From ac650d93e181297a5b0e522f6edbca2d8e2bfa6a Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Fri, 13 Feb 2026 00:05:51 +0000 Subject: [PATCH] bot: update RSS feed --- feed.xml | 615 ++++++++++++++++++++++++------------------------------- 1 file changed, 269 insertions(+), 346 deletions(-) diff --git a/feed.xml b/feed.xml index 4c2a2e6..c1b0f49 100644 --- a/feed.xml +++ b/feed.xml @@ -7,398 +7,321 @@ http://www.rssboard.org/rss-specification python-feedgen en - Thu, 12 Feb 2026 00:04:23 +0000 + Fri, 13 Feb 2026 00:05:51 +0000 - SHARP: Social Harm Analysis via Risk Profiles for Measuring Inequities in Large Language Models - https://arxiv.org/abs/2601.21235 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.21235.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alok Abhishek, Tushar Bandopadhyay, Lisa Erickson</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large language models (LLMs) are increasingly deployed in high-stakes domains, where rare but severe failures can result in irreversible harm. However, prevailing evaluation benchmarks often reduce complex social risk to mean-centered scalar scores, thereby obscuring distributional structure, cross-dimensional interactions, and worst-case behavior. This paper introduces Social Harm Analysis via Risk Profiles (SHARP), a framework for multidimensional, distribution-aware evaluation of social harm. SHARP models harm as a multivariate random variable and integrates explicit decomposition into bias, fairness, ethics, and epistemic reliability with a union-of-failures aggregation reparameterized as additive cumulative log-risk. The framework further employs risk-sensitive distributional statistics, with Conditional Value at Risk (CVaR95) as a primary metric, to characterize worst-case model behavior. Application of SHARP to eleven frontier LLMs, evaluated on a fixed corpus of n=901 socially sensitive prompts, reveals that models with similar average risk can exhibit more than twofold differences in tail exposure and volatility. Across models, dimension-wise marginal tail behavior varies systematically across harm dimensions, with bias exhibiting the strongest tail severities, epistemic and fairness risks occupying intermediate regimes, and ethical misalignment consistently lower; together, these patterns reveal heterogeneous, model-dependent failure structures that scalar benchmarks conflate. These findings indicate that responsible evaluation and governance of LLMs require moving beyond scalar averages toward multidimensional, tail-sensitive risk profiling.</p> - https://arxiv.org/abs/2601.21235 - Thu, 29 Jan 2026 03:54:25 +0000 + ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning + https://arxiv.org/abs/2602.02192 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02192.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Xiao, Meng Chen, Qingnan Ren, Jingwei Song, Jiaqi Huang, Yangshen Deng, Chris Tong, Wanyi Chen, Suli Wang, Ziqian Bi, Shuo Lu, Yiqun Duan, Xu Wang, Rymon Yu, Ween Yang, Lynn Ai, Eric Yang, Bill Shi, Song Jingwei</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Reinforcement learning (RL) is a critical stage in post-training large language models (LLMs), involving repeated interaction between rollout generation, reward evaluation, and centralized learning. Distributing rollout execution offers opportunities to leverage more cost-efficient inference resources, but introduces challenges in wide-area coordination and policy dissemination. We present ECHO-2, a distributed RL framework for post-training with remote inference workers and non-negligible dissemination latency. ECHO-2 combines centralized learning with distributed rollouts and treats bounded policy staleness as a user-controlled parameter, enabling rollout generation, dissemination, and training to overlap. We introduce an overlap-based capacity model that relates training time, dissemination latency, and rollout throughput, yielding a practical provisioning rule for sustaining learner utilization. To mitigate dissemination bottlenecks and lower cost, ECHO-2 employs peer-assisted pipelined broadcast and cost-aware activation of heterogeneous workers. Experiments on GRPO post-training of 4B and 8B models under real wide-area bandwidth regimes show that ECHO-2 significantly improves cost efficiency while preserving RL reward comparable to strong baselines.</p> + https://arxiv.org/abs/2602.02192 + Mon, 02 Feb 2026 14:57:53 +0000 - TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation - https://arxiv.org/abs/2602.00268 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ariel Shaulov, Eitan Shaar, Amit Edenzon, Lior Wolf</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Auto-regressive video generation enables long video synthesis by iteratively conditioning each new batch of frames on previously generated content. However, recent work has shown that such pipelines suffer from severe temporal drift, where errors accumulate and amplify over long horizons. We hypothesize that this drift does not primarily stem from insufficient model capacity, but rather from inference-time error propagation. Specifically, we contend that drift arises from the uncontrolled reuse of corrupted latent conditioning tokens during auto-regressive inference. To correct this accumulation of errors, we propose a simple, inference-time method that mitigates temporal drift by identifying and removing unstable latent tokens before they are reused for conditioning. For this purpose, we define unstable tokens as latent tokens whose representations deviate significantly from those of the previously generated batch, indicating potential corruption or semantic drift. By explicitly removing corrupted latent tokens from the auto-regressive context, rather than modifying entire spatial regions or model parameters, our method prevents unreliable latent information from influencing future generation steps. As a result, it significantly improves long-horizon temporal consistency without modifying the model architecture, training procedure, or leaving latent space.</p> - https://arxiv.org/abs/2602.00268 - Fri, 30 Jan 2026 19:44:16 +0000 + TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments + https://arxiv.org/abs/2602.02459 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02459.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyu Huang, Yun Zhang, Johnson Liu, Rui Song, Chen Tang, Jiaqi Ma</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Robots in dynamic, human-centric environments must follow language instructions while maintaining real-time reactive control. Vision-language-action (VLA) models offer a promising framework, but they assume temporally aligned reasoning and control, despite semantic inference being inherently delayed relative to real-time action. We introduce Think-in-Control (TIC)-VLA, a latency-aware framework that explicitly models delayed semantic reasoning during action generation. TIC-VLA defines a delayed semantic-control interface that conditions action generation on delayed vision-language semantic states and explicit latency metadata, in addition to current observations, enabling policies to compensate for asynchronous reasoning. We further propose a latency-consistent training pipeline that injects reasoning inference delays during imitation learning and online reinforcement learning, aligning training with asynchronous deployment. To support realistic evaluation, we present DynaNav, a physics-accurate, photo-realistic simulation suite for language-guided navigation in dynamic environments. Extensive experiments in simulation and on a real robot show that TIC-VLA consistently outperforms prior VLA models while maintaining robust real-time control under multi-second reasoning latency. Project website: https://ucla-mobility.github.io/TIC-VLA/</p> + https://arxiv.org/abs/2602.02459 + Mon, 02 Feb 2026 18:47:49 +0000 - LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs - https://arxiv.org/abs/2602.00462 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00462.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Benno Krojer, Shravan Nayak, Oscar Mañas, Vaibhav Adlakha, Desmond Elliott, Siva Reddy, Marius Mosbach</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Transforming a large language model (LLM) into a Vision-Language Model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP transformation. To understand why LLMs can so readily process visual tokens, we need interpretability methods that reveal what is encoded in the visual token representations at every layer of LLM processing. In this work, we introduce LatentLens, a novel approach for mapping latent representations to descriptions in natural language. LatentLens works by encoding a large text corpus and storing contextualized token representations for each token in that corpus. Visual token representations are then compared to their contextualized textual representations, with the top-k nearest neighbor representations providing descriptions of the visual token. We evaluate this method on 10 different VLMs, showing that commonly used methods, such as LogitLens, substantially underestimate the interpretability of visual tokens. With LatentLens instead, the majority of visual tokens are interpretable across all studied models and all layers. Qualitatively, we show that the descriptions produced by LatentLens are semantically meaningful and provide more fine-grained interpretations for humans compared to individual tokens. More broadly, our findings contribute new evidence on the alignment between vision and language representations, opening up new directions for analyzing latent representations.</p> - https://arxiv.org/abs/2602.00462 - Sat, 31 Jan 2026 02:33:07 +0000 + Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL + https://arxiv.org/abs/2602.03773 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03773.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ian Wu, Yuxiao Qu, Amrith Setlur, Aviral Kumar</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs) that can continually improve beyond their training budgets are able to solve increasingly difficult problems by adapting at test time, a property we refer to as extrapolation. However, standard reinforcement learning (RL) operates over fixed problem distributions and training budgets, which limits extrapolation amidst distribution shift at test time. To address this, we introduce RC, an iterative decoding algorithm that replaces standard autoregressive decoding during both training and inference. RC exploits an asymmetry between the response generation and summarization capabilities of LLMs to construct reasoning chains that consistently improve across iterations. Models trained to use RC can extrapolate and continually improve over reasoning horizons more than an order of magnitude longer than those seen during training. Empirically, training a 4B model with RC using a 16k-token training budget improves performance on HMMT 2025 from 40% to nearly 70% with 0.5m tokens at test time, outperforming both comparably sized models and many larger reasoning LLMs. Finally, we also show that models trained with RC can more effectively leverage existing scaffolds to further scale test-time performance, due to the improved summary-conditioned generation abilities learned through training.</p> + https://arxiv.org/abs/2602.03773 + Tue, 03 Feb 2026 17:34:04 +0000 - Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments - https://arxiv.org/abs/2602.01244 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01244.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siwei Wu, Yizhi Li, Yuyang Song, Wei Zhang, Yang Wang, Riza Batista-Navarro, Xian Yang, Mingjie Tang, Bryan Dai, Jian Yang, Chenghua Lin</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Training agentic models for terminal-based tasks critically depends on high-quality terminal trajectories that capture realistic long-horizon interactions across diverse domains. However, constructing such data at scale remains challenging due to two key requirements: \emph{Executability}, since each instance requires a suitable and often distinct Docker environment; and \emph{Verifiability}, because heterogeneous task outputs preclude unified, standardized verification. To address these challenges, we propose TerminalTraj, a scalable pipeline that (i) filters high-quality repositories to construct Dockerized execution environments, (ii) generates Docker-aligned task instances, and (iii) synthesizes agent trajectories with executable validation code. Using TerminalTraj, we curate 32K Docker images and generate 50,733 verified terminal trajectories across eight domains. Models trained on this data with the Qwen2.5-Coder backbone achieve consistent performance improvements on TerminalBench (TB), with gains of up to 20\% on TB~1.0 and 10\% on TB~2.0 over their respective backbones. Notably, TerminalTraj-32B achieves strong performance among models with fewer than 100B parameters, reaching 35.30\% on TB~1.0 and 22.00\% on TB~2.0, and demonstrates improved test-time scaling behavior. All code and data are available at https://github.com/Wusiwei0410/TerminalTraj.</p> - https://arxiv.org/abs/2602.01244 - Sun, 01 Feb 2026 14:09:23 +0000 + ASA: Training-Free Representation Engineering for Tool-Calling Agents + https://arxiv.org/abs/2602.04935 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.04935.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youjin Wang, Run Zhou, Rong Fu, Shuaishuai Cao, Hongwei Zeng, Jiaxuan Lu, Sicheng Fan, Jiaqiao Zhao, Liangming Pan</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy to deploy but often fragile under distribution shift and strict parsers, while continual parameter-efficient fine-tuning improves reliability at the cost of training, maintenance, and potential forgetting. We identify a critical Lazy Agent failure mode where tool necessity is nearly perfectly decodable from mid-layer activations, yet the model remains conservative in entering tool mode, revealing a representation-behavior gap. We propose Activation Steering Adapter (ASA), a training-free, inference-time controller that performs a single-shot mid-layer intervention and targets tool domains via a router-conditioned mixture of steering vectors with a probe-guided signed gate to amplify true intent while suppressing spurious triggers. On MTU-Bench with Qwen2.5-1.5B, ASA improves strict tool-use F1 from 0.18 to 0.50 while reducing the false positive rate from 0.15 to 0.05, using only about 20KB of portable assets and no weight updates.</p> + https://arxiv.org/abs/2602.04935 + Wed, 04 Feb 2026 14:20:02 +0000 - SafePred: A Predictive Guardrail for Computer-Using Agents via World Models - https://arxiv.org/abs/2602.01725 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01725.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yurun Chen, Zeyi Liao, Ping Yin, Taotao Xie, Keting Yin, Shengyu Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> With the widespread deployment of Computer-using Agents (CUAs) in complex real-world environments, prevalent long-term risks often lead to severe and irreversible consequences. Most existing guardrails for CUAs adopt a reactive approach, constraining agent behavior only within the current observation space. While these guardrails can prevent immediate short-term risks (e.g., clicking on a phishing link), they cannot proactively avoid long-term risks: seemingly reasonable actions can lead to high-risk consequences that emerge with a delay (e.g., cleaning logs leads to future audits being untraceable), which reactive guardrails cannot identify within the current observation space. To address these limitations, we propose a predictive guardrail approach, with the core idea of aligning predicted future risks with current decisions. Based on this approach, we present SafePred, a predictive guardrail framework for CUAs that establishes a risk-to-decision loop to ensure safe agent behavior. SafePred supports two key abilities: (1) Short- and long-term risk prediction: by using safety policies as the basis for risk prediction, SafePred leverages the prediction capability of the world model to generate semantic representations of both short-term and long-term risks, thereby identifying and pruning actions that lead to high-risk states; (2) Decision optimization: translating predicted risks into actionable safe decision guidances through step-level interventions and task-level re-planning. Extensive experiments show that SafePred significantly reduces high-risk behaviors, achieving over 97.6% safety performance and improving task utility by up to 21.4% compared with reactive baselines.</p> - https://arxiv.org/abs/2602.01725 - Mon, 02 Feb 2026 07:04:06 +0000 + AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions + https://arxiv.org/abs/2602.06008 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xianyang Liu, Shangding Gu, Dawn Song</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large language model (LLM)-based agents are increasingly expected to negotiate, coordinate, and transact autonomously, yet existing benchmarks lack principled settings for evaluating language-mediated economic interaction among multiple agents. We introduce AgenticPay, a benchmark and simulation framework for multi-agent buyer-seller negotiation driven by natural language. AgenticPay models markets in which buyers and sellers possess private constraints and product-dependent valuations, and must reach agreements through multi-round linguistic negotiation rather than numeric bidding alone. The framework supports a diverse suite of over 110 tasks ranging from bilateral bargaining to many-to-many markets, with structured action extraction and metrics for feasibility, efficiency, and welfare. Benchmarking state-of-the-art proprietary and open-weight LLMs reveals substantial gaps in negotiation performance and highlights challenges in long-horizon strategic reasoning, establishing AgenticPay as a foundation for studying agentic commerce and language-based market interaction. Code and dataset are available at the link: https://github.com/SafeRL-Lab/AgenticPay.</p> + https://arxiv.org/abs/2602.06008 + Thu, 05 Feb 2026 18:50:36 +0000 - Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss - https://arxiv.org/abs/2602.07022 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07022.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yucheng Zhou, Hao Li, Jianbing Shen</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Recent studies have explored autoregressive models for image generation, with promising results, and have combined diffusion models with autoregressive frameworks to optimize image generation via diffusion losses. In this study, we present a theoretical analysis of diffusion and autoregressive models with diffusion loss, highlighting the latter's advantages. We present a theoretical comparison of conditional diffusion and autoregressive diffusion with diffusion loss, demonstrating that patch denoising optimization in autoregressive models effectively mitigates condition errors and leads to a stable condition distribution. Our analysis also reveals that autoregressive condition generation refines the condition, causing the condition error influence to decay exponentially. In addition, we introduce a novel condition refinement approach based on Optimal Transport (OT) theory to address ``condition inconsistency''. We theoretically demonstrate that formulating condition refinement as a Wasserstein Gradient Flow ensures convergence toward the ideal condition distribution, effectively mitigating condition inconsistency. Experiments demonstrate the superiority of our method over diffusion and autoregressive models with diffusion loss methods.</p> - https://arxiv.org/abs/2602.07022 - Mon, 02 Feb 2026 07:48:04 +0000 + Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models + https://arxiv.org/abs/2602.07106 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Zhang, Zhipeng Li, Yiwen Guo, Tianshu Yu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Omni-modal large language models (OLLMs) aim to unify multimodal understanding and generation, yet incorporating speech with 3D facial animation remains largely unexplored despite its importance for natural interaction. A key challenge arises from the representation mismatch between discrete, token-level semantic reasoning in LLMs and the dense, fine-grained temporal dynamics required for 3D facial motion, which makes direct modeling difficult to optimize under limited data. We propose Expressive Omni (Ex-Omni), an open-source omni-modal framework that augments OLLMs with speech-accompanied 3D facial animation. Ex-Omni reduces learning difficulty by decoupling semantic reasoning from temporal generation, leveraging speech units as temporal scaffolding and a unified token-as-query gated fusion (TQGF) mechanism for controlled semantic injection. We further introduce InstructEx, a dataset aims to facilitate augment OLLMs with speech-accompanied 3D facial animation. Extensive experiments demonstrate that Ex-Omni performs competitively against existing open-source OLLMs while enabling stable aligned speech and facial animation generation.</p> + https://arxiv.org/abs/2602.07106 + Fri, 06 Feb 2026 18:03:30 +0000 - From Directions to Regions: Decomposing Activations in Language Models via Local Geometry - https://arxiv.org/abs/2602.02464 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02464.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Or Shafran, Shaked Ronen, Omri Fahn, Shauli Ravfogel, Atticus Geiger, Mor Geva</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Activation decomposition methods in language models are tightly coupled to geometric assumptions on how concepts are realized in activation space. Existing approaches search for individual global directions, implicitly assuming linear separability, which overlooks concepts with nonlinear or multi-dimensional structure. In this work, we leverage Mixture of Factor Analyzers (MFA) as a scalable, unsupervised alternative that models the activation space as a collection of Gaussian regions with their local covariance structure. MFA decomposes activations into two compositional geometric objects: the region's centroid in activation space, and the local variation from the centroid. We train large-scale MFAs for Llama-3.1-8B and Gemma-2-2B, and show they capture complex, nonlinear structures in activation space. Moreover, evaluations on localization and steering benchmarks show that MFA outperforms unsupervised baselines, is competitive with supervised localization methods, and often achieves stronger steering performance than sparse autoencoders. Together, our findings position local geometry, expressed through subspaces, as a promising unit of analysis for scalable concept discovery and model control, accounting for complex structures that isolated directions fail to capture.</p> - https://arxiv.org/abs/2602.02464 - Mon, 02 Feb 2026 18:49:05 +0000 + Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents + https://arxiv.org/abs/2602.07900 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07900.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhi Chen, Zhensu Sun, Yuling Shi, Chao Peng, Xiaodong Gu, David Lo, Lingxiao Jiang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Language Model (LLM) code agents increasingly resolve repository-level issues by iteratively editing code, invoking tools, and validating candidate patches. In these workflows, agents often write tests on the fly, a paradigm adopted by many high-ranking agents on the SWE-bench leaderboard. However, we observe that GPT-5.2, which writes almost no new tests, can even achieve performance comparable to top-ranking agents. This raises the critical question: whether such tests meaningfully improve issue resolution or merely mimic human testing practices while consuming a substantial interaction budget. To reveal the impact of agent-written tests, we present an empirical study that analyzes agent trajectories across six state-of-the-art LLMs on SWE-bench Verified. Our results show that while test writing is commonly adopted, but resolved and unresolved tasks within the same model exhibit similar test-writing frequencies Furthermore, these tests typically serve as observational feedback channels, where agents prefer value-revealing print statements significantly more than formal assertion-based checks. Based on these insights, we perform a controlled experiment by revising the prompts of four agents to either increase or reduce test writing. The results suggest that changes in the volume of agent-written tests do not significantly change final outcomes. Taken together, our study reveals that current test-writing practices may provide marginal utility in autonomous software engineering tasks.</p> + https://arxiv.org/abs/2602.07900 + Sun, 08 Feb 2026 10:26:31 +0000 - DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents - https://arxiv.org/abs/2602.07035 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07035.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Zhao, Shaoxuan Xu, Zhongxiang Sun, Fengqi Zhu, Jingyang Ou, Yuling Shi, Chongxuan Li, Xiao Zhang, Jun Xu</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Recently, Diffusion Large Language Models (dLLMs) have demonstrated unique efficiency advantages, enabled by their inherently parallel decoding mechanism and flexible generation paradigm. Meanwhile, despite the rapid advancement of Search Agents, their practical deployment is constrained by a fundamental limitation, termed as 1) Latency Challenge: the serial execution of multi-round reasoning, tool calling, and tool response waiting under the ReAct agent paradigm induces severe end-to-end latency. Intuitively, dLLMs can leverage their distinctive strengths to optimize the operational efficiency of agents under the ReAct agent paradigm. Practically, existing dLLM backbones face the 2) Agent Ability Challenge. That is, existing dLLMs exhibit remarkably weak reasoning and tool-calling capabilities, preventing these advantages from being effectively realized in practice. In this paper, we propose DLLM-Searcher, an optimization framework for dLLM-based Search Agents. To solve the Agent Ability Challenge, we design a two-stage post-training pipeline encompassing Agentic Supervised Fine-Tuning (Agentic SFT) and Agentic Variance-Reduced Preference Optimization Agentic VRPO, which enhances the backbone dLLM's information seeking and reasoning capabilities. To mitigate the Latency Challenge, we leverage the flexible generation mechanism of dLLMs and propose a novel agent paradigm termed Parallel-Reasoning and Acting P-ReAct. P-ReAct guides the model to prioritize decoding tool_call instructions, thereby allowing the model to keep thinking while waiting for the tool's return. Experimental results demonstrate that DLLM-Searcher achieves performance comparable to mainstream LLM-based search agents and P-ReAct delivers approximately 15% inference acceleration. Our code is available at https://anonymous.4open.science/r/DLLM-Searcher-553C</p> - https://arxiv.org/abs/2602.07035 - Tue, 03 Feb 2026 09:12:08 +0000 + Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation + https://arxiv.org/abs/2602.07954 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07954.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Krzysztof Wróbel, Jan Maria Kowalski, Jerzy Surma, Igor Ciuciura, Maciej Szymański</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> As Large Language Models (LLMs) become increasingly deployed in Polish language applications, the need for efficient and accurate content safety classifiers has become paramount. We present Bielik Guard, a family of compact Polish language safety classifiers comprising two model variants: a 0.1B parameter model based on MMLW-RoBERTa-base and a 0.5B parameter model based on PKOBP/polish-roberta-8k. Fine-tuned on a community-annotated dataset of 6,885 Polish texts, these models classify content across five safety categories: Hate/Aggression, Vulgarities, Sexual Content, Crime, and Self-Harm. Our evaluation demonstrates that both models achieve strong performance on multiple benchmarks. The 0.5B variant offers the best overall discrimination capability with F1 scores of 0.791 (micro) and 0.785 (macro) on the test set, while the 0.1B variant demonstrates exceptional efficiency. Notably, Bielik Guard 0.1B v1.1 achieves superior precision (77.65%) and very low false positive rate (0.63%) on real user prompts, outperforming HerBERT-PL-Guard (31.55% precision, 4.70% FPR) despite identical model size. The models are publicly available and designed to provide appropriate responses rather than simple content blocking, particularly for sensitive categories like self-harm.</p> + https://arxiv.org/abs/2602.07954 + Sun, 08 Feb 2026 12:57:04 +0000 - Temporal Pair Consistency for Variance-Reduced Flow Matching - https://arxiv.org/abs/2602.04908 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.04908.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chika Maduabuchi, Jindong Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Continuous-time generative models, such as diffusion models, flow matching, and rectified flow, learn time-dependent vector fields but are typically trained with objectives that treat timesteps independently, leading to high estimator variance and inefficient sampling. Prior approaches mitigate this via explicit smoothness penalties, trajectory regularization, or modified probability paths and solvers. We introduce Temporal Pair Consistency (TPC), a lightweight variance-reduction principle that couples velocity predictions at paired timesteps along the same probability path, operating entirely at the estimator level without modifying the model architecture, probability path, or solver. We provide a theoretical analysis showing that TPC induces a quadratic, trajectory-coupled regularization that provably reduces gradient variance while preserving the underlying flow-matching objective. Instantiated within flow matching, TPC improves sample quality and efficiency across CIFAR-10 and ImageNet at multiple resolutions, achieving lower FID at identical or lower computational cost than prior methods, and extends seamlessly to modern SOTA-style pipelines with noise-augmented training, score-based denoising, and rectified flow.</p> - https://arxiv.org/abs/2602.04908 - Wed, 04 Feb 2026 00:05:21 +0000 + Free(): Learning to Forget in Malloc-Only Reasoning Models + https://arxiv.org/abs/2602.08030 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08030.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yilun Zheng, Dongyang Ma, Tian Liang, Jiahao Xu, Xinting Huang, Lihui Chen, Haitao Mi, Yan Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reasoning models enhance problem-solving by scaling test-time compute, yet they face a critical paradox: excessive thinking tokens often degrade performance rather than improve it. We attribute this to a fundamental architectural flaw: standard LLMs operate as "malloc-only" engines, continuously accumulating valid and redundant steps alike without a mechanism to prune obsolete information. To break this cycle, we propose Free()LM, a model that introduces an intrinsic self-forgetting capability via the Free-Module, a plug-and-play LoRA adapter. By iteratively switching between reasoning and cleaning modes, Free()LM dynamically identifies and prunes useless context chunks, maintaining a compact and noise-free state. Extensive experiments show that Free()LM provides consistent improvements across all model scales (8B to 685B). It achieves a 3.3% average improvement over top-tier reasoning baselines, even establishing a new SOTA on IMOanswerBench using DeepSeek V3.2-Speciale. Most notably, in long-horizon tasks where the standard Qwen3-235B-A22B model suffers a total collapse (0% accuracy), Free()LM restores performance to 50%. Our findings suggest that sustainable intelligence requires the freedom to forget as much as the power to think.</p> + https://arxiv.org/abs/2602.08030 + Sun, 08 Feb 2026 16:04:23 +0000 - SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models - https://arxiv.org/abs/2602.04208 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.04208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyeonbeom Choi, Daechul Ahn, Youhan Lee, Taewook Kang, Seongwon Cho, Jonghyun Choi</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic control, with test-time scaling (TTS) gaining attention to enhance robustness beyond training. However, existing TTS methods for VLAs require additional training, verifiers, and multiple forward passes, making them impractical for deployment. Moreover, they intervene only at action decoding while keeping visual representations fixed-insufficient under perceptual ambiguity, where reconsidering how to perceive is as important as deciding what to do. To address these limitations, we propose SCALE, a simple inference strategy that jointly modulates visual perception and action based on 'self-uncertainty', inspired by uncertainty-driven exploration in Active Inference theory-requiring no additional training, no verifier, and only a single forward pass. SCALE broadens exploration in both perception and action under high uncertainty, while focusing on exploitation when confident-enabling adaptive execution across varying conditions. Experiments on simulated and real-world benchmarks demonstrate that SCALE improves state-of-the-art VLAs and outperforms existing TTS methods while maintaining single-pass efficiency.</p> - https://arxiv.org/abs/2602.04208 - Wed, 04 Feb 2026 04:48:16 +0000 + Graph-Enhanced Deep Reinforcement Learning for Multi-Objective Unrelated Parallel Machine Scheduling + https://arxiv.org/abs/2602.08052 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08052.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bulent Soykan, Sean Mondesire, Ghaith Rabadi, Grace Bochenek</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The Unrelated Parallel Machine Scheduling Problem (UPMSP) with release dates, setups, and eligibility constraints presents a significant multi-objective challenge. Traditional methods struggle to balance minimizing Total Weighted Tardiness (TWT) and Total Setup Time (TST). This paper proposes a Deep Reinforcement Learning framework using Proximal Policy Optimization (PPO) and a Graph Neural Network (GNN). The GNN effectively represents the complex state of jobs, machines, and setups, allowing the PPO agent to learn a direct scheduling policy. Guided by a multi-objective reward function, the agent simultaneously minimizes TWT and TST. Experimental results on benchmark instances demonstrate that our PPO-GNN agent significantly outperforms a standard dispatching rule and a metaheuristic, achieving a superior trade-off between both objectives. This provides a robust and scalable solution for complex manufacturing scheduling.</p> + https://arxiv.org/abs/2602.08052 + Sun, 08 Feb 2026 16:54:47 +0000 - C-ΔΘ: Circuit-Restricted Weight Arithmetic for Selective Refusal - https://arxiv.org/abs/2602.04521 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.04521.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aditya Kasliwal, Pratinav Seth, Vinay Kumar Sankarapu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Modern deployments require LLMs to enforce safety policies at scale, yet many controls rely on inference-time interventions that add recurring compute cost and serving complexity. Activation steering is widely used, but it requires runtime hooks and scales cost with the number of generations; conditional variants improve selectivity by gating when steering is applied but still retain an inference-time control path. We ask whether selective refusal can be moved entirely offline: can a mechanistic understanding of category-specific refusal be distilled into a circuit-restricted weight update that deploys as a standard checkpoint? We propose C-Δθ: Circuit Restricted Weight Arithmetic, which (i) localizes refusal-causal computation as a sparse circuit using EAP-IG and (ii) computes a constrained weight update ΔθC supported only on that circuit (typically <5% of parameters). Applying ΔθC yields a drop-in edited checkpoint with no inference-time hooks, shifting cost from per-request intervention to a one-time offline update. We evaluate category-targeted selectivity and capability retention on refusal and utility benchmarks.</p> - https://arxiv.org/abs/2602.04521 - Wed, 04 Feb 2026 13:10:52 +0000 + VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval + https://arxiv.org/abs/2602.08099 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08099.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Issar Tzachor, Dvir Samuel, Rami Ben-Ari</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Recent studies have adapted generative Multimodal Large Language Models (MLLMs) into embedding extractors for vision tasks, typically through fine-tuning to produce universal representations. However, their performance on video remains inferior to Video Foundation Models (VFMs). In this paper, we focus on leveraging MLLMs for video-text embedding and retrieval. We first conduct a systematic layer-wise analysis, showing that intermediate (pre-trained) MLLM layers already encode substantial task-relevant information. Leveraging this insight, we demonstrate that combining intermediate-layer embeddings with a calibrated MLLM head yields strong zero-shot retrieval performance without any training. Building on these findings, we introduce a lightweight text-based alignment strategy which maps dense video captions to short summaries and enables task-related video-text embedding learning without visual supervision. Remarkably, without any fine-tuning beyond text, our method outperforms current methods, often by a substantial margin, achieving state-of-the-art results across common video retrieval benchmarks.</p> + https://arxiv.org/abs/2602.08099 + Sun, 08 Feb 2026 19:39:32 +0000 - VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text? - https://arxiv.org/abs/2602.04802 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.04802.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qing'an Liu, Juntong Feng, Yuhao Wang, Xinzhe Han, Yujie Cheng, Yue Zhu, Haiwen Diao, Yunzhi Zhuge, Huchuan Lu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also frequently appears as visualized text embedded in images, raising the question of whether current VLMs handle such input requests comparably. We introduce VISTA-Bench, a systematic benchmark from multimodal perception, reasoning, to unimodal understanding domains. It evaluates visualized text understanding by contrasting pure-text and visualized-text questions under controlled rendering conditions. Extensive evaluation of over 20 representative VLMs reveals a pronounced modality gap: models that perform well on pure-text queries often degrade substantially when equivalent semantic content is presented as visualized text. This gap is further amplified by increased perceptual difficulty, highlighting sensitivity to rendering variations despite unchanged semantics. Overall, VISTA-Bench provides a principled evaluation framework to diagnose this limitation and to guide progress toward more unified language representations across tokenized text and pixels. The source dataset is available at https://github.com/QingAnLiu/VISTA-Bench.</p> - https://arxiv.org/abs/2602.04802 - Wed, 04 Feb 2026 17:48:55 +0000 + G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design + https://arxiv.org/abs/2602.08253 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08253.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baoyun Zhao, He Wang, Liang Zeng</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> While Large Language Models (LLMs) have recently shown promise in Automated Heuristic Design (AHD), existing approaches typically formulate AHD around constructive priority rules or parameterized local search guidance, thereby restricting the search space to fixed heuristic forms. Such designs offer limited capacity for structural exploration, making it difficult to escape deep local optima in complex Combinatorial Optimization Problems (COPs). In this work, we propose G-LNS, a generative evolutionary framework that extends LLM-based AHD to the automated design of Large Neighborhood Search (LNS) operators. Unlike prior methods that evolve heuristics in isolation, G-LNS leverages LLMs to co-evolve tightly coupled pairs of destroy and repair operators. A cooperative evaluation mechanism explicitly captures their interaction, enabling the discovery of complementary operator logic that jointly performs effective structural disruption and reconstruction. Extensive experiments on challenging COP benchmarks, such as Traveling Salesman Problems (TSP) and Capacitated Vehicle Routing Problems (CVRP), demonstrate that G-LNS significantly outperforms LLM-based AHD methods as well as strong classical solvers. The discovered heuristics not only achieve near-optimal solutions with reduced computational budgets but also exhibit robust generalization across diverse and unseen instance distributions.</p> + https://arxiv.org/abs/2602.08253 + Mon, 09 Feb 2026 04:13:35 +0000 - Locas: Your Models are Principled Initializers of Locally-Supported Parametric Memories - https://arxiv.org/abs/2602.05085 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.05085.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sidi Lu, Zhenwen Liang, Dongyang Ma, Yan Wang, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> In this paper, we aim to bridge test-time-training with a new type of parametric memory that can be flexibly offloaded from or merged into model parameters. We present Locas, a Locally-Supported parametric memory that shares the design of FFN blocks in modern transformers, allowing it to be flexibly permanentized into the model parameters while supporting efficient continual learning. We discuss two major variants of Locas: one with a conventional two-layer MLP design that has a clearer theoretical guarantee; the other one shares the same GLU-FFN structure with SOTA LLMs, and can be easily attached to existing models for both parameter-efficient and computation-efficient continual learning. Crucially, we show that proper initialization of such low-rank sideway-FFN-style memories -- performed in a principled way by reusing model parameters, activations and/or gradients -- is essential for fast convergence, improved generalization, and catastrophic forgetting prevention. We validate the proposed memory mechanism on the PG-19 whole-book language modeling and LoCoMo long-context dialogue question answering tasks. With only 0.02\% additional parameters in the lowest case, Locas-GLU is capable of storing the information from past context while maintaining a much smaller context window. In addition, we also test the model's general capability loss after memorizing the whole book with Locas, through comparative MMLU evaluation. Results show the promising ability of Locas to permanentize past context into parametric knowledge with minimized catastrophic forgetting of the model's existing internal knowledge.</p> - https://arxiv.org/abs/2602.05085 - Wed, 04 Feb 2026 22:09:40 +0000 + Beyond Correctness: Learning Robust Reasoning via Transfer + https://arxiv.org/abs/2602.08489 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08489.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyunseok Lee, Soheil Abbasloo, Jihoon Tack, Jinwoo Shin</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure the robustness of the reasoning process itself. We adopt a simple philosophical view, robust reasoning should remain useful beyond the mind that produced it, and treat reasoning as a form of meaning transfer that must survive truncation, reinterpretation, and continuation. Building on this principle, we introduce Reinforcement Learning with Transferable Reward (RLTR), which operationalizes robustness via transfer reward that tests whether a partial reasoning prefix from one model can guide a separate model to the correct answer. This encourages LLMs to produce reasoning that is stable, interpretable, and genuinely generalizable. Our approach improves sampling consistency while improving final answer accuracy, and it reaches comparable performance in substantially fewer training steps. For example, on MATH500, RLTR achieves a +3.6%p gain in Maj@64 compared to RLVR and matches RLVR's average accuracy with roughly 2.5x fewer training steps, providing both more reliable reasoning and significantly more sample efficient.</p> + https://arxiv.org/abs/2602.08489 + Mon, 09 Feb 2026 10:41:44 +0000 - OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration - https://arxiv.org/abs/2602.05400 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.05400.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaobo Wang, Xuan Ouyang, Tianyi Xu, Yuzheng Hu, Jialin Liu, Guo Chen, Tianyu Zhang, Junhao Zheng, Kexin Yang, Xingzhang Ren, Dayiheng Liu, Linfeng Zhang</p><p><b>Upvotes:</b> 279</p><p><b>Summary:</b> As high-quality public text approaches exhaustion, a phenomenon known as the Data Wall, pre-training is shifting from more tokens to better tokens. However, existing methods either rely on heuristic static filters that ignore training dynamics, or use dynamic yet optimizer-agnostic criteria based on raw gradients. We propose OPUS (Optimizer-induced Projected Utility Selection), a dynamic data selection framework that defines utility in the optimizer-induced update space. OPUS scores candidates by projecting their effective updates, shaped by modern optimizers, onto a target direction derived from a stable, in-distribution proxy. To ensure scalability, we employ Ghost technique with CountSketch for computational efficiency, and Boltzmann sampling for data diversity, incurring only 4.7\% additional compute overhead. OPUS achieves remarkable results across diverse corpora, quality tiers, optimizers, and model scales. In pre-training of GPT-2 Large/XL on FineWeb and FineWeb-Edu with 30B tokens, OPUS outperforms industrial-level baselines and even full 200B-token training. Moreover, when combined with industrial-level static filters, OPUS further improves pre-training efficiency, even with lower-quality data. Furthermore, in continued pre-training of Qwen3-8B-Base on SciencePedia, OPUS achieves superior performance using only 0.5B tokens compared to full training with 3B tokens, demonstrating significant data efficiency gains in specialized domains.</p> - https://arxiv.org/abs/2602.05400 - Thu, 05 Feb 2026 07:34:23 +0000 + TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions + https://arxiv.org/abs/2602.08711 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08711.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linli Yao, Yuancheng Wei, Yaojie Zhang, Lei Li, Xinlong Chen, Feifan Song, Ziyue Wang, Kun Ouyang, Yuanxin Liu, Lingpeng Kong, Qi Liu, Pengfei Wan, Kun Gai, Yuanxing Zhang, Xu Sun</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> This paper proposes Omni Dense Captioning, a novel task designed to generate continuous, fine-grained, and structured audio-visual narratives with explicit timestamps. To ensure dense semantic coverage, we introduce a six-dimensional structural schema to create "script-like" captions, enabling readers to vividly imagine the video content scene by scene, akin to a cinematographic screenplay. To facilitate research, we construct OmniDCBench, a high-quality, human-annotated benchmark, and propose SodaM, a unified metric that evaluates time-aware detailed descriptions while mitigating scene boundary ambiguity. Furthermore, we construct a training dataset, TimeChatCap-42K, and present TimeChat-Captioner-7B, a strong baseline trained via SFT and GRPO with task-specific rewards. Extensive experiments demonstrate that TimeChat-Captioner-7B achieves state-of-the-art performance, surpassing Gemini-2.5-Pro, while its generated dense descriptions significantly boost downstream capabilities in audio-visual reasoning (DailyOmni and WorldSense) and temporal grounding (Charades-STA). All datasets, models, and code will be made publicly available at https://github.com/yaolinli/TimeChat-Captioner.</p> + https://arxiv.org/abs/2602.08711 + Mon, 09 Feb 2026 14:21:58 +0000 - Stable Velocity: A Variance Perspective on Flow Matching - https://arxiv.org/abs/2602.05435 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.05435.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Donglin Yang, Yongxing Zhang, Xin Yu, Liang Hou, Xin Tao, Pengfei Wan, Xiaojuan Qi, Renjie Liao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By explicitly characterizing this variance, we identify 1) a high-variance regime near the prior, where optimization is challenging, and 2) a low-variance regime near the data distribution, where conditional and marginal velocities nearly coincide. Leveraging this insight, we propose Stable Velocity, a unified framework that improves both training and sampling. For training, we introduce Stable Velocity Matching (StableVM), an unbiased variance-reduction objective, along with Variance-Aware Representation Alignment (VA-REPA), which adaptively strengthen auxiliary supervision in the low-variance regime. For inference, we show that dynamics in the low-variance regime admit closed-form simplifications, enabling Stable Velocity Sampling (StableVS), a finetuning-free acceleration. Extensive experiments on ImageNet 256times256 and large pretrained text-to-image and text-to-video models, including SD3.5, Flux, Qwen-Image, and Wan2.2, demonstrate consistent improvements in training efficiency and more than 2times faster sampling within the low-variance regime without degrading sample quality. Our code is available at https://github.com/linYDTHU/StableVelocity.</p> - https://arxiv.org/abs/2602.05435 - Thu, 05 Feb 2026 08:25:05 +0000 + Large Language Lobotomy: Jailbreaking Mixture-of-Experts via Expert Silencing + https://arxiv.org/abs/2602.08741 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08741.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jona te Lintelo, Lichao Wu, Stjepan Picek</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The rapid adoption of Mixture-of-Experts (MoE) architectures marks a major shift in the deployment of Large Language Models (LLMs). MoE LLMs improve scaling efficiency by activating only a small subset of parameters per token, but their routing structure introduces new safety attack surfaces. We find that safety-critical behaviors in MoE LLMs (e.g., refusal) are concentrated in a small set of experts rather than being uniformly distributed. Building on this, we propose Large Language Lobotomy (L^3), a training-free, architecture-agnostic attack that compromises safety alignment by exploiting expert routing dynamics. L^3 learns routing patterns that correlate with refusal, attributes safety behavior to specific experts, and adaptively silences the most safety-relevant experts until harmful outputs are produced. We evaluate L^3 on eight state-of-the-art open-source MoE LLMs and show that our adaptive expert silencing increases average attack success from 7.3% to 70.4%, reaching up to 86.3%, outperforming prior training-free MoE jailbreak methods. Moreover, bypassing guardrails typically requires silencing fewer than 20% of layer-wise experts while largely preserving general language utility. These results reveal a fundamental tension between efficiency-driven MoE design and robust safety alignment and motivate distributing safety mechanisms more robustly in future MoE LLMs with architecture- and routing-aware methods.</p> + https://arxiv.org/abs/2602.08741 + Mon, 09 Feb 2026 14:42:11 +0000 - ContextBench: A Benchmark for Context Retrieval in Coding Agents - https://arxiv.org/abs/2602.05892 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.05892.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Li, Letian Zhu, Bohan Zhang, Rili Feng, Jiaming Wang, Yue Pan, Earl T. Barr, Sarro Federica, Zhaoyang Chu, He Ye</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insight into how agents retrieve and use code context during problem solving. We introduce ContextBench, a process-oriented evaluation of context retrieval in coding agents. ContextBench consists of 1,136 issue-resolution tasks from 66 repositories across eight programming languages, each augmented with human-annotated gold contexts. We further implement an automated evaluation framework that tracks agent trajectories and measures context recall, precision, and efficiency throughout issue resolution. Using ContextBench, we evaluate four frontier LLMs and five coding agents. Our results show that sophisticated agent scaffolding yields only marginal gains in context retrieval ("The Bitter Lesson" of coding agents), LLMs consistently favor recall over precision, and substantial gaps exist between explored and utilized context. ContextBench augments existing end-to-end benchmarks with intermediate gold-context metrics that unbox the issue-resolution process. These contexts offer valuable intermediate signals for guiding LLM reasoning in software tasks.</p> - https://arxiv.org/abs/2602.05892 - Thu, 05 Feb 2026 17:10:26 +0000 + StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors + https://arxiv.org/abs/2602.08934 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08934.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Suraj Ranganath, Atharv Ramesh</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve semantics while evading detection. We introduce StealthRL, a reinforcement learning framework that stress-tests detector robustness under realistic adversarial conditions. StealthRL trains a paraphrase policy against a multi-detector ensemble using Group Relative Policy Optimization (GRPO) with LoRA adapters on Qwen3-4B, optimizing a composite reward that balances detector evasion with semantic preservation. We evaluate six attack settings (M0-M5) against three detector families (RoBERTa, FastDetectGPT, and Binoculars) at the security-relevant 1% false positive rate operating point. StealthRL achieves near-zero detection (0.001 mean TPR@1%FPR), reduces mean AUROC from 0.74 to 0.27, and attains a 99.9% attack success rate. Critically, attacks transfer to a held-out detector family not seen during training, revealing shared architectural vulnerabilities rather than detector-specific brittleness. We additionally conduct LLM-based quality evaluation via Likert scoring, analyze detector score distributions to explain why evasion succeeds, and provide per-detector AUROC with bootstrap confidence intervals. Our results expose significant robustness gaps in current AI-text detection and establish StealthRL as a principled adversarial evaluation protocol. Code and evaluation pipeline are publicly available at https://github.com/suraj-ranganath/StealthRL.</p> + https://arxiv.org/abs/2602.08934 + Mon, 09 Feb 2026 17:33:46 +0000 - Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding - https://arxiv.org/abs/2602.06161 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06161.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanzheng Xiang, Lan Wei, Yizhen Yao, Qinglin Zhu, Hanqi Yan, Chen Jin, Philip Alexander Teare, Dandan Zhang, Lin Gui, Amrutha Saseendran, Yulan He</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelism often harms quality. Revocable decoding mitigates this by rechecking earlier tokens, yet we observe that existing verification schemes frequently trigger flip-flop oscillations, where tokens are remasked and later restored unchanged. This behaviour slows inference in two ways: remasking verified positions weakens the conditioning context for parallel drafting, and repeated remask cycles consume the revision budget with little net progress. We propose COVER (Cache Override Verification for Efficient Revision), which performs leave-one-out verification and stable drafting within a single forward pass. COVER constructs two attention views via KV cache override: selected seeds are masked for verification, while their cached key value states are injected for all other queries to preserve contextual information, with a closed form diagonal correction preventing self leakage at the seed positions. COVER further prioritises seeds using a stability aware score that balances uncertainty, downstream influence, and cache drift, and it adapts the number of verified seeds per step. Across benchmarks, COVER markedly reduces unnecessary revisions and yields faster decoding while preserving output quality.</p> - https://arxiv.org/abs/2602.06161 - Thu, 05 Feb 2026 19:58:48 +0000 + When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents + https://arxiv.org/abs/2602.08995 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08995.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuting Ning, Jaylen Jones, Zhehao Zhang, Chentao Ye, Weitong Ruan, Junyi Li, Rahul Gupta, Huan Sun</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from the user's original intent. Such misaligned actions may arise from external attacks (e.g., indirect prompt injection) or from internal limitations (e.g., erroneous reasoning). They not only expose CUAs to safety risks, but also degrade task efficiency and reliability. This work makes the first effort to define and study misaligned action detection in CUAs, with comprehensive coverage of both externally induced and internally arising misaligned actions. We further identify three common categories in real-world CUA deployment and construct MisActBench, a benchmark of realistic trajectories with human-annotated, action-level alignment labels. Moreover, we propose DeAction, a practical and universal guardrail that detects misaligned actions before execution and iteratively corrects them through structured feedback. DeAction outperforms all existing baselines across offline and online evaluations with moderate latency overhead: (1) On MisActBench, it outperforms baselines by over 15% absolute in F1 score; (2) In online evaluation, it reduces attack success rate by over 90% under adversarial settings while preserving or even improving task success rate in benign environments.</p> + https://arxiv.org/abs/2602.08995 + Mon, 09 Feb 2026 18:41:15 +0000 - ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training - https://arxiv.org/abs/2602.06820 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06820.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dunwei Tu, Hongyan Hao, Hansi Yang, Yihao Chen, Yi-Kai Zhang, Zhikang Xia, Yu Yang, Yueqing Sun, Xingchen Liu, Furao Shen, Qi Gu, Hui Su, Xunliang Cai</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scarce, and existing synthesis methods suffer from significant limitations regarding environmental diversity and scalability. To address these challenges, we introduce ScaleEnv, a framework that constructs fully interactive environments and verifiable tasks entirely from scratch. Specifically, ScaleEnv ensures environment reliability through procedural testing, and guarantees task completeness and solvability via tool dependency graph expansion and executable action verification. By enabling agents to learn through exploration within ScaleEnv, we demonstrate significant performance improvements on unseen, multi-turn tool-use benchmarks such as τ^2-Bench and VitaBench, highlighting strong generalization capabilities. Furthermore, we investigate the relationship between increasing number of domains and model generalization performance, providing empirical evidence that scaling environmental diversity is critical for robust agent learning.</p> - https://arxiv.org/abs/2602.06820 - Fri, 06 Feb 2026 16:05:55 +0000 + ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation + https://arxiv.org/abs/2602.09014 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09014.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihan Yang, Shuyuan Tu, Licheng Zhang, Qi Dai, Yu-Gang Jiang, Zuxuan Wu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Diffusion models have achieved remarkable generation quality, but they suffer from significant inference cost due to their reliance on multiple sequential denoising steps, motivating recent efforts to distill this inference process into a few-step regime. However, existing distillation methods typically approximate the teacher trajectory by using linear shortcuts, which makes it difficult to match its constantly changing tangent directions as velocities evolve across timesteps, thereby leading to quality degradation. To address this limitation, we propose ArcFlow, a few-step distillation framework that explicitly employs non-linear flow trajectories to approximate pre-trained teacher trajectories. Concretely, ArcFlow parameterizes the velocity field underlying the inference trajectory as a mixture of continuous momentum processes. This enables ArcFlow to capture velocity evolution and extrapolate coherent velocities to form a continuous non-linear trajectory within each denoising step. Importantly, this parameterization admits an analytical integration of this non-linear trajectory, which circumvents numerical discretization errors and results in high-precision approximation of the teacher trajectory. To train this parameterization into a few-step generator, we implement ArcFlow via trajectory distillation on pre-trained teacher models using lightweight adapters. This strategy ensures fast, stable convergence while preserving generative diversity and quality. Built on large-scale models (Qwen-Image-20B and FLUX.1-dev), ArcFlow only fine-tunes on less than 5% of original parameters and achieves a 40x speedup with 2 NFEs over the original multi-step teachers without significant quality degradation. Experiments on benchmarks show the effectiveness of ArcFlow both qualitatively and quantitatively.</p> + https://arxiv.org/abs/2602.09014 + Mon, 09 Feb 2026 18:56:14 +0000 - ANCHOR: Branch-Point Data Generation for GUI Agents - https://arxiv.org/abs/2602.07153 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07153.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinbiao Wei, Yilun Zhao, Kangqi Ni, Arman Cohan</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> End-to-end GUI agents for real desktop environments require large amounts of high-quality interaction data, yet collecting human demonstrations is expensive and existing synthetic pipelines often suffer from limited task diversity or noisy, goal-drifting trajectories. We present a trajectory expansion framework Anchor that bootstraps scalable desktop supervision from a small set of verified seed demonstrations. Starting from each seed, we identify branch points that correspond to meaningful state changes and propose new, state-grounded task variants conditioned on the current GUI context. An executing agent then follows the proposed instructions to generate new trajectories, while a verifier enforces task completion via state-aware checks and trajectory-level consistency. To improve supervision quality, we further apply task-conditioned step-level filtering to remove ungrounded actions and denoise post-branch segments to maintain coherent intent. Experiments on standard desktop benchmarks, OSWorld and WindowsAgentArena, show that models fine-tuned on our expanded corpus achieve consistent improvements over zero-shot agents and representative synthesis baselines, and generalize across applications and operating systems.</p> - https://arxiv.org/abs/2602.07153 - Fri, 06 Feb 2026 19:55:26 +0000 + EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies + https://arxiv.org/abs/2602.09514 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09514.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xavier Hu, Jinxiang Xia, Shengze Xu, Kangqi Song, Yishuo Yuan, Guibin Zhang, JinCheng Ren, Boyu Feng, Li Lu, Tieyong Zeng, Jiaheng Liu, Minghao Liu, He Zhu, Yuchen Eleanor Jiang, Wei Wang, Wangchunshu Zhou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Long-horizon planning is widely recognized as a core capability of autonomous LLM-based agents; however, current evaluation frameworks suffer from being largely episodic, domain-specific, or insufficiently grounded in persistent economic dynamics. We introduce EcoGym, a generalizable benchmark for continuous plan-and-execute decision making in interactive economies. EcoGym comprises three diverse environments: Vending, Freelance, and Operation, implemented in a unified decision-making process with standardized interfaces, and budgeted actions over an effectively unbounded horizon (1000+ steps if 365 day-loops for evaluation). The evaluation of EcoGym is based on business-relevant outcomes (e.g., net worth, income, and DAU), targeting long-term strategic coherence and robustness under partial observability and stochasticity. Experiments across eleven leading LLMs expose a systematic tension: no single model dominates across all three scenarios. Critically, we find that models exhibit significant suboptimality in either high-level strategies or efficient actions executions. EcoGym is released as an open, extensible testbed for transparent long-horizon agent evaluation and for studying controllability-utility trade-offs in realistic economic settings.</p> + https://arxiv.org/abs/2602.09514 + Tue, 10 Feb 2026 08:12:23 +0000 - Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs - https://arxiv.org/abs/2602.07276 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pengrui Han, Xueqiang Xu, Keyang Xuan, Peiyang Song, Siru Ouyang, Runchu Tian, Yuqing Jiang, Cheng Qian, Pengcheng Jiang, Jiashuo Sun, Junxia Cui, Ming Zhong, Ge Liu, Jiawei Han, Jiaxuan You</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making them inflexible under task variation and inadequate for complex tasks that require multiple coordinated capabilities. To address this limitation, we propose STEER2ADAPT, a lightweight framework that adapts LLMs by composing steering vectors rather than learning new ones from scratch. In many domains (e.g., reasoning or safety), tasks share a small set of underlying concept dimensions. STEER2ADAPT captures these dimensions as a reusable, low-dimensional semantic prior subspace, and adapts to new tasks by dynamically discovering a linear combination of basis vectors from only a handful of examples. Experiments across 9 tasks and 3 models in both reasoning and safety domains demonstrate the effectiveness of STEER2ADAPT, achieving an average improvement of 8.2%. Extensive analyses further show that STEER2ADAPT is a data-efficient, stable, and transparent inference-time adaptation method for LLMs.</p> - https://arxiv.org/abs/2602.07276 - Sat, 07 Feb 2026 00:00:50 +0000 + Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models + https://arxiv.org/abs/2602.09713 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09713.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruisi Zhao, Haoren Zheng, Zongxin Yang, Hehe Fan, Yi Yang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Rigged 3D assets are fundamental to 3D deformation and animation. However, existing 3D generation methods face challenges in generating animatable geometry, while rigging techniques lack fine-grained structural control over skeleton creation. To address these limitations, we introduce Stroke3D, a novel framework that directly generates rigged meshes from user inputs: 2D drawn strokes and a descriptive text prompt. Our approach pioneers a two-stage pipeline that separates the generation into: 1) Controllable Skeleton Generation, we employ the Skeletal Graph VAE (Sk-VAE) to encode the skeleton's graph structure into a latent space, where the Skeletal Graph DiT (Sk-DiT) generates a skeletal embedding. The generation process is conditioned on both the text for semantics and the 2D strokes for explicit structural control, with the VAE's decoder reconstructing the final high-quality 3D skeleton; and 2) Enhanced Mesh Synthesis via TextuRig and SKA-DPO, where we then synthesize a textured mesh conditioned on the generated skeleton. For this stage, we first enhance an existing skeleton-to-mesh model by augmenting its training data with TextuRig: a dataset of textured and rigged meshes with captions, curated from Objaverse-XL. Additionally, we employ a preference optimization strategy, SKA-DPO, guided by a skeleton-mesh alignment score, to further improve geometric fidelity. Together, our framework enables a more intuitive workflow for creating ready to animate 3D content. To the best of our knowledge, our work is the first to generate rigged 3D meshes conditioned on user-drawn 2D strokes. Extensive experiments demonstrate that Stroke3D produces plausible skeletons and high-quality meshes.</p> + https://arxiv.org/abs/2602.09713 + Tue, 10 Feb 2026 12:17:00 +0000 - AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management - https://arxiv.org/abs/2602.07398 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07398.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruoyao Wen, Hao Li, Chaowei Xiao, Ning Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working memory through their context window, which stores interaction history for decision-making. Conventional agents indiscriminately accumulate all tool outputs and reasoning traces in this memory, creating two critical vulnerabilities: (1) injected instructions persist throughout the workflow, granting attackers multiple opportunities to manipulate behavior, and (2) verbose, non-essential content degrades decision-making capabilities. Existing defenses treat bloated memory as given and focus on remaining resilient, rather than reducing unnecessary accumulation to prevent the attack. We present AgentSys, a framework that defends against indirect prompt injection through explicit memory management. Inspired by process memory isolation in operating systems, AgentSys organizes agents hierarchically: a main agent spawns worker agents for tool calls, each running in an isolated context and able to spawn nested workers for subtasks. External data and subtask traces never enter the main agent's memory; only schema-validated return values can cross boundaries through deterministic JSON parsing. Ablations show isolation alone cuts attack success to 2.19%, and adding a validator/sanitizer further improves defense with event-triggered checks whose overhead scales with operations rather than context length. On AgentDojo and ASB, AgentSys achieves 0.78% and 4.25% attack success while slightly improving benign utility over undefended baselines. It remains robust to adaptive attackers and across multiple foundation models, showing that explicit memory management enables secure, dynamic LLM agent architectures. Our code is available at: https://github.com/ruoyaow/agentsys-memory.</p> - https://arxiv.org/abs/2602.07398 - Sat, 07 Feb 2026 06:28:51 +0000 + QP-OneModel: A Unified Generative LLM for Multi-Task Query Understanding in Xiaohongshu Search + https://arxiv.org/abs/2602.09901 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09901.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianzhao Huang, Xiaorui Huang, Fei Zhao, Yunpeng Liu, Hui Zhang, Fangcheng Shi, Congfeng Li, Zechen Sun, Yi Wu, Yao Hu, Yunhan Bai, Shaosheng Cao</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Query Processing (QP) bridges user intent and content supply in large-scale Social Network Service (SNS) search engines. Traditional QP systems rely on pipelines of isolated discriminative models (e.g., BERT), suffering from limited semantic understanding and high maintenance overhead. While Large Language Models (LLMs) offer a potential solution, existing approaches often optimize sub-tasks in isolation, neglecting intrinsic semantic synergy and necessitating independent iterations. Moreover, standard generative methods often lack grounding in SNS scenarios, failing to bridge the gap between open-domain corpora and informal SNS linguistic patterns, while struggling to adhere to rigorous business definitions. We present QP-OneModel, a Unified Generative LLM for Multi-Task Query Understanding in the SNS domain. We reformulate heterogeneous sub-tasks into a unified sequence generation paradigm, adopting a progressive three-stage alignment strategy culminating in multi-reward Reinforcement Learning. Furthermore, QP-OneModel generates intent descriptions as a novel high-fidelity semantic signal, effectively augmenting downstream tasks such as query rewriting and ranking. Offline evaluations show QP-OneModel achieves a 7.35% overall gain over discriminative baselines, with significant F1 boosts in NER (+9.01%) and Term Weighting (+9.31%). It also exhibits superior generalization, surpassing a 32B model by 7.60% accuracy on unseen tasks. Fully deployed at Xiaohongshu, online A/B tests confirm its industrial value, optimizing retrieval relevance (DCG) by 0.21% and lifting user retention by 0.044%.</p> + https://arxiv.org/abs/2602.09901 + Tue, 10 Feb 2026 15:38:17 +0000 - Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model - https://arxiv.org/abs/2602.07422 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07422.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyi Wu, Mingzhe Du, Yue Liu, Chengran Yang, Terry Yue Zhuo, Jiaheng Zhang, See-Kiong Ng</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large language models (LLMs) are increasingly used in software development, yet their tendency to generate insecure code remains a major barrier to real-world deployment. Existing secure code alignment methods often suffer from a functionality--security paradox, improving security at the cost of substantial utility degradation. We propose SecCoderX, an online reinforcement learning framework for functionality-preserving secure code generation. SecCoderX first bridges vulnerability detection and secure code generation by repurposing mature detection resources in two ways: (i) synthesizing diverse, reality-grounded vulnerability-inducing coding tasks for online RL rollouts, and (ii) training a reasoning-based vulnerability reward model that provides scalable and reliable security supervision. Together, these components are unified in an online RL loop to align code LLMs to generate secure and functional code. Extensive experiments demonstrate that SecCoderX achieves state-of-the-art performance, improving Effective Safety Rate (ESR) by approximately 10% over unaligned models, whereas prior methods often degrade ESR by 14-54%. We release our code, dataset and model checkpoints at https://github.com/AndrewWTY/SecCoderX.</p> - https://arxiv.org/abs/2602.07422 - Sat, 07 Feb 2026 07:42:07 +0000 + Towards Autonomous Mathematics Research + https://arxiv.org/abs/2602.10177 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10177.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tony Feng, Trieu H. Trinh, Garrett Bingham, Dawsen Hwang, Yuri Chervonyi, Junehyuk Jung, Joonkyung Lee, Carlo Pagano, Sang-hyun Kim, Federico Pasqualotto, Sergei Gukov, Jonathan N. Lee, Junsu Kim, Kaiying Hou, Golnaz Ghiasi, Yi Tay, YaGuang Li, Chenkai Kuang, Yuan Liu, Hanzhao, Lin, Evan Zheran Liu, Nigamaa Nayakanti, Xiaomeng Yang, Heng-tze Cheng, Demis Hassabis, Koray Kavukcuoglu, Quoc V. Le, Thang Luong</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Recent advances in foundational models have yielded reasoning systems capable of achieving a gold-medal standard at the International Mathematical Olympiad. The transition from competition-level problem-solving to professional research, however, requires navigating vast literature and constructing long-horizon proofs. In this work, we introduce Aletheia, a math research agent that iteratively generates, verifies, and revises solutions end-to-end in natural language. Specifically, Aletheia is powered by an advanced version of Gemini Deep Think for challenging reasoning problems, a novel inference-time scaling law that extends beyond Olympiad-level problems, and intensive tool use to navigate the complexities of mathematical research. We demonstrate the capability of Aletheia from Olympiad problems to PhD-level exercises and most notably, through several distinct milestones in AI-assisted mathematics research: (a) a research paper (Feng26) generated by AI without any human intervention in calculating certain structure constants in arithmetic geometry called eigenweights; (b) a research paper (LeeSeo26) demonstrating human-AI collaboration in proving bounds on systems of interacting particles called independent sets; and (c) an extensive semi-autonomous evaluation (Feng et al., 2026a) of 700 open problems on Bloom's Erdos Conjectures database, including autonomous solutions to four open questions. In order to help the public better understand the developments pertaining to AI and mathematics, we suggest codifying standard levels quantifying autonomy and novelty of AI-assisted results. We conclude with reflections on human-AI collaboration in mathematics.</p> + https://arxiv.org/abs/2602.10177 + Tue, 10 Feb 2026 18:50:15 +0000 - Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation - https://arxiv.org/abs/2602.07670 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07670.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jarrod Barnes</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Test-time training (TTT) adapts language models through gradient-based updates at inference. But is adaptation the right strategy? We study compute-optimal test-time strategies for verifiable execution-grounded (VEG) tasks, domains like GPU kernel optimization where a deterministic evaluator provides dense, continuous reward signals. Using KernelBench as our testbed and a 120B-parameter model (GPT-OSS-120B with LoRA adaptation), we find that search outperforms minimal adaptation (1-5 gradient steps): Best-of-N sampling achieves 90% task success (18/20 tasks) at K=64 across the full KernelBench L1 eval set while TTT's best checkpoint reaches only 30.6% (3-seed mean), with TTT's "equivalent K" falling below 1, worse than single-sample inference. The failure mode is over-sharpening: gradient updates collapse diversity toward mediocre solutions rather than discovering optimal ones. Our main contribution is surprisal-guided selection: selecting the highest-surprisal (lowest-confidence) correct sample yields 80% success vs. 50% for most-confident selection, a 30% improvement. Extending to surprisal-guided-top3 matches oracle performance at 100%. This zero-cost strategy, validated through length-controlled analysis, recovers oracle performance. For dense-reward VEG tasks, compute should be allocated to sample diversity and intelligent selection rather than gradient adaptation. The surprisal-guided selection principle may generalize to other execution-grounded domains where optimal solutions occupy the distribution tail.</p> - https://arxiv.org/abs/2602.07670 - Sat, 07 Feb 2026 19:29:07 +0000 - - - Learning to Continually Learn via Meta-learning Agentic Memory Designs - https://arxiv.org/abs/2602.07755 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07755.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiming Xiong, Shengran Hu, Jeff Clune</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The statelessness of foundation models bottlenecks agentic systems' ability to continually learn, a core capability for long-horizon reasoning and adaptation. To address this limitation, agentic systems commonly incorporate memory modules to retain and reuse past experience, aiming for continual learning during test time. However, most existing memory designs are human-crafted and fixed, which limits their ability to adapt to the diversity and non-stationarity of real-world tasks. In this paper, we introduce ALMA (Automated meta-Learning of Memory designs for Agentic systems), a framework that meta-learns memory designs to replace hand-engineered memory designs, therefore minimizing human effort and enabling agentic systems to be continual learners across diverse domains. Our approach employs a Meta Agent that searches over memory designs expressed as executable code in an open-ended manner, theoretically allowing the discovery of arbitrary memory designs, including database schemas as well as their retrieval and update mechanisms. Extensive experiments across four sequential decision-making domains demonstrate that the learned memory designs enable more effective and efficient learning from experience than state-of-the-art human-crafted memory designs on all benchmarks. When developed and deployed safely, ALMA represents a step toward self-improving AI systems that learn to be adaptive, continual learners.</p> - https://arxiv.org/abs/2602.07755 - Sun, 08 Feb 2026 01:20:49 +0000 - - - TodoEvolve: Learning to Architect Agent Planning Systems - https://arxiv.org/abs/2602.07839 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07839.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxi Liu, Yanzuo Jiang, Guibin Zhang, Zihan Zhang, Heng Chang, Zhenfei Yin, Qibing Ren, Junchi Yan</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Planning has become a central capability for contemporary agent systems in navigating complex, long-horizon tasks, yet existing approaches predominantly rely on fixed, hand-crafted planning structures that lack the flexibility to adapt to the structural diversity of open-ended problems. To address this limitation, we introduce TodoEvolve, a meta-planning paradigm that autonomously synthesizes and dynamically revises task-specific planning architectures. Specifically, we first construct PlanFactory, a modular design space that standardizes diverse planning paradigms within a unified codebase encompassing topology, initialization, adaptation, and navigation, thereby providing a common interface for heterogeneous planning patterns. Leveraging PlanFactory, we collect high-quality planning trajectories and train Todo-14B via Impedance-Guided Preference Optimization (IGPO), a multi-objective reinforcement learning objective that encourages the generation of planning systems that are performant, stable, and token-efficient across arbitrary tasks and agent backbones. Empirical evaluations on five agentic benchmarks demonstrate that TodoEvolve consistently surpasses carefully engineered planning modules while maintaining economical API costs and runtime overhead.</p> - https://arxiv.org/abs/2602.07839 - Sun, 08 Feb 2026 06:37:01 +0000 - - - CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution - https://arxiv.org/abs/2602.07918 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07918.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minbeom Kim, Mihir Parmar, Phillip Wallis, Lesly Miculicich, Kyomin Jung, Krishnamurthy Dj Dvijotham, Long T. Le, Tomas Pfister</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> AI agents equipped with tool-calling capabilities are susceptible to Indirect Prompt Injection (IPI) attacks. In this attack scenario, malicious commands hidden within untrusted content trick the agent into performing unauthorized actions. Existing defenses can reduce attack success but often suffer from the over-defense dilemma: they deploy expensive, always-on sanitization regardless of actual threat, thereby degrading utility and latency even in benign scenarios. We revisit IPI through a causal ablation perspective: a successful injection manifests as a dominance shift where the user request no longer provides decisive support for the agent's privileged action, while a particular untrusted segment, such as a retrieved document or tool output, provides disproportionate attributable influence. Based on this signature, we propose CausalArmor, a selective defense framework that (i) computes lightweight, leave-one-out ablation-based attributions at privileged decision points, and (ii) triggers targeted sanitization only when an untrusted segment dominates the user intent. Additionally, CausalArmor employs retroactive Chain-of-Thought masking to prevent the agent from acting on ``poisoned'' reasoning traces. We present a theoretical analysis showing that sanitization based on attribution margins conditionally yields an exponentially small upper bound on the probability of selecting malicious actions. Experiments on AgentDojo and DoomArena demonstrate that CausalArmor matches the security of aggressive defenses while improving explainability and preserving utility and latency of AI agents.</p> - https://arxiv.org/abs/2602.07918 - Sun, 08 Feb 2026 11:34:08 +0000 - - - SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning - https://arxiv.org/abs/2602.08234 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08234.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peng Xia, Jianwen Chen, Hanyang Wang, Jiaqi Liu, Kaide Zeng, Yu Wang, Siwei Han, Yiyang Zhou, Xujiang Zhao, Haifeng Chen, Zeyu Zheng, Cihang Xie, Huaxiu Yao</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Large Language Model (LLM) agents have shown stunning results in complex tasks, yet they often operate in isolation, failing to learn from past experiences. Existing memory-based methods primarily store raw trajectories, which are often redundant and noise-heavy. This prevents agents from extracting high-level, reusable behavioral patterns that are essential for generalization. In this paper, we propose SkillRL, a framework that bridges the gap between raw experience and policy improvement through automatic skill discovery and recursive evolution. Our approach introduces an experience-based distillation mechanism to build a hierarchical skill library SkillBank, an adaptive retrieval strategy for general and task-specific heuristics, and a recursive evolution mechanism that allows the skill library to co-evolve with the agent's policy during reinforcement learning. These innovations significantly reduce the token footprint while enhancing reasoning utility. Experimental results on ALFWorld, WebShop and seven search-augmented tasks demonstrate that SkillRL achieves state-of-the-art performance, outperforming strong baselines over 15.3% and maintaining robustness as task complexity increases. Code is available at this https://github.com/aiming-lab/SkillRL.</p> - https://arxiv.org/abs/2602.08234 - Mon, 09 Feb 2026 03:17:17 +0000 - - - OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration - https://arxiv.org/abs/2602.08344 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08344.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qi Guo, Jianing Wang, Deyang Kong, Xiangyu Xi, Jianfei Zhang, Yi Lu, Jingang Wang, Wei Wang, Shikun Zhang, Wei Ye</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Parallel thinking has emerged as a new paradigm for large reasoning models (LRMs) in tackling complex problems. Recent methods leverage Reinforcement Learning (RL) to enhance parallel thinking, aiming to address the limitations in computational resources and effectiveness encountered with supervised fine-tuning. However, most existing studies primarily focus on optimizing the aggregation phase, with limited attention to the path exploration stage. In this paper, we theoretically analyze the optimization of parallel thinking under the Reinforcement Learning with Verifiable Rewards (RLVR) setting, and identify that the mutual information bottleneck among exploration paths fundamentally restricts overall performance. To address this, we propose Outline-Guided Path Exploration (OPE), which explicitly partitions the solution space by generating diverse reasoning outlines prior to parallel path reasoning, thereby reducing information redundancy and improving the diversity of information captured across exploration paths. We implement OPE with an iterative RL strategy that optimizes outline planning and outline-guided reasoning independently. Extensive experiments across multiple challenging mathematical benchmarks demonstrate that OPE effectively improves reasoning performance in different aggregation strategies, enabling LRMs to more reliably discover correct solutions.</p> - https://arxiv.org/abs/2602.08344 - Mon, 09 Feb 2026 07:29:13 +0000 - - - Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning - https://arxiv.org/abs/2602.08382 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08382.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuoen Chen, Dongfang Li, Meishan Zhang, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generation (RAG). We propose a cognitively inspired framework for efficient long-context inference based on chunk-wise compression and selective memory recall, rather than processing all raw tokens. The framework segments long inputs into chunks and encodes each chunk into compressed memory representations using a learned compressor. A gating module dynamically selects relevant memory blocks, which are then iteratively processed by a reasoning module with an evolving working memory to solve downstream tasks. The compressor and reasoner are jointly optimized via end-to-end reinforcement learning, while the gating module is trained separately as a classifier. Experimental results show that the proposed method achieves competitive accuracy on multi-hop reasoning benchmarks such as RULER-HQA, extrapolates context length from 7K to 1.75M tokens, and offers a favorable accuracy-efficiency trade-off compared to strong long-context baselines. In particular, it achieves up to a 2 times reduction in peak GPU memory usage and a 6 times inference speedup over MemAgent.</p> - https://arxiv.org/abs/2602.08382 - Mon, 09 Feb 2026 08:33:11 +0000 - - - Prism: Spectral-Aware Block-Sparse Attention - https://arxiv.org/abs/2602.08426 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinghao Wang, Pengyu Wang, Xiaoran Liu, Fangxu Liu, Jason Chu, Kai Song, Xipeng Qiu</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Block-sparse attention is promising for accelerating long-context LLM pre-filling, yet identifying relevant blocks efficiently remains a bottleneck. Existing methods typically employ coarse-grained attention as a proxy for block importance estimation, but often resort to expensive token-level searching or scoring, resulting in significant selection overhead. In this work, we trace the inaccuracy of standard coarse-grained attention via mean pooling to a theoretical root cause: the interaction between mean pooling and Rotary Positional Embeddings (RoPE). We prove that mean pooling acts as a low-pass filter that induces destructive interference in high-frequency dimensions, effectively creating a "blind spot" for local positional information (e.g., slash patterns). To address this, we introduce Prism, a training-free spectral-aware approach that decomposes block selection into high-frequency and low-frequency branches. By applying energy-based temperature calibration, Prism restores the attenuated positional signals directly from pooled representations, enabling block importance estimation using purely block-level operations, thereby improving efficiency. Extensive evaluations confirm that Prism maintains accuracy parity with full attention while delivering up to 5.1times speedup.</p> - https://arxiv.org/abs/2602.08426 - Mon, 09 Feb 2026 09:31:06 +0000 - - - Learning Self-Correction in Vision-Language Models via Rollout Augmentation - https://arxiv.org/abs/2602.08503 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08503.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Ding, Ziliang Qiu, Bolian Li, Ruqi Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Self-correction is essential for solving complex reasoning problems in vision-language models (VLMs). However, existing reinforcement learning (RL) methods struggle to learn it, as effective self-correction behaviors emerge only rarely, making learning signals extremely sparse. To address this challenge, we propose correction-specific rollouts (Octopus), an RL rollout augmentation framework that synthesizes dense self-correction examples by recombining existing rollouts. This augmentation simultaneously improves sample efficiency due to rollout reuse and stabilizes RL optimization through balanced supervision. Furthermore, we introduce a response-masking strategy that decouples self-correction from direct reasoning, avoiding signal conflicts and enabling both behaviors to be learned effectively. Building on this, we introduce Octopus-8B, a reasoning VLM with controllable self-correction capability. Across 7 benchmarks, it achieves SoTA performance among open-source VLMs, outperforming the best RLVR baseline by 1.0 score while requiring only 0.72times training time per step.</p> - https://arxiv.org/abs/2602.08503 - Mon, 09 Feb 2026 10:55:13 +0000 - - - Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering - https://arxiv.org/abs/2602.08519 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08519.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunhui Liu, Pengyu Qiu, Yu Xing, Yongchao Liu, Peng Du, Chuntao Hong, Jiajun Zheng, Tao Zheng, Tieke He</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Attributed Graph Clustering (AGC) is a fundamental unsupervised task that integrates structural topology and node attributes to uncover latent patterns in graph-structured data. Despite its significance in industrial applications such as fraud detection and user segmentation, a significant chasm persists between academic research and real-world deployment. Current evaluation protocols suffer from the small-scale, high-homophily citation datasets, non-scalable full-batch training paradigms, and a reliance on supervised metrics that fail to reflect performance in label-scarce environments. To bridge these gaps, we present PyAGC, a comprehensive, production-ready benchmark and library designed to stress-test AGC methods across diverse scales and structural properties. We unify existing methodologies into a modular Encode-Cluster-Optimize framework and, for the first time, provide memory-efficient, mini-batch implementations for a wide array of state-of-the-art AGC algorithms. Our benchmark curates 12 diverse datasets, ranging from 2.7K to 111M nodes, specifically incorporating industrial graphs with complex tabular features and low homophily. Furthermore, we advocate for a holistic evaluation protocol that mandates unsupervised structural metrics and efficiency profiling alongside traditional supervised metrics. Battle-tested in high-stakes industrial workflows at Ant Group, this benchmark offers the community a robust, reproducible, and scalable platform to advance AGC research towards realistic deployment. The code and resources are publicly available via GitHub (https://github.com/Cloudy1225/PyAGC), PyPI (https://pypi.org/project/pyagc), and Documentation (https://pyagc.readthedocs.io).</p> - https://arxiv.org/abs/2602.08519 - Mon, 09 Feb 2026 11:07:24 +0000 - - - Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems - https://arxiv.org/abs/2602.08847 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08847.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lang Feng, Longtao Zheng, Shuo He, Fuxiang Zhang, Bo An</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for such systems remains difficult. In this work, we theoretically pinpoint a key reason for training instability when extending group-based RL to multi-agent LLM systems. We show that under GRPO-style optimization, a global normalization baseline may deviate from diverse agents' reward distributions, which ultimately leads to gradient-norm instability. Based on this finding, we propose Dr. MAS, a simple and stable RL training recipe for multi-agent LLM systems. Dr. MAS uses an agent-wise remedy: normalizing advantages per agent using each agent's own reward statistics, which calibrates gradient scales and dramatically stabilizes training, both theoretically and empirically. Beyond the algorithm, Dr. MAS provides an end-to-end RL training framework for multi-agent LLM systems, supporting scalable orchestration, flexible per-agent LLM serving and optimization configs, and shared resource scheduling of LLM actor backends. We evaluate Dr. MAS on multi-agent math reasoning and multi-turn search benchmarks using Qwen2.5 and Qwen3 series models. Dr. MAS achieves clear gains over vanilla GRPO (e.g., +5.6\% avg@16 and +4.6\% pass@16 on math, and +15.2\% avg@16 and +13.1\% pass@16 on search) while largely eliminating gradient spikes. Moreover, it remains highly effective under heterogeneous agent-model assignments while improving efficiency.</p> - https://arxiv.org/abs/2602.08847 - Mon, 09 Feb 2026 16:13:39 +0000 - - - UI-Venus-1.5 Technical Report - https://arxiv.org/abs/2602.09082 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09082.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Veuns-Team, Changlong Gao, Zhangxuan Gu, Yulin Liu, Xinyu Qiu, Shuheng Shen, Yue Wen, Tianyu Xia, Zhenyu Xu, Zhengwen Zeng, Beitong Zhou, Xingran Zhou, Weizhi Chen, Sunhao Dai, Jingya Dou, Yichen Gong, Yuan Guo, Zhenlin Guo, Feng Li, Qian Li, Jinzhen Lin, Yuqi Zhou, Linchao Zhu, Liang Chen, Zhenyu Guo, Changhua Meng, Weiqiang Wang</p><p><b>Upvotes:</b> 143</p><p><b>Summary:</b> GUI agents have emerged as a powerful paradigm for automating interactions in digital environments, yet achieving both broad generality and consistently strong task performance remains challenging.In this report, we present UI-Venus-1.5, a unified, end-to-end GUI Agent designed for robust real-world applications.The proposed model family comprises two dense variants (2B and 8B) and one mixture-of-experts variant (30B-A3B) to meet various downstream application scenarios.Compared to our previous version, UI-Venus-1.5 introduces three key technical advances: (1) a comprehensive Mid-Training stage leveraging 10 billion tokens across 30+ datasets to establish foundational GUI semantics; (2) Online Reinforcement Learning with full-trajectory rollouts, aligning training objectives with long-horizon, dynamic navigation in large-scale environments; and (3) a single unified GUI Agent constructed via Model Merging, which synthesizes domain-specific models (grounding, web, and mobile) into one cohesive checkpoint. Extensive evaluations demonstrate that UI-Venus-1.5 establishes new state-of-the-art performance on benchmarks such as ScreenSpot-Pro (69.6%), VenusBench-GD (75.0%), and AndroidWorld (77.6%), significantly outperforming previous strong baselines. In addition, UI-Venus-1.5 demonstrates robust navigation capabilities across a variety of Chinese mobile apps, effectively executing user instructions in real-world scenarios. Code: https://github.com/inclusionAI/UI-Venus; Model: https://huggingface.co/collections/inclusionAI/ui-venus</p> - https://arxiv.org/abs/2602.09082 - Mon, 09 Feb 2026 18:43:40 +0000 - - - iGRPO: Self-Feedback-Driven LLM Reasoning - https://arxiv.org/abs/2602.09000 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09000.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ali Hatamizadeh, Shrimai Prabhumoye, Igor Gitman, Ximing Lu, Seungju Han, Wei Ping, Yejin Choi, Jan Kautz</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions. Reinforcement Learning (RL) is a framework for aligning these models with task-specific rewards, improving overall quality and reliability. Group Relative Policy Optimization (GRPO) is an efficient, value-function-free alternative to Proximal Policy Optimization (PPO) that leverages group-relative reward normalization. We introduce Iterative Group Relative Policy Optimization (iGRPO), a two-stage extension of GRPO that adds dynamic self-conditioning through model-generated drafts. In Stage 1, iGRPO samples multiple exploratory drafts and selects the highest-reward draft using the same scalar reward signal used for optimization. In Stage 2, it appends this best draft to the original prompt and applies a GRPO-style update on draft-conditioned refinements, training the policy to improve beyond its strongest prior attempt. Under matched rollout budgets, iGRPO consistently outperforms GRPO across base models (e.g., Nemotron-H-8B-Base-8K and DeepSeek-R1 Distilled), validating its effectiveness on diverse reasoning benchmarks. Moreover, applying iGRPO to OpenReasoning-Nemotron-7B trained on AceReason-Math achieves new state-of-the-art results of 85.62\% and 79.64\% on AIME24 and AIME25, respectively. Ablations further show that the refinement wrapper generalizes beyond GRPO variants, benefits from a generative judge, and alters learning dynamics by delaying entropy collapse. These results underscore the potential of iterative, self-feedback-based RL for advancing verifiable mathematical reasoning.</p> - https://arxiv.org/abs/2602.09000 - Mon, 09 Feb 2026 18:45:11 +0000 - - - Contact-Anchored Policies: Contact Conditioning Creates Strong Robot Utility Models - https://arxiv.org/abs/2602.09017 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09017.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichen Jeff Cui, Omar Rayyan, Haritheja Etukuru, Bowen Tan, Zavier Andrianarivo, Zicheng Teng, Yihang Zhou, Krish Mehta, Nicholas Wojno, Kevin Yuanbo Wu, Manan H Anjaria, Ziyuan Wu, Manrong Mao, Guangxun Zhang, Binit Shah, Yejin Kim, Soumith Chintala, Lerrel Pinto, Nur Muhammad Mahi Shafiullah</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> The prevalent paradigm in robot learning attempts to generalize across environments, embodiments, and tasks with language prompts at runtime. A fundamental tension limits this approach: language is often too abstract to guide the concrete physical understanding required for robust manipulation. In this work, we introduce Contact-Anchored Policies (CAP), which replace language conditioning with points of physical contact in space. Simultaneously, we structure CAP as a library of modular utility models rather than a monolithic generalist policy. This factorization allows us to implement a real-to-sim iteration cycle: we build EgoGym, a lightweight simulation benchmark, to rapidly identify failure modes and refine our models and datasets prior to real-world deployment. We show that by conditioning on contact and iterating via simulation, CAP generalizes to novel environments and embodiments out of the box on three fundamental manipulation skills while using only 23 hours of demonstration data, and outperforms large, state-of-the-art VLAs in zero-shot evaluations by 56%. All model checkpoints, codebase, hardware, simulation, and datasets will be open-sourced. Project page: https://cap-policy.github.io/</p> - https://arxiv.org/abs/2602.09017 - Mon, 09 Feb 2026 18:58:50 +0000 - - - Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling - https://arxiv.org/abs/2602.09084 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09084.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruijie Ye, Jiayi Zhang, Zhuoxin Liu, Zihao Zhu, Siyuan Yang, Li Li, Tianfu Fu, Franck Dernoncourt, Yue Zhao, Jiacheng Zhu, Ryan Rossi, Wenhao Chai, Zhengzhong Tu</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> We study instruction-based image editing under professional workflows and identify three persistent challenges: (i) editors often over-edit, modifying content beyond the user's intent; (ii) existing models are largely single-turn, while multi-turn edits can alter object faithfulness; and (iii) evaluation at around 1K resolution is misaligned with real workflows that often operate on ultra high-definition images (e.g., 4K). We propose Agent Banana, a hierarchical agentic planner-executor framework for high-fidelity, object-aware, deliberative editing. Agent Banana introduces two key mechanisms: (1) Context Folding, which compresses long interaction histories into structured memory for stable long-horizon control; and (2) Image Layer Decomposition, which performs localized layer-based edits to preserve non-target regions while enabling native-resolution outputs. To support rigorous evaluation, we build HDD-Bench, a high-definition, dialogue-based benchmark featuring verifiable stepwise targets and native 4K images (11.8M pixels) for diagnosing long-horizon failures. On HDD-Bench, Agent Banana achieves the best multi-turn consistency and background fidelity (e.g., IC 0.871, SSIM-OM 0.84, LPIPS-OM 0.12) while remaining competitive on instruction following, and also attains strong performance on standard single-turn editing benchmarks. We hope this work advances reliable, professional-grade agentic image editing and its integration into real workflows.</p> - https://arxiv.org/abs/2602.09084 - Mon, 09 Feb 2026 18:59:18 +0000 - - - Autoregressive Image Generation with Masked Bit Modeling - https://arxiv.org/abs/2602.09024 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09024.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qihang Yu, Qihao Liu, Ju He, Xinyang Zhang, Yang Liu, Liang-Chieh Chen, Xi Chen</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> This paper challenges the dominance of continuous pipelines in visual generation. We systematically investigate the performance gap between discrete and continuous methods. Contrary to the belief that discrete tokenizers are intrinsically inferior, we demonstrate that the disparity arises primarily from the total number of bits allocated in the latent space (i.e., the compression ratio). We show that scaling up the codebook size effectively bridges this gap, allowing discrete tokenizers to match or surpass their continuous counterparts. However, existing discrete generation methods struggle to capitalize on this insight, suffering from performance degradation or prohibitive training costs with scaled codebook. To address this, we propose masked Bit AutoRegressive modeling (BAR), a scalable framework that supports arbitrary codebook sizes. By equipping an autoregressive transformer with a masked bit modeling head, BAR predicts discrete tokens through progressively generating their constituent bits. BAR achieves a new state-of-the-art gFID of 0.99 on ImageNet-256, outperforming leading methods across both continuous and discrete paradigms, while significantly reducing sampling costs and converging faster than prior continuous approaches. Project page is available at https://bar-gen.github.io/</p> - https://arxiv.org/abs/2602.09024 - Mon, 09 Feb 2026 18:59:58 +0000 - - - SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes - https://arxiv.org/abs/2602.09153 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09153.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nicholas Pfaff, Thomas Cohn, Sergey Zakharov, Rick Cory, Russ Tedrake</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Simulation has become a key tool for training and evaluating home robots at scale, yet existing environments fail to capture the diversity and physical complexity of real indoor spaces. Current scene synthesis methods produce sparsely furnished rooms that lack the dense clutter, articulated furniture, and physical properties essential for robotic manipulation. We introduce SceneSmith, a hierarchical agentic framework that generates simulation-ready indoor environments from natural language prompts. SceneSmith constructs scenes through successive stagesx2013from architectural layout to furniture placement to small object populationx2013each implemented as an interaction among VLM agents: designer, critic, and orchestrator. The framework tightly integrates asset generation through text-to-3D synthesis for static objects, dataset retrieval for articulated objects, and physical property estimation. SceneSmith generates 3-6x more objects than prior methods, with <2% inter-object collisions and 96% of objects remaining stable under physics simulation. In a user study with 205 participants, it achieves 92% average realism and 91% average prompt faithfulness win rates against baselines. We further demonstrate that these environments can be used in an end-to-end pipeline for automatic robot policy evaluation.</p> - https://arxiv.org/abs/2602.09153 - Mon, 09 Feb 2026 19:56:04 +0000 - - - Rethinking Global Text Conditioning in Diffusion Transformers - https://arxiv.org/abs/2602.09268 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikita Starodubcev, Daniil Pakhomov, Zongze Wu, Ilya Drobyshevskiy, Yuchen Liu, Zhonghao Wang, Yuqian Zhou, Zhe Lin, Dmitry Baranchuk</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Diffusion transformers typically incorporate textual information via attention layers and a modulation mechanism using a pooled text embedding. Nevertheless, recent approaches discard modulation-based text conditioning and rely exclusively on attention. In this paper, we address whether modulation-based text conditioning is necessary and whether it can provide any performance advantage. Our analysis shows that, in its conventional usage, the pooled embedding contributes little to overall performance, suggesting that attention alone is generally sufficient for faithfully propagating prompt information. However, we reveal that the pooled embedding can provide significant gains when used from a different perspective-serving as guidance and enabling controllable shifts toward more desirable properties. This approach is training-free, simple to implement, incurs negligible runtime overhead, and can be applied to various diffusion models, bringing improvements across diverse tasks, including text-to-image/video generation and image editing.</p> - https://arxiv.org/abs/2602.09268 - Mon, 09 Feb 2026 23:06:58 +0000 - - - Effective Reasoning Chains Reduce Intrinsic Dimensionality - https://arxiv.org/abs/2602.09276 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Archiki Prasad, Mandar Joshi, Kenton Lee, Mohit Bansal, Peter Shaw</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Chain-of-thought (CoT) reasoning and its variants have substantially improved the performance of language models on complex reasoning tasks, yet the precise mechanisms by which different strategies facilitate generalization remain poorly understood. While current explanations often point to increased test-time computation or structural guidance, establishing a consistent, quantifiable link between these factors and generalization remains challenging. In this work, we identify intrinsic dimensionality as a quantitative measure for characterizing the effectiveness of reasoning chains. Intrinsic dimensionality quantifies the minimum number of model dimensions needed to reach a given accuracy threshold on a given task. By keeping the model architecture fixed and varying the task formulation through different reasoning strategies, we demonstrate that effective reasoning strategies consistently reduce the intrinsic dimensionality of the task. Validating this on GSM8K with Gemma-3 1B and 4B, we observe a strong inverse correlation between the intrinsic dimensionality of a reasoning strategy and its generalization performance on both in-distribution and out-of-distribution data. Our findings suggest that effective reasoning chains facilitate learning by better compressing the task using fewer parameters, offering a new quantitative metric for analyzing reasoning processes.</p> - https://arxiv.org/abs/2602.09276 - Mon, 09 Feb 2026 23:32:12 +0000 - - - Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning - https://arxiv.org/abs/2602.09439 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09439.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xu Ma, Yitian Zhang, Qihua Dong, Yun Fu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> High-quality and open datasets remain a major bottleneck for text-to-image (T2I) fine-tuning. Despite rapid progress in model architectures and training pipelines, most publicly available fine-tuning datasets suffer from low resolution, poor text-image alignment, or limited diversity, resulting in a clear performance gap between open research models and enterprise-grade models. In this work, we present Fine-T2I, a large-scale, high-quality, and fully open dataset for T2I fine-tuning. Fine-T2I spans 10 task combinations, 32 prompt categories, 11 visual styles, and 5 prompt templates, and combines synthetic images generated by strong modern models with carefully curated real images from professional photographers. All samples are rigorously filtered for text-image alignment, visual fidelity, and prompt quality, with over 95% of initial candidates removed. The final dataset contains over 6 million text-image pairs, around 2 TB on disk, approaching the scale of pretraining datasets while maintaining fine-tuning-level quality. Across a diverse set of pretrained diffusion and autoregressive models, fine-tuning on Fine-T2I consistently improves both generation quality and instruction adherence, as validated by human evaluation, visual comparison, and automatic metrics. We release Fine-T2I under an open license to help close the data gap in T2I fine-tuning in the open community.</p> - https://arxiv.org/abs/2602.09439 - Tue, 10 Feb 2026 06:06:54 +0000 - - - P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads - https://arxiv.org/abs/2602.09443 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09443.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yun Luo, Futing Wang, Qianjia Cheng, Fangchen Yu, Haodi Lei, Jianhao Yan, Chenxi Li, Jiacheng Chen, Yufeng Zhao, Haiyuan Wan, Yuchen Zhang, Shenghe Zheng, Junchi Yao, Qingyang Zhang, Haonan He, Wenxuan Zeng, Li Sheng, Chengxing Xie, Yuxin Zuo, Yizhuo Li, Yulun Wu, Rui Huang, Dongzhan Zhou, Kai Chen, Yu Qiao, Lei Bai, Yu Cheng, Ning Ding, Bowen Zhou, Peng Ye, Ganqu Cui</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> The transition from symbolic manipulation to science-grade reasoning represents a pivotal frontier for Large Language Models (LLMs), with physics serving as the critical test anchor for binding abstract logic to physical reality. Physics demands that a model maintain physical consistency with the laws governing the universe, a task that fundamentally requires multimodal perception to ground abstract logic in reality. At the Olympiad level, diagrams are often constitutive rather than illustrative, containing essential constraints, such as boundary conditions and spatial symmetries, that are absent from the text. To bridge this visual-logical gap, we introduce P1-VL, a family of open-source vision-language models engineered for advanced scientific reasoning. Our method harmonizes Curriculum Reinforcement Learning, which employs progressive difficulty expansion to stabilize post-training, with Agentic Augmentation, enabling iterative self-verification at inference. Evaluated on HiPhO, a rigorous benchmark of 13 exams from 2024-2025, our flagship P1-VL-235B-A22B becomes the first open-source Vision-Language Model (VLM) to secure 12 gold medals and achieves the state-of-the-art performance in the open-source models. Our agent-augmented system achieves the No.2 overall rank globally, trailing only Gemini-3-Pro. Beyond physics, P1-VL demonstrates remarkable scientific reasoning capacity and generalizability, establishing significant leads over base models in STEM benchmarks. By open-sourcing P1-VL, we provide a foundational step toward general-purpose physical intelligence to better align visual perceptions with abstract physical laws for machine scientific discovery.</p> - https://arxiv.org/abs/2602.09443 - Tue, 10 Feb 2026 06:28:08 +0000 - - - On the Optimal Reasoning Length for RL-Trained Language Models - https://arxiv.org/abs/2602.09591 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09591.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daisuke Nohara, Taishi Nakamura, Rio Yokota</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Reinforcement learning substantially improves reasoning in large language models, but it also tends to lengthen chain of thought outputs and increase computational cost during both training and inference. Though length control methods have been proposed, it remains unclear what the optimal output length is for balancing efficiency and performance. In this work, we compare several length control methods on two models, Qwen3-1.7B Base and DeepSeek-R1-Distill-Qwen-1.5B. Our results indicate that length penalties may hinder reasoning acquisition, while properly tuned length control can improve efficiency for models with strong prior reasoning. By extending prior work to RL trained policies, we identify two failure modes, 1) long outputs increase dispersion, and 2) short outputs lead to under-thinking.</p> - https://arxiv.org/abs/2602.09591 - Tue, 10 Feb 2026 09:45:42 +0000 - - - TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution - https://arxiv.org/abs/2602.09662 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09662.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Deyang Jiang, Jing Huang, Xuanle Zhao, Lei Chen, Liming Zheng, Fanfan Liu, Haibo Qiu, Peng Shi, Zhixiong Zeng</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Effectively scaling GUI automation is essential for computer-use agents (CUAs); however, existing work primarily focuses on scaling GUI grounding rather than the more crucial GUI planning, which requires more sophisticated data collection. In reality, the exploration process of a CUA across apps/desktops/web pages typically follows a tree structure, with earlier functional entry points often being explored more frequently. Thus, organizing large-scale trajectories into tree structures can reduce data cost and streamline the data scaling of GUI planning. In this work, we propose TreeCUA to efficiently scale GUI automation with tree-structured verifiable evolution. We propose a multi-agent collaborative framework to explore the environment, verify actions, summarize trajectories, and evaluate quality to generate high-quality and scalable GUI trajectories. To improve efficiency, we devise a novel tree-based topology to store and replay duplicate exploration nodes, and design an adaptive exploration algorithm to balance the depth (i.e., trajectory difficulty) and breadth (i.e., trajectory diversity). Moreover, we develop world knowledge guidance and global memory backtracking to avoid low-quality generation. Finally, we naturally extend and propose the TreeCUA-DPO method from abundant tree node information, improving GUI planning capability by referring to the branch information of adjacent trajectories. Experimental results show that TreeCUA and TreeCUA-DPO offer significant improvements, and out-of-domain (OOD) studies further demonstrate strong generalization. All trajectory node information and code will be available at https://github.com/UITron-hub/TreeCUA.</p> - https://arxiv.org/abs/2602.09662 - Tue, 10 Feb 2026 11:16:57 +0000 - - - Covo-Audio Technical Report - https://arxiv.org/abs/2602.09823 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09823.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenfu Wang, Chenxing Li, Liqiang Zhang, Yiyang Zhao, Yuxiang Zou, Hanzhao Li, Mingyu Cui, Hao Zhang, Kun Wei, Le Xu, Zikang Huang, Jiajun Xu, Jiliang Hu, Xiang He, Zeyu Xie, Jiawen Kang, Youjun Chen, Meng Yu, Dong Yu, Rilin Chen, Linlin Di, Shulin Feng, Na Hu, Yang Liu, Bang Wang, Shan Yang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> In this work, we present Covo-Audio, a 7B-parameter end-to-end LALM that directly processes continuous audio inputs and generates audio outputs within a single unified architecture. Through large-scale curated pretraining and targeted post-training, Covo-Audio achieves state-of-the-art or competitive performance among models of comparable scale across a broad spectrum of tasks, including speech-text modeling, spoken dialogue, speech understanding, audio understanding, and full-duplex voice interaction. Extensive evaluations demonstrate that the pretrained foundation model exhibits strong speech-text comprehension and semantic reasoning capabilities on multiple benchmarks, outperforming representative open-source models of comparable scale. Furthermore, Covo-Audio-Chat, the dialogue-oriented variant, demonstrates strong spoken conversational abilities, including understanding, contextual reasoning, instruction following, and generating contextually appropriate and empathetic responses, validating its applicability to real-world conversational assistant scenarios. Covo-Audio-Chat-FD, the evolved full-duplex model, achieves substantially superior performance on both spoken dialogue capabilities and full-duplex interaction behaviors, demonstrating its competence in practical robustness. To mitigate the high cost of deploying end-to-end LALMs for natural conversational systems, we propose an intelligence-speaker decoupling strategy that separates dialogue intelligence from voice rendering, enabling flexible voice customization with minimal text-to-speech (TTS) data while preserving dialogue performance. Overall, our results highlight the strong potential of 7B-scale models to integrate sophisticated audio intelligence with high-level semantic reasoning, and suggest a scalable path toward more capable and versatile LALMs.</p> - https://arxiv.org/abs/2602.09823 - Tue, 10 Feb 2026 14:31:11 +0000 - - - BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation - https://arxiv.org/abs/2602.09849 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09849.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yucheng Hu, Jianke Zhang, Yuanfei Luo, Yanjiang Guo, Xiaoyu Chen, Xinshu Sun, Kun Feng, Qingzhou Lu, Sheng Chen, Yangang Zhang, Wei Li, Jianyu Chen</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Equipping embodied agents with the ability to reason about tasks, foresee physical outcomes, and generate precise actions is essential for general-purpose manipulation. While recent Vision-Language-Action (VLA) models have leveraged pre-trained foundation models, they typically focus on either linguistic planning or visual forecasting in isolation. These methods rarely integrate both capabilities simultaneously to guide action generation, leading to suboptimal performance in complex, long-horizon manipulation tasks. To bridge this gap, we propose BagelVLA, a unified model that integrates linguistic planning, visual forecasting, and action generation within a single framework. Initialized from a pretrained unified understanding and generative model, BagelVLA is trained to interleave textual reasoning and visual prediction directly into the action execution loop. To efficiently couple these modalities, we introduce Residual Flow Guidance (RFG), which initializes from current observation and leverages single-step denoising to extract predictive visual features, guiding action generation with minimal latency. Extensive experiments demonstrate that BagelVLA outperforms existing baselines by a significant margin on multiple simulated and real-world benchmarks, particularly in tasks requiring multi-stage reasoning.</p> - https://arxiv.org/abs/2602.09849 - Tue, 10 Feb 2026 14:54:01 +0000 - - - Code2World: A GUI World Model via Renderable Code Generation - https://arxiv.org/abs/2602.09856 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09856.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Zheng, Li'an Zhong, Yi Wang, Rui Dai, Kaikui Liu, Xiangxiang Chu, Linyuan Lv, Philip Torr, Kevin Qinghong Lin</p><p><b>Upvotes:</b> 168</p><p><b>Summary:</b> Autonomous GUI agents interact with environments by perceiving interfaces and executing actions. As a virtual sandbox, the GUI World model empowers agents with human-like foresight by enabling action-conditioned prediction. However, existing text- and pixel-based approaches struggle to simultaneously achieve high visual fidelity and fine-grained structural controllability. To this end, we propose Code2World, a vision-language coder that simulates the next visual state via renderable code generation. Specifically, to address the data scarcity problem, we construct AndroidCode by translating GUI trajectories into high-fidelity HTML and refining synthesized code through a visual-feedback revision mechanism, yielding a corpus of over 80K high-quality screen-action pairs. To adapt existing VLMs into code prediction, we first perform SFT as a cold start for format layout following, then further apply Render-Aware Reinforcement Learning which uses rendered outcome as the reward signal by enforcing visual semantic fidelity and action consistency. Extensive experiments demonstrate that Code2World-8B achieves the top-performing next UI prediction, rivaling the competitive GPT-5 and Gemini-3-Pro-Image. Notably, Code2World significantly enhances downstream navigation success rates in a flexible manner, boosting Gemini-2.5-Flash by +9.5% on AndroidWorld navigation. The code is available at https://github.com/AMAP-ML/Code2World.</p> - https://arxiv.org/abs/2602.09856 - Tue, 10 Feb 2026 14:56:19 +0000 - - - LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations - https://arxiv.org/abs/2602.09924 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09924.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> William Lugoloobi, Thomas Foster, William Bankes, Chris Russell</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains challenging. We investigate whether their own likelihood of success is recoverable from their internal representations before generation, and if this signal can guide more efficient inference. We train linear probes on pre-generation activations to predict policy-specific success on math and coding tasks, substantially outperforming surface features such as question length and TF-IDF. Using E2H-AMC, which provides both human and model performance on identical problems, we show that models encode a model-specific notion of difficulty that is distinct from human difficulty, and that this distinction increases with extended reasoning. Leveraging these probes, we demonstrate that routing queries across a pool of models can exceed the best-performing model whilst reducing inference cost by up to 70\% on MATH, showing that internal representations enable practical efficiency gains even when they diverge from human intuitions about difficulty. Our code is available at: https://github.com/KabakaWilliam/llms_know_difficulty</p> - https://arxiv.org/abs/2602.09924 - Tue, 10 Feb 2026 15:57:00 +0000 - - - Chain of Mindset: Reasoning with Adaptive Cognitive Modes - https://arxiv.org/abs/2602.10063 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10063.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyi Jiang, Arctanx An, Hengyi Feng, Naixin Zhai, Haodong Li, Xiaomin Yu, Jiahui Liu, Hanwen Du, Shuo Zhang, Zhi Yang, Jie Huang, Yuhua Li, Yongxin Ni, Huacan Wang, Ronghao Chen</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Human problem-solving is never the repetition of a single mindset, by which we mean a distinct mode of cognitive processing. When tackling a specific task, we do not rely on a single mindset; instead, we integrate multiple mindsets within the single solution process. However, existing LLM reasoning methods fall into a common trap: they apply the same fixed mindset across all steps, overlooking that different stages of solving the same problem require fundamentally different mindsets. This single-minded assumption prevents models from reaching the next level of intelligence. To address this limitation, we propose Chain of Mindset (CoM), a training-free agentic framework that enables step-level adaptive mindset orchestration. CoM decomposes reasoning into four functionally heterogeneous mindsets: Spatial, Convergent, Divergent, and Algorithmic. A Meta-Agent dynamically selects the optimal mindset based on the evolving reasoning state, while a bidirectional Context Gate filters cross-module information flow to maintain effectiveness and efficiency. Experiments across six challenging benchmarks spanning mathematics, code generation, scientific QA, and spatial reasoning demonstrate that CoM achieves state-of-the-art performance, outperforming the strongest baseline by 4.96\% and 4.72\% in overall accuracy on Qwen3-VL-32B-Instruct and Gemini-2.0-Flash, while balancing reasoning efficiency. Our code is publicly available at https://github.com/QuantaAlpha/chain-of-mindset{https://github.com/QuantaAlpha/chain-of-mindset}.</p> - https://arxiv.org/abs/2602.10063 - Tue, 10 Feb 2026 18:31:47 +0000 - - - Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning - https://arxiv.org/abs/2602.10090 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10090.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoyang Wang, Canwen Xu, Boyi Liu, Yite Wang, Siwei Han, Zhewei Yao, Huaxiu Yao, Yuxiong He</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Recent advances in large language model (LLM) have empowered autonomous agents to perform complex tasks that require multi-turn interactions with tools and environments. However, scaling such agent training is limited by the lack of diverse and reliable environments. In this paper, we propose Agent World Model (AWM), a fully synthetic environment generation pipeline. Using this pipeline, we scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets (35 tools per environment on average) and obtain high-quality observations. Notably, these environments are code-driven and backed by databases, providing more reliable and consistent state transitions than environments simulated by LLMs. Moreover, they enable more efficient agent interaction compared with collecting trajectories from realistic environments. To demonstrate the effectiveness of this resource, we perform large-scale reinforcement learning for multi-turn tool-use agents. Thanks to the fully executable environments and accessible database states, we can also design reliable reward functions. Experiments on three benchmarks show that training exclusively in synthetic environments, rather than benchmark-specific ones, yields strong out-of-distribution generalization. The code is available at https://github.com/Snowflake-Labs/agent-world-model.</p> - https://arxiv.org/abs/2602.10090 - Tue, 10 Feb 2026 18:55:41 +0000 - - - VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model - https://arxiv.org/abs/2602.10098 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10098.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingwen Sun, Wenyao Zhang, Zekun Qi, Shaojie Ren, Zezhi Liu, Hanxin Zhu, Guangzhong Sun, Xin Jin, Zhibo Chen</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Pretraining Vision-Language-Action (VLA) policies on internet-scale video is appealing, yet current latent-action objectives often learn the wrong thing: they remain anchored to pixel variation rather than action-relevant state transitions, making them vulnerable to appearance bias, nuisance motion, and information leakage. We introduce VLA-JEPA, a JEPA-style pretraining framework that sidesteps these pitfalls by design. The key idea is leakage-free state prediction: a target encoder produces latent representations from future frames, while the student pathway sees only the current observation -- future information is used solely as supervision targets, never as input. By predicting in latent space rather than pixel space, VLA-JEPA learns dynamics abstractions that are robust to camera motion and irrelevant background changes. This yields a simple two-stage recipe -- JEPA pretraining followed by action-head fine-tuning -- without the multi-stage complexity of prior latent-action pipelines. Experiments on LIBERO, LIBERO-Plus, SimplerEnv and real-world manipulation tasks show that VLA-JEPA achieves consistent gains in generalization and robustness over existing methods.</p> - https://arxiv.org/abs/2602.10098 - Tue, 10 Feb 2026 18:58:01 +0000 - - - Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders - https://arxiv.org/abs/2602.10099 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10099.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amandeep Kumar, Vishal M. Patel</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Leveraging representation encoders for generative modeling offers a path for efficient, high-fidelity synthesis. However, standard diffusion transformers fail to converge on these representations directly. While recent work attributes this to a capacity bottleneck proposing computationally expensive width scaling of diffusion transformers we demonstrate that the failure is fundamentally geometric. We identify Geometric Interference as the root cause: standard Euclidean flow matching forces probability paths through the low-density interior of the hyperspherical feature space of representation encoders, rather than following the manifold surface. To resolve this, we propose Riemannian Flow Matching with Jacobi Regularization (RJF). By constraining the generative process to the manifold geodesics and correcting for curvature-induced error propagation, RJF enables standard Diffusion Transformer architectures to converge without width scaling. Our method RJF enables the standard DiT-B architecture (131M parameters) to converge effectively, achieving an FID of 3.37 where prior methods fail to converge. Code: https://github.com/amandpkr/RJF</p> - https://arxiv.org/abs/2602.10099 - Tue, 10 Feb 2026 18:58:04 +0000 - - - VideoWorld 2: Learning Transferable Knowledge from Real-world Videos - https://arxiv.org/abs/2602.10102 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10102.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongwei Ren, Yunchao Wei, Xiao Yu, Guixun Luo, Yao Zhao, Bingyi Kang, Jiashi Feng, Xiaojie Jin</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Learning transferable knowledge from unlabeled video data and applying it in new environments is a fundamental capability of intelligent agents. This work presents VideoWorld 2, which extends VideoWorld and offers the first investigation into learning transferable knowledge directly from raw real-world videos. At its core, VideoWorld 2 introduces a dynamic-enhanced Latent Dynamics Model (dLDM) that decouples action dynamics from visual appearance: a pretrained video diffusion model handles visual appearance modeling, enabling the dLDM to learn latent codes that focus on compact and meaningful task-related dynamics. These latent codes are then modeled autoregressively to learn task policies and support long-horizon reasoning. We evaluate VideoWorld 2 on challenging real-world handcraft making tasks, where prior video generation and latent-dynamics models struggle to operate reliably. Remarkably, VideoWorld 2 achieves up to 70% improvement in task success rate and produces coherent long execution videos. In robotics, we show that VideoWorld 2 can acquire effective manipulation knowledge from the Open-X dataset, which substantially improves task performance on CALVIN. This study reveals the potential of learning transferable world knowledge directly from raw videos, with all code, data, and models to be open-sourced for further research.</p> - https://arxiv.org/abs/2602.10102 - Tue, 10 Feb 2026 18:58:19 +0000 - - - Olaf-World: Orienting Latent Actions for Video World Modeling - https://arxiv.org/abs/2602.10104 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10104.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxin Jiang, Yuchao Gu, Ivor W. Tsang, Mike Zheng Shou</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Scaling action-controllable world models is limited by the scarcity of action labels. While latent action learning promises to extract control interfaces from unlabeled video, learned latents often fail to transfer across contexts: they entangle scene-specific cues and lack a shared coordinate system. This occurs because standard objectives operate only within each clip, providing no mechanism to align action semantics across contexts. Our key insight is that although actions are unobserved, their semantic effects are observable and can serve as a shared reference. We introduce SeqΔ-REPA, a sequence-level control-effect alignment objective that anchors integrated latent action to temporal feature differences from a frozen, self-supervised video encoder. Building on this, we present Olaf-World, a pipeline that pretrains action-conditioned video world models from large-scale passive video. Extensive experiments demonstrate that our method learns a more structured latent action space, leading to stronger zero-shot action transfer and more data-efficient adaptation to new control interfaces than state-of-the-art baselines.</p> - https://arxiv.org/abs/2602.10104 - Tue, 10 Feb 2026 18:58:41 +0000 - - - SAGE: Scalable Agentic 3D Scene Generation for Embodied AI - https://arxiv.org/abs/2602.10116 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10116.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongchi Xia, Xuan Li, Zhaoshuo Li, Qianli Ma, Jiashu Xu, Ming-Yu Liu, Yin Cui, Tsung-Yi Lin, Wei-Chiu Ma, Shenlong Wang, Shuran Song, Fangyin Wei</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Real-world data collection for embodied agents remains costly and unsafe, calling for scalable, realistic, and simulator-ready 3D environments. However, existing scene-generation systems often rely on rule-based or task-specific pipelines, yielding artifacts and physically invalid scenes. We present SAGE, an agentic framework that, given a user-specified embodied task (e.g., "pick up a bowl and place it on the table"), understands the intent and automatically generates simulation-ready environments at scale. The agent couples multiple generators for layout and object composition with critics that evaluate semantic plausibility, visual realism, and physical stability. Through iterative reasoning and adaptive tool selection, it self-refines the scenes until meeting user intent and physical validity. The resulting environments are realistic, diverse, and directly deployable in modern simulators for policy training. Policies trained purely on this data exhibit clear scaling trends and generalize to unseen objects and layouts, demonstrating the promise of simulation-driven scaling for embodied AI. Code, demos, and the SAGE-10k dataset can be found on the project page here: https://nvlabs.github.io/sage.</p> - https://arxiv.org/abs/2602.10116 + When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models + https://arxiv.org/abs/2602.10179 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10179.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiacheng Hou, Yining Sun, Ruochong Jin, Haochen Han, Fangming Liu, Wai Kin Victor Chan, Alex Jinpeng Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Recent advances in large image editing models have shifted the paradigm from text-driven instructions to vision-prompt editing, where user intent is inferred directly from visual inputs such as marks, arrows, and visual-text prompts. While this paradigm greatly expands usability, it also introduces a critical and underexplored safety risk: the attack surface itself becomes visual. In this work, we propose Vision-Centric Jailbreak Attack (VJA), the first visual-to-visual jailbreak attack that conveys malicious instructions purely through visual inputs. To systematically study this emerging threat, we introduce IESBench, a safety-oriented benchmark for image editing models. Extensive experiments on IESBench demonstrate that VJA effectively compromises state-of-the-art commercial models, achieving attack success rates of up to 80.9% on Nano Banana Pro and 70.1% on GPT-Image-1.5. To mitigate this vulnerability, we propose a training-free defense based on introspective multimodal reasoning, which substantially improves the safety of poorly aligned models to a level comparable with commercial systems, without auxiliary guard models and with negligible computational overhead. Our findings expose new vulnerabilities, provide both a benchmark and practical defense to advance safe and trustworthy modern image editing systems. Warning: This paper contains offensive images created by large image editing models.</p> + https://arxiv.org/abs/2602.10179 Tue, 10 Feb 2026 18:59:55 +0000 + + Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models + https://arxiv.org/abs/2602.10224 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10224.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiting Huang, Zecheng Li, Yu Zeng, Qingnan Ren, Zhen Fang, Qisheng Su, Kou Shi, Lin Chen, Zehui Chen, Feng Zhao</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for enhancing the reasoning capabilities of Large Language Models (LLMs). Despite its efficacy, RLVR faces a meta-learning bottleneck: it lacks mechanisms for error attribution and experience internalization intrinsic to the human learning cycle beyond practice and verification, thereby limiting fine-grained credit assignment and reusable knowledge formation. We term such reusable knowledge representations derived from past errors as meta-experience. Based on this insight, we propose Meta-Experience Learning (MEL), a novel framework that incorporates self-distilled meta-experience into the model's parametric memory. Building upon standard RLVR, we introduce an additional design that leverages the LLM's self-verification capability to conduct contrastive analysis on paired correct and incorrect trajectories, identify the precise bifurcation points where reasoning errors arise, and summarize them into generalizable meta-experience. The meta-experience is further internalized into the LLM's parametric memory by minimizing the negative log-likelihood, which induces a language-modeled reward signal that bridges correct and incorrect reasoning trajectories and facilitates effective knowledge reuse. Experimental results demonstrate that MEL achieves consistent improvements on benchmarks, yielding 3.92%--4.73% Pass@1 gains across varying model sizes.</p> + https://arxiv.org/abs/2602.10224 + Tue, 10 Feb 2026 19:16:09 +0000 + + + Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens + https://arxiv.org/abs/2602.10229 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10229.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weihao Liu, Dehai Min, Lu Cheng</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary space. Recently, reasoning in continuous latent space has emerged as a promising alternative, enabling more robust inference and flexible computation beyond discrete token constraints. However, current latent paradigms often suffer from feature collapse and instability, stemming from distribution mismatches when recurrently using hidden states as the input embeddings, or alignment issues when relying on assistant models. To address this, we propose Latent Thoughts Tuning (LT-Tuning), a framework that redefines how latent thoughts are constructed and deployed. Instead of relying solely on raw hidden states, our method introduces a Context-Prediction-Fusion mechanism that jointly leveraging contextual hidden states and predictive semantic guidance from the vocabulary embedding space. Combined with a progressive three-stage curriculum learning pipeline, LT-Tuning also enables dynamically switching between latent and explicit thinking modes. Experiments demonstrate that our method outperforms existing latent reasoning baselines, effectively mitigating feature collapse and achieving robust reasoning accuracy.</p> + https://arxiv.org/abs/2602.10229 + Tue, 10 Feb 2026 19:19:10 +0000 + + + Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards + https://arxiv.org/abs/2602.10231 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10231.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kirill Pavlenko, Alexander Golubev, Simon Karasik, Boris Yangel</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Group Relative Policy Optimization (GRPO) assigns a single scalar advantage to all tokens in a completion. For structured generations with explicit segments and objectives, this couples unrelated reward signals across segments, leading to objective interference and misattributed credit. We propose Blockwise Advantage Estimation, a family of GRPO-compatible methods that assigns each objective its own advantage and applies it only to the tokens in the corresponding text block, reducing reliance on hand-designed scalar rewards and scaling naturally to additional objectives. A key challenge is estimating advantages for later blocks whose rewards are conditioned on sampled prefixes; standard unbiased approaches require expensive nested rollouts from intermediate states. Concretely, we introduce an Outcome-Conditioned Baseline that approximates intermediate state values using only within-group statistics by stratifying samples according to a prefix-derived intermediate outcome. On math tasks with uncertainty estimation, our method mitigates reward interference, is competitive with a state-of-the-art reward-designed approach, and preserves test-time gains from confidence-weighted ensembling. More broadly, it provides a modular recipe for optimizing sequential objectives in structured generations without additional rollouts.</p> + https://arxiv.org/abs/2602.10231 + Tue, 10 Feb 2026 19:22:37 +0000 + + + LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation + https://arxiv.org/abs/2602.10367 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10367.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiling Yan, Dingjie Song, Zhe Fang, Yisheng Ji, Xiang Li, Quanzheng Li, Lichao Sun</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> The deployment of Large Language Models (LLMs) in high-stakes clinical settings demands rigorous and reliable evaluation. However, existing medical benchmarks remain static, suffering from two critical limitations: (1) data contamination, where test sets inadvertently leak into training corpora, leading to inflated performance estimates; and (2) temporal misalignment, failing to capture the rapid evolution of medical knowledge. Furthermore, current evaluation metrics for open-ended clinical reasoning often rely on either shallow lexical overlap (e.g., ROUGE) or subjective LLM-as-a-Judge scoring, both inadequate for verifying clinical correctness. To bridge these gaps, we introduce LiveMedBench, a continuously updated, contamination-free, and rubric-based benchmark that weekly harvests real-world clinical cases from online medical communities, ensuring strict temporal separation from model training data. We propose a Multi-Agent Clinical Curation Framework that filters raw data noise and validates clinical integrity against evidence-based medical principles. For evaluation, we develop an Automated Rubric-based Evaluation Framework that decomposes physician responses into granular, case-specific criteria, achieving substantially stronger alignment with expert physicians than LLM-as-a-Judge. To date, LiveMedBench comprises 2,756 real-world cases spanning 38 medical specialties and multiple languages, paired with 16,702 unique evaluation criteria. Extensive evaluation of 38 LLMs reveals that even the best-performing model achieves only 39.2%, and 84% of models exhibit performance degradation on post-cutoff cases, confirming pervasive data contamination risks. Error analysis further identifies contextual application-not factual knowledge-as the dominant bottleneck, with 35-48% of failures stemming from the inability to tailor medical knowledge to patient-specific constraints.</p> + https://arxiv.org/abs/2602.10367 + Tue, 10 Feb 2026 23:38:25 +0000 + + + When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning + https://arxiv.org/abs/2602.10560 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10560.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Leheng Sheng, Yongtao Zhang, Wenchang Ma, Yaorui Shi, Ting Huang, Xiang Wang, An Zhang, Ke Shen, Tat-Seng Chua</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> While reasoning over long context is crucial for various real-world applications, it remains challenging for large language models (LLMs) as they suffer from performance degradation as the context length grows. Recent work MemAgent has tried to tackle this by processing context chunk-by-chunk in an RNN-like loop and updating a textual memory for final answering. However, this naive recurrent memory update faces two crucial drawbacks: (i) memory can quickly explode because it can update indiscriminately, even on evidence-free chunks; and (ii) the loop lacks an exit mechanism, leading to unnecessary computation after even sufficient evidence is collected. To address these issues, we propose GRU-Mem, which incorporates two text-controlled gates for more stable and efficient long-context reasoning. Specifically, in GRU-Mem, the memory only updates when the update gate is open and the recurrent loop will exit immediately once the exit gate is open. To endow the model with such capabilities, we introduce two reward signals r^{update} and r^{exit} within end-to-end RL, rewarding the correct updating and exiting behaviors respectively. Experiments on various long-context reasoning tasks demonstrate the effectiveness and efficiency of GRU-Mem, which generally outperforms the vanilla MemAgent with up to 400\% times inference speed acceleration.</p> + https://arxiv.org/abs/2602.10560 + Wed, 11 Feb 2026 06:14:53 +0000 + + + Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters + https://arxiv.org/abs/2602.10604 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10604.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ailin Huang, Ang Li, Aobo Kong, Bin Wang, Binxing Jiao, Bo Dong, Bojun Wang, Boyu Chen, Brian Li, Buyun Ma, Chang Su, Changxin Miao, Changyi Wan, Chao Lou, Chen Hu, Chen Xu, Chenfeng Yu, Chengting Feng, Chengyuan Yao, Chunrui Han, Dan Ma, Dapeng Shi, Daxin Jiang, Dehua Ma, Deshan Sun, Di Qi, Enle Liu, Fajie Zhang, Fanqi Wan, Guanzhe Huang, Gulin Yan, Guoliang Cao, Guopeng Li, Han Cheng, Hangyu Guo, Hanshan Zhang, Hao Nie, Haonan Jia, Haoran Lv, Hebin Zhou, Hekun Lv, Heng Wang, Heung-Yeung Shum, Hongbo Huang, Hongbo Peng, Hongyu Zhou, Hongyuan Wang, Houyong Chen, Huangxi Zhu, Huimin Wu, Huiyong Guo, Jia Wang, Jian Zhou, Jianjian Sun, Jiaoren Wu, Jiaran Zhang, Jiashu Lv, Jiashuo Liu, Jiayi Fu, Jiayu Liu, Jie Cheng, Jie Luo, Jie Yang, Jie Zhou, Jieyi Hou, Jing Bai, Jingcheng Hu, Jingjing Xie, Jingwei Wu, Jingyang Zhang, Jishi Zhou, Junfeng Liu, Junzhe Lin, Ka Man Lo, Kai Liang, Kaibo Liu, Kaijun Tan, Kaiwen Yan, Kaixiang Li, Kang An, Kangheng Lin, Lei Yang, Liang Lv, Liang Zhao, Liangyu Chen, Lieyu Shi, Liguo Tan, Lin Lin, Lina Chen, Luck Ma, Mengqiang Ren, Michael Li, Ming Li, Mingliang Li, Mingming Zhang, Mingrui Chen, Mitt Huang, Na Wang, Peng Liu, Qi Han, Qian Zhao, Qinglin He, Qinxin Du, Qiuping Wu, Quan Sun, Rongqiu Yang, Ruihang Miao, Ruixin Han, Ruosi Wan, Ruyan Guo, Shan Wang, Shaoliang Pang, Shaowen Yang, Shengjie Fan, Shijie Shang, Shiliang Yang, Shiwei Li, Shuangshuang Tian, Siqi Liu, Siye Wu, Siyu Chen, Song Yuan, Tiancheng Cao, Tianchi Yue, Tianhao Cheng, Tianning Li, Tingdan Luo, Wang You, Wei Ji, Wei Yuan, Wei Zhang, Weibo Wu, Weihao Xie, Wen Sun, Wenjin Deng, Wenzhen Zheng, Wuxun Xie, Xiangfeng Wang, Xiangwen Kong, Xiangyu Liu, Xiangyu Zhang, Xiaobo Yang, Xiaojia Liu, Xiaolan Yuan, Xiaoran Jiao, Xiaoxiao Ren, Xiaoyun Zhang, Xin Li, Xin Liu, Xin Wu, Xing Chen, Xingping Yang, Xinran Wang, Xu Zhao, Xuan He, Xuanti Feng, Xuedan Cai, Xuqiang Zhou, Yanbo Yu, Yang Li, Yang Xu, Yanlin Lai, Yanming Xu, Yaoyu Wang, Yeqing Shen, Yibo Zhu, Yichen Lv, Yicheng Cao, Yifeng Gong, Yijing Yang, Yikun Yang, Yin Zhao, Yingxiu Zhao, Yinmin Zhang, Yitong Zhang, Yixuan Zhang, Yiyang Chen, Yongchi Zhao, Yongshen Long, Yongyao Wang, Yousong Guan, Yu Zhou, Yuang Peng, Yuanhao Ding, Yuantao Fan, Yuanzhen Yang, Yuchu Luo, Yudi Zhao, Yue Peng, Yueqiang Lin, Yufan Lu, Yuling Zhao, Yunzhou Ju, Yurong Zhang, Yusheng Li, Yuxiang Yang, Yuyang Chen, Yuzhu Cai, Zejia Weng, Zetao Hong, Zexi Li, Zhe Xie, Zheng Ge, Zheng Gong, Zheng Zeng, Zhenyi Lu, Zhewei Huang, Zhichao Chang, Zhiguo Huang, Zhiheng Hu, Zidong Yang, Zili Wang, Ziqi Ren, Zixin Zhang, Zixuan Wang</p><p><b>Upvotes:</b> 150</p><p><b>Summary:</b> We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments.</p> + https://arxiv.org/abs/2602.10604 + Wed, 11 Feb 2026 07:53:51 +0000 + + + Online Causal Kalman Filtering for Stable and Effective Policy Optimization + https://arxiv.org/abs/2602.10609 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10609.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuo He, Lang Feng, Xin Cheng, Lei Feng, Bo An</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Reinforcement learning for large language models suffers from high-variance token-level importance sampling (IS) ratios, which would destabilize policy optimization at scale. To improve stability, recent methods typically use a fixed sequence-level IS ratio for all tokens in a sequence or adjust each token's IS ratio separately, thereby neglecting temporal off-policy derivation across tokens in a sequence. In this paper, we first empirically identify that local off-policy deviation is structurally inconsistent at the token level, which may distort policy-gradient updates across adjacent tokens and lead to training collapse. To address the issue, we propose Online Causal Kalman Filtering for stable and effective Policy Optimization (KPO). Concretely, we model the desired IS ratio as a latent state that evolves across tokens and apply a Kalman filter to update this state online and autoregressively based on the states of past tokens, regardless of future tokens. The resulting filtered IS ratios preserve token-wise local structure-aware variation while strongly smoothing noise spikes, yielding more stable and effective policy updates. Experimentally, KPO achieves superior results on challenging math reasoning datasets compared with state-of-the-art counterparts.</p> + https://arxiv.org/abs/2602.10609 + Wed, 11 Feb 2026 07:57:43 +0000 + + + How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning + https://arxiv.org/abs/2602.10622 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10622.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Yuan, Yike Xu, Jinyong Wen, Baokun Wang, Yang Chen, Xiaotong Lin, Wuliang Huang, Ziyi Gao, Xing Fu, Yu Cheng, Weiqiang Wang</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Decoder-only large language models are increasingly used as behavioral encoders for user representation learning, yet the impact of attention masking on the quality of user embeddings remains underexplored. In this work, we conduct a systematic study of causal, hybrid, and bidirectional attention masks within a unified contrastive learning framework trained on large-scale real-world Alipay data that integrates long-horizon heterogeneous user behaviors. To improve training dynamics when transitioning from causal to bidirectional attention, we propose Gradient-Guided Soft Masking, a gradient-based pre-warmup applied before a linear scheduler that gradually opens future attention during optimization. Evaluated on 9 industrial user cognition benchmarks covering prediction, preference, and marketing sensitivity tasks, our approach consistently yields more stable training and higher-quality bidirectional representations compared with causal, hybrid, and scheduler-only baselines, while remaining compatible with decoder pretraining. Overall, our findings highlight the importance of masking design and training transition in adapting decoder-only LLMs for effective user representation learning. Our code is available at https://github.com/JhCircle/Deepfind-GGSM.</p> + https://arxiv.org/abs/2602.10622 + Wed, 11 Feb 2026 08:12:43 +0000 + + + UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory + https://arxiv.org/abs/2602.10652 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10652.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongshi Ye, Hui Jiang, Feihu Jiang, Tian Lan, Yichao Du, Biao Fu, Xiaodong Shi, Qianghuai Jia, Longyue Wang, Weihua Luo</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Self-evolving memory serves as the trainable parameters for Large Language Models (LLMs)-based agents, where extraction (distilling insights from experience) and management (updating the memory bank) must be tightly coordinated. Existing methods predominately optimize memory management while treating memory extraction as a static process, resulting in poor generalization, where agents accumulate instance-specific noise rather than robust memories. To address this, we propose Unified Memory Extraction and Management (UMEM), a self-evolving agent framework that jointly optimizes a Large Language Model to simultaneous extract and manage memories. To mitigate overfitting to specific instances, we introduce Semantic Neighborhood Modeling and optimize the model with a neighborhood-level marginal utility reward via GRPO. This approach ensures memory generalizability by evaluating memory utility across clusters of semantically related queries. Extensive experiments across five benchmarks demonstrate that UMEM significantly outperforms highly competitive baselines, achieving up to a 10.67% improvement in multi-turn interactive tasks. Futhermore, UMEM maintains a monotonic growth curve during continuous evolution. Codes and models will be publicly released.</p> + https://arxiv.org/abs/2602.10652 + Wed, 11 Feb 2026 08:58:41 +0000 + + + Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation + https://arxiv.org/abs/2602.10699 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10699.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Jiang, Yangru Huang, Zeyu Wang, Changping Wang, Yuling Xiong, Jun Zhang, Huan Yu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Generative recommendation via autoregressive models has unified retrieval and ranking into a single conditional generation framework. However, fine-tuning these models with Reinforcement Learning (RL) often suffers from a fundamental probability-reward mismatch. Conventional likelihood-dominated decoding (e.g., beam search) exhibits a myopic bias toward locally probable prefixes, which causes two critical failures: (1) insufficient exploration, where high-reward items in low-probability branches are prematurely pruned and rarely sampled, and (2) advantage compression, where trajectories sharing high-probability prefixes receive highly correlated rewards with low within-group variance, yielding a weak comparative signal for RL. To address these challenges, we propose V-STAR, a Value-guided Sampling and Tree-structured Advantage Reinforcement framework. V-STAR forms a self-evolving loop via two synergistic components. First, a Value-Guided Efficient Decoding (VED) is developed to identify decisive nodes and selectively deepen high-potential prefixes. This improves exploration efficiency without exhaustive tree search. Second, we propose Sibling-GRPO, which exploits the induced tree topology to compute sibling-relative advantages and concentrates learning signals on decisive branching decisions. Extensive experiments on both offline and online datasets demonstrate that V-STAR outperforms state-of-the-art baselines, delivering superior accuracy and candidate-set diversity under strict latency constraints.</p> + https://arxiv.org/abs/2602.10699 + Wed, 11 Feb 2026 09:57:36 +0000 + + + Benchmarking Large Language Models for Knowledge Graph Validation + https://arxiv.org/abs/2602.10748 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10748.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Farzad Shami, Stefano Marchesin, Gianmaria Silvello</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Knowledge Graphs (KGs) store structured factual knowledge by linking entities through relationships, crucial for many applications. These applications depend on the KG's factual accuracy, so verifying facts is essential, yet challenging. Expert manual verification is ideal but impractical on a large scale. Automated methods show promise but are not ready for real-world KGs. Large Language Models (LLMs) offer potential with their semantic understanding and knowledge access, yet their suitability and effectiveness for KG fact validation remain largely unexplored. In this paper, we introduce FactCheck, a benchmark designed to evaluate LLMs for KG fact validation across three key dimensions: (1) LLMs internal knowledge; (2) external evidence via Retrieval-Augmented Generation (RAG); and (3) aggregated knowledge employing a multi-model consensus strategy. We evaluated open-source and commercial LLMs on three diverse real-world KGs. FactCheck also includes a RAG dataset with 2+ million documents tailored for KG fact validation. Additionally, we offer an interactive exploration platform for analyzing verification decisions. The experimental analyses demonstrate that while LLMs yield promising results, they are still not sufficiently stable and reliable to be used in real-world KG validation scenarios. Integrating external evidence through RAG methods yields fluctuating performance, providing inconsistent improvements over more streamlined approaches -- at higher computational costs. Similarly, strategies based on multi-model consensus do not consistently outperform individual models, underscoring the lack of a one-fits-all solution. These findings further emphasize the need for a benchmark like FactCheck to systematically evaluate and drive progress on this difficult yet crucial task.</p> + https://arxiv.org/abs/2602.10748 + Wed, 11 Feb 2026 11:24:46 +0000 + + + GoodVibe: Security-by-Vibe for LLM-Based Code Generation + https://arxiv.org/abs/2602.10778 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10778.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maximilian Thang, Lichao Wu, Sasha Behrouzi, Mohamadreza Rostami, Jona te Lintelo, Stjepan Picek, Ahmad-Reza Sadeghi</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large language models (LLMs) are increasingly used for code generation in fast, informal development workflows, often referred to as vibe coding, where speed and convenience are prioritized, and security requirements are rarely made explicit. In this setting, models frequently produce functionally correct but insecure code, creating a growing security risk. Existing approaches to improving code security rely on full-parameter fine-tuning or parameter-efficient adaptations, which are either costly and prone to catastrophic forgetting or operate at coarse granularity with limited interpretability and control. We present GoodVibe, a neuron-level framework for improving the security of code language models by default. GoodVibe is based on the key insight that security-relevant reasoning is localized to a small subset of neurons. We identify these neurons using gradient-based attribution from a supervised security task and perform neuron-selective fine-tuning that updates only this security-critical subspace. To further reduce training cost, we introduce activation-driven neuron clustering, enabling structured updates with minimal overhead. We evaluate GoodVibe on six LLMs across security-critical programming languages, including C++, Java, Swift, and Go. GoodVibe substantially improves the security of generated code while preserving general model utility, achieving up to a 2.5x improvement over base models, matching or exceeding full fine-tuning with over 4,700x fewer trainable parameters, and reducing training computation by more than 3.6x compared to the parameter-efficient baseline (LoRA). Our results demonstrate that neuron-level optimization offers an effective and scalable approach to securing code generation without sacrificing efficiency or generality.</p> + https://arxiv.org/abs/2602.10778 + Wed, 11 Feb 2026 12:10:14 +0000 + + + FedPS: Federated data Preprocessing via aggregated Statistics + https://arxiv.org/abs/2602.10870 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10870.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuefeng Xu, Graham Cormode</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Federated Learning (FL) enables multiple parties to collaboratively train machine learning models without sharing raw data. However, before training, data must be preprocessed to address missing values, inconsistent formats, and heterogeneous feature scales. This preprocessing stage is critical for model performance but is largely overlooked in FL research. In practical FL systems, privacy constraints prohibit centralizing raw data, while communication efficiency introduces further challenges for distributed preprocessing. We introduce FedPS, a unified framework for federated data preprocessing based on aggregated statistics. FedPS leverages data-sketching techniques to efficiently summarize local datasets while preserving essential statistical information. Building on these summaries, we design federated algorithms for feature scaling, encoding, discretization, and missing-value imputation, and extend preprocessing-related models such as k-Means, k-Nearest Neighbors, and Bayesian Linear Regression to both horizontal and vertical FL settings. FedPS provides flexible, communication-efficient, and consistent preprocessing pipelines for practical FL deployments.</p> + https://arxiv.org/abs/2602.10870 + Wed, 11 Feb 2026 13:58:55 +0000 + + + FeatureBench: Benchmarking Agentic Coding for Complex Feature Development + https://arxiv.org/abs/2602.10975 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10975.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qixing Zhou, Jiacheng Zhang, Haiyang Wang, Rui Hao, Jiahe Wang, Minghao Han, Yuxue Yang, Shuzhe Wu, Feiyang Pan, Lue Fan, Dandan Tu, Zhaoxiang Zhang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current boundaries of their coding abilities. Existing agentic coding benchmarks, however, cover a limited task scope, e.g., bug fixing within a single pull request (PR), and often rely on non-executable evaluations or lack an automated approach for continually updating the evaluation coverage. To address such issues, we propose FeatureBench, a benchmark designed to evaluate agentic coding performance in end-to-end, feature-oriented software development. FeatureBench incorporates an execution-based evaluation protocol and a scalable test-driven method that automatically derives tasks from code repositories with minimal human effort. By tracing from unit tests along a dependency graph, our approach can identify feature-level coding tasks spanning multiple commits and PRs scattered across the development timeline, while ensuring the proper functioning of other features after the separation. Using this framework, we curated 200 challenging evaluation tasks and 3825 executable environments from 24 open-source repositories in the first version of our benchmark. Empirical evaluation reveals that the state-of-the-art agentic model, such as Claude 4.5 Opus, which achieves a 74.4% resolved rate on SWE-bench, succeeds on only 11.0% of tasks, opening new opportunities for advancing agentic coding. Moreover, benefiting from our automated task collection toolkit, FeatureBench can be easily scaled and updated over time to mitigate data leakage. The inherent verifiability of constructed environments also makes our method potentially valuable for agent training.</p> + https://arxiv.org/abs/2602.10975 + Wed, 11 Feb 2026 16:06:32 +0000 + + + CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion + https://arxiv.org/abs/2602.10999 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10999.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yusong Lin, Haiyang Wang, Shuzhe Wu, Lue Fan, Feiyang Pan, Sanyuan Zhao, Dandan Tu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Agentic coding requires agents to effectively interact with runtime environments, e.g., command line interfaces (CLI), so as to complete tasks like resolving dependency issues, fixing system problems, etc. But it remains underexplored how such environment-intensive tasks can be obtained at scale to enhance agents' capabilities. To address this, based on an analogy between the Dockerfile and the agentic task, we propose to employ agents to simulate and explore environment histories, guided by execution feedback. By tracing histories of a healthy environment, its state can be inverted to an earlier one with runtime failures, from which a task can be derived by packing the buggy state and the corresponding error messages. With our method, named CLI-Gym, a total of 1,655 environment-intensive tasks are derived, being the largest collection of its kind. Moreover, with curated successful trajectories, our fine-tuned model, named LiberCoder, achieves substantial absolute improvements of +21.1% (to 46.1%) on Terminal-Bench, outperforming various strong baselines. To our knowledge, this is the first public pipeline for scalable derivation of environment-intensive tasks.</p> + https://arxiv.org/abs/2602.10999 + Wed, 11 Feb 2026 16:22:18 +0000 + + + ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression + https://arxiv.org/abs/2602.11008 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.11008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ammar Ali, Baher Mohammad, Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip, Stamatios Lefkimmiatis</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We present ROCKET, a training-free model compression method that achieves state-of-the-art performance in comparison with factorization, structured-sparsification and dynamic compression baselines. Operating under a global compression budget, ROCKET comprises two key innovations: First, it formulates layer-wise compression allocation as a multi-choice knapsack problem, selecting the optimal compression level for each layer to minimize total reconstruction error while adhering to a target model size. Second, it introduces a single-step sparse matrix factorization inspired by dictionary learning: using only a small calibration set, it sparsifies weight coefficients based on activation-weights sensitivity and then updates the dictionary in closed form via least squares bypassing iterative optimization, sparse coding, or backpropagation entirely. ROCKET consistently outperforms existing compression approaches across different model architectures at 20-50\% compression rates. Notably, it retains over 90\% of the original model's performance at 30\% compression without any fine-tuning. Moreover, when applying a light fine-tuning phase, recovery is substantially enhanced: for instance, compressing Qwen3-14B to an 8B-parameter model and healing it with just 30 million tokens yields performance nearly on par with the original Qwen3-8B. The code for ROCKET is at github.com/mts-ai/ROCKET/tree/main.</p> + https://arxiv.org/abs/2602.11008 + Wed, 11 Feb 2026 16:34:52 +0000 + + + DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning + https://arxiv.org/abs/2602.11089 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.11089.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yicheng Chen, Zerun Ma, Xinchen Xie, Yining Li, Kai Chen</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> In the current landscape of Large Language Models (LLMs), the curation of large-scale, high-quality training data is a primary driver of model performance. A key lever is the data recipe, which comprises a data processing pipeline to transform raw sources into training corpora. Despite the growing use of LLMs to automate individual data processing steps, such as data synthesis and filtering, the overall design of data recipes remains largely manual and labor-intensive, requiring substantial human expertise and iteration. To bridge this gap, we formulate end-to-end data recipe generation for LLM adaptation. Given a target benchmark and a pool of available data sources, a model is required to output a complete data recipe that adapts a base LLM to the target task. We present DataChef-32B, which performs online reinforcement learning using a proxy reward that predicts downstream performance for candidate recipes. Across six held-out tasks, DataChef-32B produces practical recipes that reach comparable downstream performance to those curated by human experts. Notably, the recipe from DataChef-32B adapts Qwen3-1.7B-Base to the math domain, achieving 66.7 on AIME'25 and surpassing Qwen3-1.7B. This work sheds new light on automating LLM training and developing self-evolving AI systems.</p> + https://arxiv.org/abs/2602.11089 + Wed, 11 Feb 2026 17:56:15 +0000 + + + GameDevBench: Evaluating Agentic Capabilities Through Game Development + https://arxiv.org/abs/2602.11103 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.11103.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wayne Chi, Yixiong Fang, Arnav Yayavaram, Siddharth Yayavaram, Seth Karten, Qiuhong Anna Wei, Runkun Chen, Alexander Wang, Valerie Chen, Ameet Talwalkar, Chris Donahue</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Despite rapid progress on coding agents, progress on their multimodal counterparts has lagged behind. A key challenge is the scarcity of evaluation testbeds that combine the complexity of software development with the need for deep multimodal understanding. Game development provides such a testbed as agents must navigate large, dense codebases while manipulating intrinsically multimodal assets such as shaders, sprites, and animations within a visual game scene. We present GameDevBench, the first benchmark for evaluating agents on game development tasks. GameDevBench consists of 132 tasks derived from web and video tutorials. Tasks require significant multimodal understanding and are complex -- the average solution requires over three times the amount of lines of code and file changes compared to prior software development benchmarks. Agents still struggle with game development, with the best agent solving only 54.5% of tasks. We find a strong correlation between perceived task difficulty and multimodal complexity, with success rates dropping from 46.9% on gameplay-oriented tasks to 31.6% on 2D graphics tasks. To improve multimodal capability, we introduce two simple image and video-based feedback mechanisms for agents. Despite their simplicity, these methods consistently improve performance, with the largest change being an increase in Claude Sonnet 4.5's performance from 33.3% to 47.7%. We release GameDevBench publicly to support further research into agentic game development.</p> + https://arxiv.org/abs/2602.11103 + Wed, 11 Feb 2026 18:15:11 +0000 + + + PhyCritic: Multimodal Critic Models for Physical AI + https://arxiv.org/abs/2602.11124 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.11124.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyi Xiong, Shihao Wang, Guilin Liu, Yi Dong, Ming Li, Heng Huang, Jan Kautz, Zhiding Yu</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> With the rapid development of large multimodal models, reliable judge and critic models have become essential for open-ended evaluation and preference alignment, providing pairwise preferences, numerical scores, and explanatory justifications for assessing model-generated responses. However, existing critics are primarily trained in general visual domains such as captioning or image question answering, leaving physical AI tasks involving perception, causal reasoning, and planning largely underexplored. We introduce PhyCritic, a multimodal critic model optimized for physical AI through a two-stage RLVR pipeline: a physical skill warmup stage that enhances physically oriented perception and reasoning, followed by self-referential critic finetuning, where the critic generates its own prediction as an internal reference before judging candidate responses, improving judgment stability and physical correctness. Across both physical and general-purpose multimodal judge benchmarks, PhyCritic achieves strong performance gains over open-source baselines and, when applied as a policy model, further improves perception and reasoning in physically grounded tasks.</p> + https://arxiv.org/abs/2602.11124 + Wed, 11 Feb 2026 18:35:39 +0000 + + + Weight Decay Improves Language Model Plasticity + https://arxiv.org/abs/2602.11137 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.11137.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tessa Han, Sebastian Bordt, Hanlin Zhang, Sham Kakade</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The prevailing paradigm in large language model (LLM) development is to pretrain a base model, then perform further training to improve performance and model behavior. However, hyperparameter optimization and scaling laws have been studied primarily from the perspective of the base model's validation loss, ignoring downstream adaptability. In this work, we study pretraining from the perspective of model plasticity, that is, the ability of the base model to successfully adapt to downstream tasks through fine-tuning. We focus on the role of weight decay, a key regularization parameter during pretraining. Through systematic experiments, we show that models trained with larger weight decay values are more plastic, meaning they show larger performance gains when fine-tuned on downstream tasks. This phenomenon can lead to counterintuitive trade-offs where base models that perform worse after pretraining can perform better after fine-tuning. Further investigation of weight decay's mechanistic effects on model behavior reveals that it encourages linearly separable representations, regularizes attention matrices, and reduces overfitting on the training data. In conclusion, this work demonstrates the importance of using evaluation metrics beyond cross-entropy loss for hyperparameter optimization and casts light on the multifaceted role of that a single optimization hyperparameter plays in shaping model behavior.</p> + https://arxiv.org/abs/2602.11137 + Wed, 11 Feb 2026 18:49:26 +0000 + + + GENIUS: Generative Fluid Intelligence Evaluation Suite + https://arxiv.org/abs/2602.11144 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.11144.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruichuan An, Sihan Yang, Ziyu Guo, Wei Dai, Zijun Shen, Haodong Li, Renrui Zhang, Xinyu Wei, Guopeng Li, Wenshan Wu, Wentao Zhang</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Unified Multimodal Models (UMMs) have shown remarkable progress in visual generation. Yet, existing benchmarks predominantly assess Crystallized Intelligence, which relies on recalling accumulated knowledge and learned schemas. This focus overlooks Generative Fluid Intelligence (GFI): the capacity to induce patterns, reason through constraints, and adapt to novel scenarios on the fly. To rigorously assess this capability, we introduce GENIUS (GEN Fluid Intelligence EvalUation Suite). We formalize GFI as a synthesis of three primitives. These include Inducing Implicit Patterns (e.g., inferring personalized visual preferences), Executing Ad-hoc Constraints (e.g., visualizing abstract metaphors), and Adapting to Contextual Knowledge (e.g., simulating counter-intuitive physics). Collectively, these primitives challenge models to solve problems grounded entirely in the immediate context. Our systematic evaluation of 12 representative models reveals significant performance deficits in these tasks. Crucially, our diagnostic analysis disentangles these failure modes. It demonstrates that deficits stem from limited context comprehension rather than insufficient intrinsic generative capability. To bridge this gap, we propose a training-free attention intervention strategy. Ultimately, GENIUS establishes a rigorous standard for GFI, guiding the field beyond knowledge utilization toward dynamic, general-purpose reasoning. Our dataset and code will be released at: https://github.com/arctanxarc/GENIUS{https://github.com/arctanxarc/GENIUS}.</p> + https://arxiv.org/abs/2602.11144 + Wed, 11 Feb 2026 18:55:54 +0000 + + + Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning + https://arxiv.org/abs/2602.11149 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.11149.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dawid J. Kopiczko, Sagar Vaze, Tijmen Blankevoort, Yuki M. Asano</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Supervised fine-tuning (SFT) on chain-of-thought data is an essential post-training step for reasoning language models. Standard machine learning intuition suggests that training with more unique training samples yields better generalization. Counterintuitively, we show that SFT benefits from repetition: under a fixed update budget, training for more epochs on smaller datasets outperforms single-epoch training on larger datasets. On AIME'24/25 and GPQA benchmarks, Olmo3-7B trained for 128 epochs on 400 samples outperforms the equivalent 1 epoch on 51200 samples by 12-26 percentage points, with no additional catastrophic forgetting. We find that training token accuracy reliably signals when repetition has saturated; improvements from additional epochs plateau at full memorization, a pattern consistent across all settings. These findings provide a practical approach for reasoning SFT, where scaling epochs with token accuracy as a stopping criterion can replace expensive undirected data scaling. We pose the repetition advantage, where full memorization coincides with improved generalization, as a new open problem for the community in understanding the training dynamics of large language models.</p> + https://arxiv.org/abs/2602.11149 + Wed, 11 Feb 2026 18:58:54 +0000 +