortizes the generation cost across hundreds of frames while enforcing geometric consistency. We further introduce a model that predicts the optimal number of keyframes for a given camera trajectory, allowing the system to adaptively allocate computation. Our final method, SRENDER, uses very sparse keyframes for simple trajectories and denser ones for complex camera motion. This results in video generation that is more than 40 times faster than the diffusion-based baseline in generating 20 seconds of video, while maintaining high visual fidelity and temporal stability, offering a practical path toward efficient and controllable video synthesis.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09697</guid>
|
||
<pubDate>Wed, 14 Jan 2026 18:50:06 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning</title>
|
||
<link>https://arxiv.org/abs/2601.09708</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09708.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chi-Pin Huang, Yunze Man, Zhiding Yu, Min-Hung Chen, Jan Kautz, Yu-Chiang Frank Wang, Fu-En Yang</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on reasoning VLAs show that explicit chain-of-thought (CoT) can improve generalization, they suffer from high inference latency due to lengthy reasoning traces. We propose Fast-ThinkAct, an efficient reasoning framework that achieves compact yet performant planning through verbalizable latent reasoning. Fast-ThinkAct learns to reason efficiently with latent CoTs by distilling from a teacher, driven by a preference-guided objective to align manipulation trajectories that transfers both linguistic and visual planning capabilities for embodied control. This enables reasoning-enhanced policy learning that effectively connects compact reasoning to action execution. Extensive experiments across diverse embodied manipulation and reasoning benchmarks demonstrate that Fast-ThinkAct achieves strong performance with up to 89.3\% reduced inference latency over state-of-the-art reasoning VLAs, while maintaining effective long-horizon planning, few-shot adaptation, and failure recovery.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09708</guid>
|
||
<pubDate>Wed, 14 Jan 2026 18:59:59 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Transition Matching Distillation for Fast Video Generation</title>
|
||
<link>https://arxiv.org/abs/2601.09881</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weili Nie, Julius Berner, Nanye Ma, Chao Liu, Saining Xie, Arash Vahdat</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to their inefficient multi-step sampling process. In this work, we present Transition Matching Distillation (TMD), a novel framework for distilling video diffusion models into efficient few-step generators. The central idea of TMD is to match the multi-step denoising trajectory of a diffusion model with a few-step probability transition process, where each transition is modeled as a lightweight conditional flow. To enable efficient distillation, we decompose the original diffusion backbone into two components: (1) a main backbone, comprising the majority of early layers, that extracts semantic representations at each outer transition step; and (2) a flow head, consisting of the last few layers, that leverages these representations to perform multiple inner flow updates. Given a pretrained video diffusion model, we first introduce a flow head to the model, and adapt it into a conditional flow map. We then apply distribution matching distillation to the student model with flow head rollout in each transition step. Extensive experiments on distilling Wan2.1 1.3B and 14B text-to-video models demonstrate that TMD provides a flexible and strong trade-off between generation speed and visual quality. In particular, TMD outperforms existing distilled models under comparable inference costs in terms of visual fidelity and prompt adherence. Project page: https://research.nvidia.com/labs/genair/tmd</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.09881</guid>
|
||
<pubDate>Wed, 14 Jan 2026 21:30:03 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation</title>
|
||
<link>https://arxiv.org/abs/2601.10061</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10061.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengzhuo Tong, Mingkun Chang, Shenglong Zhang, Yuran Wang, Cheng Liang, Zhizheng Zhao, Ruichuan An, Bohan Zeng, Yang Shi, Yifan Dai, Ziming Zhao, Guanbin Li, Pengfei Wan, Yuanxing Zhang, Wentao Zhang</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Recent video generation models have revealed the emergence of Chain-of-Frame (CoF) reasoning, enabling frame-by-frame visual inference. With this capability, video models have been successfully applied to various visual tasks (e.g., maze solving, visual puzzles). However, their potential to enhance text-to-image (T2I) generation remains largely unexplored due to the absence of a clearly defined visual reasoning starting point and interpretable intermediate states in the T2I generation process. To bridge this gap, we propose CoF-T2I, a model that integrates CoF reasoning into T2I generation via progressive visual refinement, where intermediate frames act as explicit reasoning steps and the final frame is taken as output. To establish such an explicit generation process, we curate CoF-Evol-Instruct, a dataset of CoF trajectories that model the generation process from semantics to aesthetics. To further improve quality and avoid motion artifacts, we enable independent encoding operation for each frame. Experiments show that CoF-T2I significantly outperforms the base video model and achieves competitive performance on challenging benchmarks, reaching 0.86 on GenEval and 7.468 on Imagine-Bench. These results indicate the substantial promise of video models for advancing high-quality text-to-image generation.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10061</guid>
|
||
<pubDate>Thu, 15 Jan 2026 04:33:06 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Deriving Character Logic from Storyline as Codified Decision Trees</title>
|
||
<link>https://arxiv.org/abs/2601.10080</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10080.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Letian Peng, Kun Zhou, Longfei Yun, Yupeng Hou, Jingbo Shang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Role-playing (RP) agents rely on behavioral profiles to act consistently across diverse narrative contexts, yet existing profiles are largely unstructured, non-executable, and weakly validated, leading to brittle agent behavior. We propose Codified Decision Trees (CDT), a data-driven framework that induces an executable and interpretable decision structure from large-scale narrative data. CDT represents behavioral profiles as a tree of conditional rules, where internal nodes correspond to validated scene conditions and leaves encode grounded behavioral statements, enabling deterministic retrieval of context-appropriate rules at execution time. The tree is learned by iteratively inducing candidate scene-action rules, validating them against data, and refining them through hierarchical specialization, yielding profiles that support transparent inspection and principled updates. Across multiple benchmarks, CDT substantially outperforms human-written profiles and prior profile induction methods on 85 characters across 16 artifacts, indicating that codified and validated behavioral representations lead to more reliable agent grounding.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10080</guid>
|
||
<pubDate>Thu, 15 Jan 2026 05:12:43 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>FlowAct-R1: Towards Interactive Humanoid Video Generation</title>
|
||
<link>https://arxiv.org/abs/2601.10103</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10103.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lizhen Wang, Yongming Zhu, Zhipeng Ge, Youwei Zheng, Longhao Zhang, Tianshu Hu, Shiyang Qin, Mingshuang Luo, Jiaxu Zhang, Xin Chen, Yulong Wang, Zerong Zheng, Jianwen Jiang, Chao Liang, Weifeng Chen, Xing Wang, Yuan Zhang, Mingyuan Gao</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Interactive humanoid video generation aims to synthesize lifelike visual agents that can engage with humans through continuous and responsive video. Despite recent advances in video synthesis, existing methods often grapple with the trade-off between high-fidelity synthesis and real-time interaction requirements. In this paper, we propose FlowAct-R1, a framework specifically designed for real-time interactive humanoid video generation. Built upon a MMDiT architecture, FlowAct-R1 enables the streaming synthesis of video with arbitrary durations while maintaining low-latency responsiveness. We introduce a chunkwise diffusion forcing strategy, complemented by a novel self-forcing variant, to alleviate error accumulation and ensure long-term temporal consistency during continuous interaction. By leveraging efficient distillation and system-level optimizations, our framework achieves a stable 25fps at 480p resolution with a time-to-first-frame (TTFF) of only around 1.5 seconds. The proposed method provides holistic and fine-grained full-body control, enabling the agent to transition naturally between diverse behavioral states in interactive scenarios. Experimental results demonstrate that FlowAct-R1 achieves exceptional behavioral vividness and perceptual realism, while maintaining robust generalization across diverse character styles.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10103</guid>
|
||
<pubDate>Thu, 15 Jan 2026 06:16:22 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.10129</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10129.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linquan Wu, Tianxiang Jiang, Yifei Dong, Haoyu Yang, Fengji Zhang, Shichaang Meng, Ai Xuan, Linqi Song, Jacky Keung</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamics. In this work, we identify a critical Perception Gap in distillation: student models frequently mimic a teacher's textual output while attending to fundamentally divergent visual regions, effectively relying on language priors rather than grounded perception. To bridge this, we propose LaViT, a framework that aligns latent visual thoughts rather than static embeddings. LaViT compels the student to autoregressively reconstruct the teacher's visual semantics and attention trajectories prior to text generation, employing a curriculum sensory gating mechanism to prevent shortcut learning. Extensive experiments show that LaViT significantly enhances visual grounding, achieving up to +16.9% gains on complex reasoning tasks and enabling a compact 3B model to outperform larger open-source variants and proprietary models like GPT-4o.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10129</guid>
|
||
<pubDate>Thu, 15 Jan 2026 07:14:24 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints</title>
|
||
<link>https://arxiv.org/abs/2601.10131</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10131.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizhan Li, Florence Cloutier, Sifan Wu, Ali Parviz, Boris Knyazev, Yan Zhang, Glen Berseth, Bang Liu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Generating molecules that satisfy precise numeric constraints over multiple physicochemical properties is critical and challenging. Although large language models (LLMs) are expressive, they struggle with precise multi-objective control and numeric reasoning without external structure and feedback. We introduce M olGen, a fragment-level, retrieval-augmented, two-stage framework for molecule generation under multi-property constraints. Stage I : Prototype generation: a multi-agent reasoner performs retrieval-anchored, fragment-level edits to produce a candidate near the feasible region. Stage II : RL-based fine-grained optimization: a fragment-level optimizer trained with Group Relative Policy Optimization (GRPO) applies one- or multi-hop refinements to explicitly minimize the property errors toward our target while regulating edit complexity and deviation from the prototype. A large, automatically curated dataset with reasoning chains of fragment edits and measured property deltas underpins both stages, enabling deterministic, reproducible supervision and controllable multi-hop reasoning. Unlike prior work, our framework better reasons about molecules by leveraging fragments and supports controllable refinement toward numeric targets. Experiments on generation under two sets of property constraints (QED, LogP, Molecular Weight and HOMO, LUMO) show consistent gains in validity and precise satisfaction of multi-property targets, outperforming strong LLMs and graph-based algorithms.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10131</guid>
|
||
<pubDate>Thu, 15 Jan 2026 07:18:05 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback</title>
|
||
<link>https://arxiv.org/abs/2601.10156</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10156.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yutao Mou, Zhangchi Xue, Lijun Li, Peiyang Liu, Shikun Zhang, Wei Ye, Jing Shao</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation behaviors in real time and proactively intervening before unsafe execution is critical for agent deployment, yet remains under-explored. In this work, we first construct TS-Bench, a novel benchmark for step-level tool invocation safety detection in LLM agents. We then develop a guardrail model, TS-Guard, using multi-task reinforcement learning. The model proactively detects unsafe tool invocation actions before execution by reasoning over the interaction history. It assesses request harmfulness and action-attack correlations, producing interpretable and generalizable safety judgments and feedback. Furthermore, we introduce TS-Flow, a guardrail-feedback-driven reasoning framework for LLM agents, which reduces harmful tool invocations of ReAct-style agents by 65 percent on average and improves benign task completion by approximately 10 percent under prompt injection attacks.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10156</guid>
|
||
<pubDate>Thu, 15 Jan 2026 07:54:32 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>PRL: Process Reward Learning Improves LLMs' Reasoning Ability and Broadens the Reasoning Boundary</title>
|
||
<link>https://arxiv.org/abs/2601.10201</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10201.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiarui Yao, Ruida Wang, Tong Zhang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Improving the reasoning abilities of Large Language Models (LLMs) has been a continuous topic recently. But most relevant works are based on outcome rewards at the trajectory level, missing fine-grained supervision during the reasoning process. Other existing training frameworks that try to combine process signals together to optimize LLMs also rely heavily on tedious additional steps like MCTS, training a separate reward model, etc., doing harm to the training efficiency. Moreover, the intuition behind the process signals design lacks rigorous theoretical support, leaving the understanding of the optimization mechanism opaque. In this paper, we propose Process Reward Learning (PRL), which decomposes the entropy regularized reinforcement learning objective into intermediate steps, with rigorous process rewards that could be assigned to models accordingly. Starting from theoretical motivation, we derive the formulation of PRL that is essentially equivalent to the objective of reward maximization plus a KL-divergence penalty term between the policy model and a reference model. However, PRL could turn the outcome reward into process supervision signals, which helps better guide the exploration during RL optimization. From our experiment results, we demonstrate that PRL not only improves the average performance for LLMs' reasoning ability measured by average @ n, but also broadens the reasoning boundary by improving the pass @ n metric. Extensive experiments show the effectiveness of PRL could be verified and generalized.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10201</guid>
|
||
<pubDate>Thu, 15 Jan 2026 09:01:53 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset</title>
|
||
<link>https://arxiv.org/abs/2601.10305</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10305.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hengyu Shen, Tiancheng Gu, Bin Qin, Lan Wu, Yuling Wu, Shuo Tan, Zelong Sun, Jun Wang, Nan Wu, Xiang An, Weidong Cai, Ziyong Feng, Kaicheng Yang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Vision-Language Pre-training (VLP) models demonstrate strong performance across various downstream tasks by learning from large-scale image-text pairs through contrastive pretraining. The release of extensive English image-text datasets (e.g., COYO-700M and LAION-400M) has enabled widespread adoption of models such as CLIP and SigLIP in tasks including cross-modal retrieval and image captioning. However, the advancement of Chinese vision-language pretraining has substantially lagged behind, due to the scarcity of high-quality Chinese image-text data. To address this gap, we develop a comprehensive pipeline for constructing a high-quality Chinese cross-modal dataset. As a result, we propose DanQing, which contains 100 million image-text pairs collected from Common Crawl. Different from existing datasets, DanQing is curated through a more rigorous selection process, yielding superior data quality. Moreover, DanQing is primarily built from 2024-2025 web data, enabling models to better capture evolving semantic trends and thus offering greater practical utility. We compare DanQing with existing datasets by continual pre-training of the SigLIP2 model. Experimental results show that DanQing consistently achieves superior performance across a range of Chinese downstream tasks, including zero-shot classification, cross-modal retrieval, and LMM-based evaluations. To facilitate further research in Chinese vision-language pre-training, we will open-source the DanQing dataset under the Creative Common CC-BY 4.0 license.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10305</guid>
|
||
<pubDate>Thu, 15 Jan 2026 11:28:58 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders</title>
|
||
<link>https://arxiv.org/abs/2601.10332</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10332.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siqi Kou, Jiachun Jin, Zetong Zhou, Ye Ma, Yugang Wang, Quan Chen, Peng Jiang, Xiao Yang, Jun Zhu, Kai Yu, Zhijie Deng</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Recent progress in text-to-image (T2I) diffusion models (DMs) has enabled high-quality visual synthesis from diverse textual prompts. Yet, most existing T2I DMs, even those equipped with large language model (LLM)-based text encoders, remain text-pixel mappers -- they employ LLMs merely as text encoders, without leveraging their inherent reasoning capabilities to infer what should be visually depicted given the textual prompt. To move beyond such literal generation, we propose the think-then-generate (T2G) paradigm, where the LLM-based text encoder is encouraged to reason about and rewrite raw user prompts; the states of the rewritten prompts then serve as diffusion conditioning. To achieve this, we first activate the think-then-rewrite pattern of the LLM encoder with a lightweight supervised fine-tuning process. Subsequently, the LLM encoder and diffusion backbone are co-optimized to ensure faithful reasoning about the context and accurate rendering of the semantics via Dual-GRPO. In particular, the text encoder is reinforced using image-grounded rewards to infer and recall world knowledge, while the diffusion backbone is pushed to produce semantically consistent and visually coherent images. Experiments show substantial improvements in factual consistency, semantic alignment, and visual realism across reasoning-based image generation and editing benchmarks, achieving 0.79 on WISE score, nearly on par with GPT-4. Our results constitute a promising step toward next-generation unified models with reasoning, expression, and demonstration capacities.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10332</guid>
|
||
<pubDate>Thu, 15 Jan 2026 12:19:05 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering</title>
|
||
<link>https://arxiv.org/abs/2601.10402</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10402.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Zhu, Yuzhu Cai, Zexi Liu, Bingyang Zheng, Cheng Wang, Rui Ye, Jiaao Chen, Hanrui Wang, Wei-Chen Wang, Yuzhi Zhang, Linfeng Zhang, Weinan E, Di Jin, Siheng Chen</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic coherence and iterative correction over experimental cycles spanning days or weeks. While Large Language Models (LLMs) have demonstrated prowess in short-horizon reasoning, they are easily overwhelmed by execution details in the high-dimensional, delayed-feedback environments of real-world research, failing to consolidate sparse feedback into coherent long-term guidance. Here, we present ML-Master 2.0, an autonomous agent that masters ultra-long-horizon machine learning engineering (MLE) which is a representative microcosm of scientific discovery. By reframing context management as a process of cognitive accumulation, our approach introduces Hierarchical Cognitive Caching (HCC), a multi-tiered architecture inspired by computer systems that enables the structural differentiation of experience over time. By dynamically distilling transient execution traces into stable knowledge and cross-task wisdom, HCC allows agents to decouple immediate execution from long-term experimental strategy, effectively overcoming the scaling limits of static context windows. In evaluations on OpenAI's MLE-Bench under 24-hour budgets, ML-Master 2.0 achieves a state-of-the-art medal rate of 56.44%. Our findings demonstrate that ultra-long-horizon autonomy provides a scalable blueprint for AI capable of autonomous exploration beyond human-precedent complexities.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10402</guid>
|
||
<pubDate>Thu, 15 Jan 2026 13:52:04 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Urban Socio-Semantic Segmentation with Vision-Language Reasoning</title>
|
||
<link>https://arxiv.org/abs/2601.10477</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10477.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Wang, Yi Wang, Rui Dai, Yujie Wang, Kaikui Liu, Xiangxiang Chu, Yansheng Li</p><p><b>Upvotes:</b> 148</p><p><b>Summary:</b> As hubs of human activity, urban surfaces consist of a wealth of semantic entities. Segmenting these various entities from satellite imagery is crucial for a range of downstream applications. Current advanced segmentation models can reliably segment entities defined by physical attributes (e.g., buildings, water bodies) but still struggle with socially defined categories (e.g., schools, parks). In this work, we achieve socio-semantic segmentation by vision-language model reasoning. To facilitate this, we introduce the Urban Socio-Semantic Segmentation dataset named SocioSeg, a new resource comprising satellite imagery, digital maps, and pixel-level labels of social semantic entities organized in a hierarchical structure. Additionally, we propose a novel vision-language reasoning framework called SocioReasoner that simulates the human process of identifying and annotating social semantic entities via cross-modal recognition and multi-stage reasoning. We employ reinforcement learning to optimize this non-differentiable process and elicit the reasoning capabilities of the vision-language model. Experiments demonstrate our approach's gains over state-of-the-art models and strong zero-shot generalization. Our dataset and code are available in https://github.com/AMAP-ML/SocioReasoner.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10477</guid>
|
||
<pubDate>Thu, 15 Jan 2026 15:00:36 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5</title>
|
||
<link>https://arxiv.org/abs/2601.10527</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10527.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingjun Ma, Yixu Wang, Hengyuan Xu, Yutao Wu, Yifan Ding, Yunhan Zhao, Zilong Wang, Jiabin Hua, Ming Wen, Jianan Liu, Ranjie Duan, Yifeng Gao, Yingshui Tan, Yunhao Chen, Hui Xue, Xin Wang, Wei Cheng, Jingjing Chen, Zuxuan Wu, Bo Li, Yu-Gang Jiang</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> The rapid evolution of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has produced substantial gains in reasoning, perception, and generative capability across language and vision. However, whether these advances yield commensurate improvements in safety remains unclear, in part due to fragmented evaluation practices limited to single modalities or threat models. In this report, we present an integrated safety evaluation of 7 frontier models: GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5. We evaluate each model across language, vision-language, and image generation settings using a unified protocol that integrates benchmark evaluation, adversarial evaluation, multilingual evaluation, and compliance evaluation. Aggregating our evaluations into safety leaderboards and model safety profiles across multiple evaluation modes reveals a sharply heterogeneous safety landscape. While GPT-5.2 demonstrates consistently strong and balanced safety performance across evaluations, other models exhibit pronounced trade-offs among benchmark safety, adversarial alignment, multilingual generalization, and regulatory compliance. Both language and vision-language modalities show significant vulnerability under adversarial evaluation, with all models degrading substantially despite strong results on standard benchmarks. Text-to-image models achieve relatively stronger alignment in regulated visual risk categories, yet remain brittle under adversarial or semantically ambiguous prompts. Overall, these results show that safety in frontier models is inherently multidimensional--shaped by modality, language, and evaluation scheme, underscoring the need for standardized safety evaluations to accurately assess real-world risk and guide responsible model development and deployment.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10527</guid>
|
||
<pubDate>Thu, 15 Jan 2026 15:52:52 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>HeartMuLa: A Family of Open Sourced Music Foundation Models</title>
|
||
<link>https://arxiv.org/abs/2601.10547</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10547.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongchao Yang, Yuxin Xie, Yuguo Yin, Zheyu Wang, Xiaoyu Yi, Gongxi Zhu, Xiaolong Weng, Zihan Xiong, Yingzhe Ma, Dading Cong, Jingliang Liu, Zihang Huang, Jinghan Ru, Rongjie Huang, Haoran Wan, Peixu Wang, Kuoxi Yu, Helin Wang, Liming Liang, Xianwei Zhuang, Yuanyuan Wang, Haohan Guo, Junjie Cao, Zeqian Ju, Songxiang Liu, Yuewen Cao, Heming Weng, Yuexian Zou</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We present a family of open-source Music Foundation Models designed to advance large-scale music understanding and generation across diverse tasks and modalities. Our framework consists of four major components: (1) HeartCLAP, an audio-text alignment model; (2) HeartTranscriptor, a robust lyric recognition model optimized for real-world music scenarios; and (3) HeartCodec, a low-frame-rate (12.5 Hz) yet high-fidelity music codec tokenizer that captures long-range musical structure while preserving fine-grained acoustic details and enabling efficient autoregressive modeling; (4) HeartMuLa, an LLM-based song generation model capable of synthesizing high-fidelity music under rich, user-controllable conditions (e.g., textual style descriptions, lyrics, and reference audio). In addition, it provides two specialized modes: (i) fine-grained musical attribute control, which allows users to specify the style of different song sections (e.g., intro, verse, chorus) using natural language prompts; and (ii) short, engaging music generation, which is suitable as background music for short videos. Lastly, HeartMuLa improves significantly when scaled to 7B parameters. For the first time, we show that a Suno-level, commercial-grade system can be reproduced using academic-scale data and GPU resources. We expect these foundation models to serve as strong baselines for future research and to facilitate practical applications in multimodal content production.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10547</guid>
|
||
<pubDate>Thu, 15 Jan 2026 16:14:25 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Inference-time Physics Alignment of Video Generative Models with Latent World Models</title>
|
||
<link>https://arxiv.org/abs/2601.10553</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10553.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich, Nicolas Beltran-Velez, Melissa Hall, Reyhane Askari-Hemmat, Xiaochuang Han, Nicolas Ballas, Michal Drozdzal, Adriana Romero-Soriano</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> State-of-the-art video generative models produce promising visual content yet often violate basic physics principles, limiting their utility. While some attribute this deficiency to insufficient physics understanding from pre-training, we find that the shortfall in physics plausibility also stems from suboptimal inference strategies. We therefore introduce WMReward and treat improving physics plausibility of video generation as an inference-time alignment problem. In particular, we leverage the strong physics prior of a latent world model (here, VJEPA-2) as a reward to search and steer multiple candidate denoising trajectories, enabling scaling test-time compute for better generation performance. Empirically, our approach substantially improves physics plausibility across image-conditioned, multiframe-conditioned, and text-conditioned generation settings, with validation from human preference study. Notably, in the ICCV 2025 Perception Test PhysicsIQ Challenge, we achieve a final score of 62.64%, winning first place and outperforming the previous state of the art by 7.42%. Our work demonstrates the viability of using latent world models to improve physics plausibility of video generation, beyond this specific instantiation or parameterization.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10553</guid>
|
||
<pubDate>Thu, 15 Jan 2026 16:18:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Action100M: A Large-scale Video Action Dataset</title>
|
||
<link>https://arxiv.org/abs/2601.10592</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Delong Chen, Tejaswi Kasarla, Yejin Bang, Mustafa Shukor, Willy Chung, Jade Yu, Allen Bolourchi, Theo Moutakanni, Pascale Fung</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Inferring physical actions from visual observations is a fundamental capability for advancing machine intelligence in the physical world. Achieving this requires large-scale, open-vocabulary video action datasets that span broad domains. We introduce Action100M, a large-scale dataset constructed from 1.2M Internet instructional videos (14.6 years of duration), yielding O(100 million) temporally localized segments with open-vocabulary action supervision and rich captions. Action100M is generated by a fully automated pipeline that (i) performs hierarchical temporal segmentation using V-JEPA 2 embeddings, (ii) produces multi-level frame and segment captions organized as a Tree-of-Captions, and (iii) aggregates evidence with a reasoning model (GPT-OSS-120B) under a multi-round Self-Refine procedure to output structured annotations (brief/detailed action, actor, brief/detailed caption). Training VL-JEPA on Action100M demonstrates consistent data-scaling improvements and strong zero-shot performance across diverse action recognition benchmarks, establishing Action100M as a new foundation for scalable research in video understanding and world modeling.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10592</guid>
|
||
<pubDate>Thu, 15 Jan 2026 17:02:27 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding</title>
|
||
<link>https://arxiv.org/abs/2601.10611</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Christopher Clark, Jieyu Zhang, Zixian Ma, Jae Sung Park, Mohammadreza Salehi, Rohun Tripathi, Sangho Lee, Zhongzheng Ren, Chris Dongjoo Kim, Yinuo Yang, Vincent Shao, Yue Yang, Weikai Huang, Ziqi Gao, Taira Anderson, Jianrui Zhang, Jitesh Jain, George Stoica, Winson Han, Ali Farhadi, Ranjay Krishna</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from them, or do not disclose their training data or recipe. As a result, the open-source community lacks the foundations needed to improve on the state-of-the-art video (and image) language models. Crucially, many downstream applications require more than just high-level video understanding; they require grounding -- either by pointing or by tracking in pixels. Even proprietary models lack this capability. We present Molmo2, a new family of VLMs that are state-of-the-art among open-source models and demonstrate exceptional new capabilities in point-driven grounding in single image, multi-image, and video tasks. Our key contribution is a collection of 7 new video datasets and 2 multi-image datasets, including a dataset of highly detailed video captions for pre-training, a free-form video Q&A dataset for fine-tuning, a new object tracking dataset with complex queries, and an innovative new video pointing dataset, all collected without the use of closed VLMs. We also present a training recipe for this data utilizing an efficient packing and message-tree encoding scheme, and show bi-directional attention on vision tokens and a novel token-weight strategy improves performance. Our best-in-class 8B model outperforms others in the class of open weight and data models on short videos, counting, and captioning, and is competitive on long-videos. On video-grounding Molmo2 significantly outperforms existing open-weight models like Qwen3-VL (35.5 vs 29.6 accuracy on video counting) and surpasses proprietary models like Gemini 3 Pro on some tasks (38.4 vs 20.0 F1 on video pointing and 56.2 vs 41.1 J&F on video tracking).</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10611</guid>
|
||
<pubDate>Thu, 15 Jan 2026 17:27:44 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution</title>
|
||
<link>https://arxiv.org/abs/2601.10657</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10657.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minghao Yan, Bo Peng, Benjamin Coleman, Ziqi Chen, Zhouhang Xie, Zhankui He, Noveen Sachdeva, Isabella Ye, Weili Wang, Chi Wang, Ed H. Chi, Wang-Cheng Kang, Derek Zhiyuan Cheng, Beidou Wang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Large Language Models (LLMs) have emerged as powerful operators for evolutionary search, yet the design of efficient search scaffolds remains ad hoc. While promising, current LLM-in-the-loop systems lack a systematic approach to managing the evolutionary process. We identify three distinct failure modes: Context Pollution, where experiment history biases future candidate generation; Mode Collapse, where agents stagnate in local minima due to poor exploration-exploitation balance; and Weak Collaboration, where rigid crossover strategies fail to leverage parallel search trajectories effectively. We introduce Progress-Aware Consistent Evolution (PACEvolve), a framework designed to robustly govern the agent's context and search dynamics, to address these challenges. PACEvolve combines hierarchical context management (HCM) with pruning to address context pollution; momentum-based backtracking (MBB) to escape local minima; and a self-adaptive sampling policy that unifies backtracking and crossover for dynamic search coordination (CE), allowing agents to balance internal refinement with cross-trajectory collaboration. We demonstrate that PACEvolve provides a systematic path to consistent, long-horizon self-improvement, achieving state-of-the-art results on LLM-SR and KernelBench, while discovering solutions surpassing the record on Modded NanoGPT.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10657</guid>
|
||
<pubDate>Thu, 15 Jan 2026 18:25:23 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching</title>
|
||
<link>https://arxiv.org/abs/2601.10712</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10712.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Changle Qu, Sunhao Dai, Hengyi Cai, Jun Xu, Shuaiqiang Wang, Dawei Yin</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Tool-Integrated Reasoning (TIR) empowers large language models (LLMs) to tackle complex tasks by interleaving reasoning steps with external tool interactions. However, existing reinforcement learning methods typically rely on outcome- or trajectory-level rewards, assigning uniform advantages to all steps within a trajectory. This coarse-grained credit assignment fails to distinguish effective tool calls from redundant or erroneous ones, particularly in long-horizon multi-turn scenarios. To address this, we propose MatchTIR, a framework that introduces fine-grained supervision via bipartite matching-based turn-level reward assignment and dual-level advantage estimation. Specifically, we formulate credit assignment as a bipartite matching problem between predicted and ground-truth traces, utilizing two assignment strategies to derive dense turn-level rewards. Furthermore, to balance local step precision with global task success, we introduce a dual-level advantage estimation scheme that integrates turn-level and trajectory-level signals, assigning distinct advantage values to individual interaction turns. Extensive experiments on three benchmarks demonstrate the superiority of MatchTIR. Notably, our 4B model surpasses the majority of 8B competitors, particularly in long-horizon and multi-turn tasks. Our codes are available at https://github.com/quchangle1/MatchTIR.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10712</guid>
|
||
<pubDate>Thu, 15 Jan 2026 18:59:23 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Alterbute: Editing Intrinsic Attributes of Objects in Images</title>
|
||
<link>https://arxiv.org/abs/2601.10714</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10714.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tal Reiss, Daniel Winter, Matan Cohen, Alex Rav-Acha, Yael Pritch, Ariel Shamir, Yedid Hoshen</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> We introduce Alterbute, a diffusion-based method for editing an object's intrinsic attributes in an image. We allow changing color, texture, material, and even the shape of an object, while preserving its perceived identity and scene context. Existing approaches either rely on unsupervised priors that often fail to preserve identity or use overly restrictive supervision that prevents meaningful intrinsic variations. Our method relies on: (i) a relaxed training objective that allows the model to change both intrinsic and extrinsic attributes conditioned on an identity reference image, a textual prompt describing the target intrinsic attributes, and a background image and object mask defining the extrinsic context. At inference, we restrict extrinsic changes by reusing the original background and object mask, thereby ensuring that only the desired intrinsic attributes are altered; (ii) Visual Named Entities (VNEs) - fine-grained visual identity categories (e.g., ''Porsche 911 Carrera'') that group objects sharing identity-defining features while allowing variation in intrinsic attributes. We use a vision-language model to automatically extract VNE labels and intrinsic attribute descriptions from a large public image dataset, enabling scalable, identity-preserving supervision. Alterbute outperforms existing methods on identity-preserving object intrinsic attribute editing.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2601.10714</guid>
|
||
<pubDate>Thu, 15 Jan 2026 18:59:53 +0000</pubDate>
|
||
</item>
|
||
</channel>
|
||
</rss>
|