bot: update RSS feed
This commit is contained in:
github-actions[bot]
556
feed.xml
556
feed.xml
@@ -7,384 +7,398 @@
|
|||||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||||
<generator>python-feedgen</generator>
|
<generator>python-feedgen</generator>
|
||||||
<language>en</language>
|
<language>en</language>
|
||||||
<lastBuildDate>Wed, 11 Feb 2026 00:08:54 +0000</lastBuildDate>
|
<lastBuildDate>Thu, 12 Feb 2026 00:04:23 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control</title>
|
<title>SHARP: Social Harm Analysis via Risk Profiles for Measuring Inequities in Large Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2601.21363</link>
|
<link>https://arxiv.org/abs/2601.21235</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.21363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weidong Huang, Zhehan Li, Hangxin Liu, Biao Hou, Yao Su, Jingwen Zhang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reinforcement learning (RL) is widely used for humanoid control, with on-policy methods such as Proximal Policy Optimization (PPO) enabling robust training via large-scale parallel simulation and, in some cases, zero-shot deployment to real robots. However, the low sample efficiency of on-policy algorithms limits safe adaptation to new environments. Although off-policy RL and model-based RL have shown improved sample efficiency, the gap between large-scale pretraining and efficient finetuning on humanoids still exists. In this paper, we find that off-policy Soft Actor-Critic (SAC), with large-batch update and a high Update-To-Data (UTD) ratio, reliably supports large-scale pretraining of humanoid locomotion policies, achieving zero-shot deployment on real robots. For adaptation, we demonstrate that these SAC-pretrained policies can be finetuned in new environments and out-of-distribution tasks using model-based methods. Data collection in the new environment executes a deterministic policy while stochastic exploration is instead confined to a physics-informed world model. This separation mitigates the risks of random exploration during adaptation while preserving exploratory coverage for improvement. Overall, the approach couples the wall-clock efficiency of large-scale simulation during pretraining with the sample efficiency of model-based learning during fine-tuning.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2601.21363</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2601.21235</guid>
|
||||||
<pubDate>Thu, 29 Jan 2026 07:43:24 +0000</pubDate>
|
<pubDate>Thu, 29 Jan 2026 03:54:25 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Towards Agentic Intelligence for Materials Science</title>
|
<title>TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation</title>
|
||||||
<link>https://arxiv.org/abs/2602.00169</link>
|
<link>https://arxiv.org/abs/2602.00268</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00169.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huan Zhang, Yizhan Li, Wenhao Huang, Ziyu Hou, Yu Song, Xuye Liu, Farshid Effaty, Jinya Jiang, Sifan Wu, Qianggang Ding, Izumi Takahara, Leonard R. MacGillivray, Teruyasu Mizoguchi, Tianshu Yu, Lizi Liao, Yuyu Luo, Yu Rong, Jia Li, Ying Diao, Heng Ji, Bang Liu</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> The convergence of artificial intelligence and materials science presents a transformative opportunity, but achieving true acceleration in discovery requires moving beyond task-isolated, fine-tuned models toward agentic systems that plan, act, and learn across the full discovery loop. This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining, through domain adaptation and instruction tuning, to goal-conditioned agents interfacing with simulation and experimental platforms. Unlike prior reviews, we treat the entire process as an end-to-end system to be optimized for tangible discovery outcomes rather than proxy benchmarks. This perspective allows us to trace how upstream design choices-such as data curation and training objectives-can be aligned with downstream experimental success through effective credit assignment. To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science. We then analyze the field through two focused lenses: From the AI perspective, the survey details LLM strengths in pattern recognition, predictive analytics, and natural language processing for literature mining, materials characterization, and property prediction; from the materials science perspective, it highlights applications in materials design, process optimization, and the acceleration of computational workflows via integration with external tools (e.g., DFT, robotic labs). Finally, we contrast passive, reactive approaches with agentic design, cataloging current contributions while motivating systems that pursue long-horizon goals with autonomy, memory, and tool use. This survey charts a practical roadmap towards autonomous, safety-aware LLM agents aimed at discovering novel and useful materials.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.00169</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.00268</guid>
|
||||||
<pubDate>Thu, 29 Jan 2026 23:48:43 +0000</pubDate>
|
<pubDate>Fri, 30 Jan 2026 19:44:16 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models</title>
|
<title>LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2602.07026</link>
|
<link>https://arxiv.org/abs/2602.00462</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07026.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaomin Yu, Yi Xin, Wenjie Zhang, Chonghan Liu, Hanzhen Zhao, Xiaoxing Hu, Xinlei Yu, Ziyue Qiao, Hao Tang, Xue Yang, Xiaobin Hu, Chengwei Qin, Hui Xiong, Yu Qiao, Shuicheng Yan</p><p><b>Upvotes:</b> 120</p><p><b>Summary:</b> Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions. Prior approaches to bridge this gap are largely limited by oversimplified isotropic assumptions, hindering their application in large-scale scenarios. In this paper, we address these limitations by precisely characterizing the geometric shape of the modality gap and leveraging it for efficient model scaling. First, we propose the Fixed-frame Modality Gap Theory, which decomposes the modality gap within a frozen reference frame into stable biases and anisotropic residuals. Guided by this precise modeling, we introduce ReAlign, a training-free modality alignment strategy. Utilizing statistics from massive unpaired data, ReAlign aligns text representation into the image representation distribution via a three-step process comprising Anchor, Trace, and Centroid Alignment, thereby explicitly rectifying geometric misalignment. Building on ReAlign, we propose ReVision, a scalable training paradigm for Multimodal Large Language Models (MLLMs). ReVision integrates ReAlign into the pretraining stage, enabling the model to learn the distribution of visual representations from unpaired text before visual instruction tuning, without the need for large-scale, high-quality image-text pairs. Our framework demonstrates that statistically aligned unpaired data can effectively substitute for expensive image-text pairs, offering a robust path for the efficient scaling of MLLMs.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07026</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.00462</guid>
|
||||||
<pubDate>Mon, 02 Feb 2026 13:59:39 +0000</pubDate>
|
<pubDate>Sat, 31 Jan 2026 02:33:07 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Statistical Learning Theory in Lean 4: Empirical Processes from Scratch</title>
|
<title>Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments</title>
|
||||||
<link>https://arxiv.org/abs/2602.02285</link>
|
<link>https://arxiv.org/abs/2602.01244</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02285.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanhe Zhang, Jason D. Lee, Fanghui Liu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our end-to-end formal infrastructure implement the missing contents in latest Lean 4 Mathlib library, including a complete development of Gaussian Lipschitz concentration, the first formalization of Dudley's entropy integral theorem for sub-Gaussian processes, and an application to least-squares (sparse) regression with a sharp rate. The project was carried out using a human-AI collaborative workflow, in which humans design proof strategies and AI agents execute tactical proof construction, leading to the human-verified Lean 4 toolbox for SLT. Beyond implementation, the formalization process exposes and resolves implicit assumptions and missing details in standard SLT textbooks, enforcing a granular, line-by-line understanding of the theory. This work establishes a reusable formal foundation and opens the door for future developments in machine learning theory. The code is available at https://github.com/YuanheZ/lean-stat-learning-theory</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.02285</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.01244</guid>
|
||||||
<pubDate>Mon, 02 Feb 2026 16:24:53 +0000</pubDate>
|
<pubDate>Sun, 01 Feb 2026 14:09:23 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Col-Bandit: Zero-Shot Query-Time Pruning for Late-Interaction Retrieval</title>
|
<title>SafePred: A Predictive Guardrail for Computer-Using Agents via World Models</title>
|
||||||
<link>https://arxiv.org/abs/2602.02827</link>
|
<link>https://arxiv.org/abs/2602.01725</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02827.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roi Pony, Adi Raz, Oshri Naparstek, Idan Friedman, Udi Barzelay</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Multi-vector late-interaction retrievers such as ColBERT achieve state-of-the-art retrieval quality, but their query-time cost is dominated by exhaustively computing token-level MaxSim interactions for every candidate document. While approximating late interaction with single-vector representations reduces cost, it often incurs substantial accuracy loss. We introduce Col-Bandit, a query-time pruning algorithm that reduces this computational burden by casting reranking as a finite-population Top-K identification problem. Col-Bandit maintains uncertainty-aware bounds over partially observed document scores and adaptively reveals only the (document, query token) MaxSim entries needed to determine the top results under statistical decision bounds with a tunable relaxation. Unlike coarse-grained approaches that prune entire documents or tokens offline, Col-Bandit sparsifies the interaction matrix on the fly. It operates as a zero-shot, drop-in layer over standard multi-vector systems, requiring no index modifications, offline preprocessing, or model retraining. Experiments on textual (BEIR) and multimodal (REAL-MM-RAG) benchmarks show that Col-Bandit preserves ranking fidelity while reducing MaxSim FLOPs by up to 5times, indicating that dense late-interaction scoring contains substantial redundancy that can be identified and pruned efficiently at query time.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.02827</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.01725</guid>
|
||||||
<pubDate>Mon, 02 Feb 2026 21:27:01 +0000</pubDate>
|
<pubDate>Mon, 02 Feb 2026 07:04:06 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Context Compression via Explicit Information Transmission</title>
|
<title>Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss</title>
|
||||||
<link>https://arxiv.org/abs/2602.03784</link>
|
<link>https://arxiv.org/abs/2602.07022</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03784.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiangnan Ye, Hanqi Yan, Zhenyi Shen, Heng Chang, Ye Mao, Yulan He</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Long-context inference with Large Language Models (LLMs) is costly due to quadratic attention and growing key-value caches, motivating context compression. In this work, we study soft context compression, where a long context is condensed into a small set of continuous representations. Existing methods typically re-purpose the LLM itself as a trainable compressor, relying on layer-by-layer self-attention to iteratively aggregate information. We argue that this paradigm suffers from two structural limitations: (i) progressive representation overwriting across layers (ii) uncoordinated allocation of compression capacity across tokens. We propose ComprExIT (Context Compression via Explicit Information Transmission), a lightweight framework that formulates soft compression into a new paradigm: explicit information transmission over frozen LLM hidden states. This decouples compression from the model's internal self-attention dynamics. ComprExIT performs (i) depth-wise transmission to selectively transmit multi-layer information into token anchors, mitigating progressive overwriting, and (ii) width-wise transmission to aggregate anchors into a small number of slots via a globally optimized transmission plan, ensuring coordinated allocation of information. Across six question-answering benchmarks, ComprExIT consistently outperforms state-of-the-art context compression methods while introducing only ~1% additional parameters, demonstrating that explicit and coordinated information transmission enables more effective and robust long-context compression.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.03784</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.07022</guid>
|
||||||
<pubDate>Tue, 03 Feb 2026 17:44:12 +0000</pubDate>
|
<pubDate>Mon, 02 Feb 2026 07:48:04 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods</title>
|
<title>From Directions to Regions: Decomposing Activations in Language Models via Local Geometry</title>
|
||||||
<link>https://arxiv.org/abs/2602.07040</link>
|
<link>https://arxiv.org/abs/2602.02464</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07040.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Emmett Bicker</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce Aster, an AI agent for autonomous scientific discovery capable of operating over 20 times faster than existing frameworks. Given a task, an initial program, and a script to evaluate the performance of the program, Aster iteratively improves the program, often leading to new state-of-the-art performances. Aster's significant reduction in the number of iterations required for novel discovery expands the domain of tractable problems to include tasks with long evaluation durations, such as multi-hour machine learning training runs. We applied Aster to problems in mathematics, GPU kernel engineering, biology, neuroscience, and language model training. More specifically: the Erdos minimum overlap problem, optimizing the TriMul kernel, a single-cell analysis denoising problem, training a neural activity prediction model to perform well on ZAPBench, and the NanoGPT Speedrun Competition. Aster attains SOTA results in every task, except for ZAPBench, where it matches the performance of the best human solution with less than 1/190th of the compute. Aster is accessible via a web interface and API at asterlab.ai.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07040</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.02464</guid>
|
||||||
<pubDate>Tue, 03 Feb 2026 19:01:23 +0000</pubDate>
|
<pubDate>Mon, 02 Feb 2026 18:49:05 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Reliable and Responsible Foundation Models: A Comprehensive Survey</title>
|
<title>DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents</title>
|
||||||
<link>https://arxiv.org/abs/2602.08145</link>
|
<link>https://arxiv.org/abs/2602.07035</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08145.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Yang, Junlin Han, Rishi Bommasani, Jinqi Luo, Wenjie Qu, Wangchunshu Zhou, Adel Bibi, Xiyao Wang, Jaehong Yoon, Elias Stengel-Eskin, Shengbang Tong, Lingfeng Shen, Rafael Rafailov, Runjia Li, Zhaoyang Wang, Yiyang Zhou, Chenhang Cui, Yu Wang, Wenhao Zheng, Huichi Zhou, Jindong Gu, Zhaorun Chen, Peng Xia, Tony Lee, Thomas Zollo, Vikash Sehwag, Jixuan Leng, Jiuhai Chen, Yuxin Wen, Huan Zhang, Zhun Deng, Linjun Zhang, Pavel Izmailov, Pang Wei Koh, Yulia Tsvetkov, Andrew Wilson, Jiaheng Zhang, James Zou, Cihang Xie, Hao Wang, Philip Torr, Julian McAuley, David Alvarez-Melis, Florian Tramèr, Kaidi Xu, Suman Jana, Chris Callison-Burch, Rene Vidal, Filippos Kokkinos, Mohit Bansal, Beidi Chen, Huaxiu Yao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with broad applications across various domains such as law, medicine, education, finance, science, and beyond. As these models see increasing real-world deployment, ensuring their reliability and responsibility has become critical for academia, industry, and government. This survey addresses the reliable and responsible development of foundation models. We explore critical issues, including bias and fairness, security and privacy, uncertainty, explainability, and distribution shift. Our research also covers model limitations, such as hallucinations, as well as methods like alignment and Artificial Intelligence-Generated Content (AIGC) detection. For each area, we review the current state of the field and outline concrete future research directions. Additionally, we discuss the intersections between these areas, highlighting their connections and shared challenges. We hope our survey fosters the development of foundation models that are not only powerful but also ethical, trustworthy, reliable, and socially responsible.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08145</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.07035</guid>
|
||||||
<pubDate>Wed, 04 Feb 2026 17:25:03 +0000</pubDate>
|
<pubDate>Tue, 03 Feb 2026 09:12:08 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization</title>
|
<title>Temporal Pair Consistency for Variance-Reduced Flow Matching</title>
|
||||||
<link>https://arxiv.org/abs/2602.07054</link>
|
<link>https://arxiv.org/abs/2602.04908</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07054.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ashutosh Chaubey, Jiacheng Pang, Maksim Siniukov, Mohammad Soleymani</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Emotion understanding is essential for building socially intelligent agents. Although recent multimodal large language models have shown strong performance on this task, two key challenges remain - spurious associations between emotions and irrelevant audiovisual cues, and hallucinations of audiovisual cues driven by text priors in the language model backbone. To quantify and understand these issues, we introduce EmoReAlM, a benchmark designed to evaluate MLLMs for cue-emotion associations, hallucinations and modality agreement. We then propose AVEm-DPO, a preference optimization technique that aligns model responses with both audiovisual inputs and emotion-centric queries. Specifically, we construct preferences over responses exhibiting spurious associations or hallucinations, and audiovisual input pairs guided by textual prompts. We also include a regularization term that penalizes reliance on text priors, thereby mitigating modality-specific cue hallucinations. Experimental results on DFEW, RAVDESS and EMER demonstrate that our method significantly improves the performance of the reference baseline models with 6-19% of relative performance gains in zero-shot settings. By providing both a rigorous benchmark and a robust optimization framework, this work enables principled evaluation and improvement of MLLMs for emotion understanding and social AI. Code, models and benchmark will be released at https://avere-iclr.github.io.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07054</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.04908</guid>
|
||||||
<pubDate>Wed, 04 Feb 2026 18:24:25 +0000</pubDate>
|
<pubDate>Wed, 04 Feb 2026 00:05:21 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?</title>
|
<title>SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models</title>
|
||||||
<link>https://arxiv.org/abs/2602.07055</link>
|
<link>https://arxiv.org/abs/2602.04208</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pingyue Zhang, Zihan Huang, Yue Wang, Jieyu Zhang, Letian Xue, Zihan Wang, Qineng Wang, Keshigeyan Chandrasegaran, Ruohan Zhang, Yejin Choi, Ranjay Krishna, Jiajun Wu, Li Fei-Fei, Manling Li</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Spatial embodied intelligence requires agents to act to acquire information under partial observability. While multimodal foundation models excel at passive perception, their capacity for active, self-directed exploration remains understudied. We propose Theory of Space, defined as an agent's ability to actively acquire information through self-directed, active exploration and to construct, revise, and exploit a spatial belief from sequential, partial observations. We evaluate this through a benchmark where the goal is curiosity-driven exploration to build an accurate cognitive map. A key innovation is spatial belief probing, which prompts models to reveal their internal spatial representations at each step. Our evaluation of state-of-the-art models reveals several critical bottlenecks. First, we identify an Active-Passive Gap, where performance drops significantly when agents must autonomously gather information. Second, we find high inefficiency, as models explore unsystematically compared to program-based proxies. Through belief probing, we diagnose that while perception is an initial bottleneck, global beliefs suffer from instability that causes spatial knowledge to degrade over time. Finally, using a false belief paradigm, we uncover Belief Inertia, where agents fail to update obsolete priors with new evidence. This issue is present in text-based agents but is particularly severe in vision-based models. Our findings suggest that current foundation models struggle to maintain coherent, revisable spatial beliefs during active exploration.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07055</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.04208</guid>
|
||||||
<pubDate>Wed, 04 Feb 2026 19:06:40 +0000</pubDate>
|
<pubDate>Wed, 04 Feb 2026 04:48:16 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration</title>
|
<title>C-ΔΘ: Circuit-Restricted Weight Arithmetic for Selective Refusal</title>
|
||||||
<link>https://arxiv.org/abs/2602.05708</link>
|
<link>https://arxiv.org/abs/2602.04521</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.05708.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chuangtao Ma, Zeyu Zhang, Arijit Khan, Sebastian Schelter, Paul Groth</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Retrieval-augmented generation (RAG) enhances LLM reasoning in knowledge-intensive tasks, but existing RAG pipelines incur substantial retrieval and generation overhead when applied to large-scale entity matching. To address this limitation, we introduce CE-RAG4EM, a cost-efficient RAG architecture that reduces computation through blocking-based batch retrieval and generation. We also present a unified framework for analyzing and evaluating RAG systems for entity matching, focusing on blocking-aware optimizations and retrieval granularity. Extensive experiments suggest that CE-RAG4EM can achieve comparable or improved matching quality while substantially reducing end-to-end runtime relative to strong baselines. Our analysis further reveals that key configuration parameters introduce an inherent trade-off between performance and overhead, offering practical guidance for designing efficient and scalable RAG systems for entity matching and data integration.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.05708</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.04521</guid>
|
||||||
<pubDate>Thu, 05 Feb 2026 14:33:00 +0000</pubDate>
|
<pubDate>Wed, 04 Feb 2026 13:10:52 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs</title>
|
<title>VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?</title>
|
||||||
<link>https://arxiv.org/abs/2602.05929</link>
|
<link>https://arxiv.org/abs/2602.04802</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.05929.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jian Chen, Zhuoran Wang, Jiayu Qin, Ming Li, Meng Wang, Changyou Chen, Yin Chen, Qizhen Weng, Yirui Liu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large language models rely on kv-caches to avoid redundant computation during autoregressive decoding, but as context length grows, reading and writing the cache can quickly saturate GPU memory bandwidth. Recent work has explored KV-cache compression, yet most approaches neglect the data-dependent nature of kv-caches and their variation across layers. We introduce KV-CoRE KV-cache Compressibility by Rank Evaluation), an SVD-based method for quantifying the data-dependent low-rank compressibility of kv-caches. KV-CoRE computes the optimal low-rank approximation under the Frobenius norm and, being gradient-free and incremental, enables efficient dataset-level, layer-wise evaluation. Using this method, we analyze multiple models and datasets spanning five English domains and sixteen languages, uncovering systematic patterns that link compressibility to model architecture, training data, and language coverage. As part of this analysis, we employ the Normalized Effective Rank as a metric of compressibility and show that it correlates strongly with performance degradation under compression. Our study establishes a principled evaluation framework and the first large-scale benchmark of kv-cache compressibility in LLMs, offering insights for dynamic, data-aware compression and data-centric model development.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.05929</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.04802</guid>
|
||||||
<pubDate>Thu, 05 Feb 2026 17:41:57 +0000</pubDate>
|
<pubDate>Wed, 04 Feb 2026 17:48:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment</title>
|
<title>Locas: Your Models are Principled Initializers of Locally-Supported Parametric Memories</title>
|
||||||
<link>https://arxiv.org/abs/2602.05946</link>
|
<link>https://arxiv.org/abs/2602.05085</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.05946.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rajdeep Haldar, Lantao Mei, Guang Lin, Yue Xing, Qifan Song</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent research shows that Preference Alignment (PA) objectives act as divergence estimators between aligned (chosen) and unaligned (rejected) response distributions. In this work, we extend this divergence-based perspective to general alignment settings, such as reinforcement learning with verifiable rewards (RLVR), where only environmental rewards are available. Within this unified framework, we propose f-Group Relative Policy Optimization (f-GRPO), a class of on-policy reinforcement learning, and f-Hybrid Alignment Loss (f-HAL), a hybrid on/off policy objectives, for general LLM alignment based on variational representation of f-divergences. We provide theoretical guarantees that these classes of objectives improve the average reward after alignment. Empirically, we validate our framework on both RLVR (Math Reasoning) and PA tasks (Safety Alignment), demonstrating superior performance and flexibility compared to current methods.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.05946</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.05085</guid>
|
||||||
<pubDate>Thu, 05 Feb 2026 18:01:52 +0000</pubDate>
|
<pubDate>Wed, 04 Feb 2026 22:09:40 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory</title>
|
<title>OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration</title>
|
||||||
<link>https://arxiv.org/abs/2602.06025</link>
|
<link>https://arxiv.org/abs/2602.05400</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06025.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haozhen Zhang, Haodong Yue, Tao Feng, Quanyu Long, Jianzhu Bao, Bowen Jin, Weizhi Zhang, Xiao Li, Jiaxuan You, Chengwei Qin, Wenya Wang</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offline, query-agnostic memory construction that can be inefficient and may discard query-critical information. Although runtime memory utilization is a natural alternative, prior work often incurs substantial overhead and offers limited explicit control over the performance-cost trade-off. In this work, we present BudgetMem, a runtime agent memory framework for explicit, query-aware performance-cost control. BudgetMem structures memory processing as a set of memory modules, each offered in three budget tiers (i.e., Low/Mid/High). A lightweight router performs budget-tier routing across modules to balance task performance and memory construction cost, which is implemented as a compact neural policy trained with reinforcement learning. Using BudgetMem as a unified testbed, we study three complementary strategies for realizing budget tiers: implementation (method complexity), reasoning (inference behavior), and capacity (module model size). Across LoCoMo, LongMemEval, and HotpotQA, BudgetMem surpasses strong baselines when performance is prioritized (i.e., high-budget setting), and delivers better accuracy-cost frontiers under tighter budgets. Moreover, our analysis disentangles the strengths and weaknesses of different tiering strategies, clarifying when each axis delivers the most favorable trade-offs under varying budget regimes.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.06025</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.05400</guid>
|
||||||
<pubDate>Thu, 05 Feb 2026 18:57:09 +0000</pubDate>
|
<pubDate>Thu, 05 Feb 2026 07:34:23 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning</title>
|
<title>Stable Velocity: A Variance Perspective on Flow Matching</title>
|
||||||
<link>https://arxiv.org/abs/2602.07075</link>
|
<link>https://arxiv.org/abs/2602.05435</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07075.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinwu Ye, Yicheng Mao, Jia Zhang, Yimeng Liu, Li Hao, Fang Wu, Zhiwei Li, Yuxuan Liao, Zehong Wang, Zhiyuan Liu, Zhenfei Yin, Li Yuan, Philip Torr, Huan Sun, Xiangxiang Zeng, Mengdi Wang, Le Cong, Shenghua Gao, Xiangru Tang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) in natural language to perform complex reasoning. However, chemical reasoning is inherently continuous and structural, and forcing it into discrete linguistic tokens introduces a fundamental representation mismatch that constrains both efficiency and performance. We introduce LatentChem, a latent reasoning interface that decouples chemical computation from textual generation, enabling models to perform multi-step reasoning directly in continuous latent space while emitting language only for final outputs. Remarkably, we observe a consistent emergent behavior: when optimized solely for task success, models spontaneously internalize reasoning, progressively abandoning verbose textual derivations in favor of implicit latent computation. This shift is not merely stylistic but computationally advantageous. Across diverse chemical reasoning benchmarks, LatentChem achieves a 59.88\% non-tie win rate over strong CoT-based baselines on ChemCoTBench, while delivering a 10.84times average inference speedup. Our results provide empirical evidence that chemical reasoning is more naturally and effectively realized as continuous latent dynamics rather than discretized linguistic trajectories.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07075</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.05435</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 01:28:27 +0000</pubDate>
|
<pubDate>Thu, 05 Feb 2026 08:25:05 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs</title>
|
<title>ContextBench: A Benchmark for Context Retrieval in Coding Agents</title>
|
||||||
<link>https://arxiv.org/abs/2602.07080</link>
|
<link>https://arxiv.org/abs/2602.05892</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07080.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yicheng He, Zheng Zhao, Zhou Kaiyu, Bryan Dai, Jie Fu, Yonghui Yang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Current paradigms for code verification rely heavily on external mechanisms-such as execution-based unit tests or auxiliary LLM judges-which are often labor-intensive or limited by the judging model's own capabilities. This raises a fundamental, yet unexplored question: Can an LLM's functional correctness be assessed purely from its internal computational structure? Our primary objective is to investigate whether the model's neural dynamics encode internally decodable signals that are predictive of logical validity during code generation. Inspired by mechanistic interpretability, we propose to treat code verification as a mechanistic diagnostic task, mapping the model's explicit algorithmic trajectory into line-level attribution graphs. By decomposing complex residual flows, we aim to identify the structural signatures that distinguish sound reasoning from logical failure within the model's internal circuits. Analysis across Python, C++, and Java confirms that intrinsic correctness signals are robust across diverse syntaxes. Topological features from these internal graphs predict correctness more reliably than surface heuristics and enable targeted causal interventions to fix erroneous logic. These findings establish internal introspection as a decodable property for verifying generated code. Our code is at https:// github.com/bruno686/CodeCircuit.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07080</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.05892</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 03:49:15 +0000</pubDate>
|
<pubDate>Thu, 05 Feb 2026 17:10:26 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO</title>
|
<title>Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding</title>
|
||||||
<link>https://arxiv.org/abs/2602.06422</link>
|
<link>https://arxiv.org/abs/2602.06161</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06422.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunze Tong, Mushui Liu, Canyu Zhao, Wanggui He, Shiyi Zhang, Hongwei Zhang, Peng Zhang, Jinlong Liu, Ju Huang, Jiamang Wang, Hao Jiang, Pipei Huang</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Deploying GRPO on Flow Matching models has proven effective for text-to-image generation. However, existing paradigms typically propagate an outcome-based reward to all preceding denoising steps without distinguishing the local effect of each step. Moreover, current group-wise ranking mainly compares trajectories at matched timesteps and ignores within-trajectory dependencies, where certain early denoising actions can affect later states via delayed, implicit interactions. We propose TurningPoint-GRPO (TP-GRPO), a GRPO framework that alleviates step-wise reward sparsity and explicitly models long-term effects within the denoising trajectory. TP-GRPO makes two key innovations: (i) it replaces outcome-based rewards with step-level incremental rewards, providing a dense, step-aware learning signal that better isolates each denoising action's "pure" effect, and (ii) it identifies turning points-steps that flip the local reward trend and make subsequent reward evolution consistent with the overall trajectory trend-and assigns these actions an aggregated long-term reward to capture their delayed impact. Turning points are detected solely via sign changes in incremental rewards, making TP-GRPO efficient and hyperparameter-free. Extensive experiments also demonstrate that TP-GRPO exploits reward signals more effectively and consistently improves generation. Demo code is available at https://github.com/YunzeTong/TurningPoint-GRPO.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.06422</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.06161</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 06:37:10 +0000</pubDate>
|
<pubDate>Thu, 05 Feb 2026 19:58:48 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking</title>
|
<title>ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training</title>
|
||||||
<link>https://arxiv.org/abs/2602.06445</link>
|
<link>https://arxiv.org/abs/2602.06820</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06445.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weidong Huang, Jingwen Zhang, Jiongye Li, Shibowen Zhang, Jiayang Wu, Jiayi Wang, Hangxin Liu, Yaodong Yang, Yao Su</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Achieving stable and energy-efficient locomotion is essential for humanoid robots to operate continuously in real-world applications. Existing MPC and RL approaches often rely on energy-related metrics embedded within a multi-objective optimization framework, which require extensive hyperparameter tuning and often result in suboptimal policies. To address these challenges, we propose ECO (Energy-Constrained Optimization), a constrained RL framework that separates energy-related metrics from rewards, reformulating them as explicit inequality constraints. This method provides a clear and interpretable physical representation of energy costs, enabling more efficient and intuitive hyperparameter tuning for improved energy efficiency. ECO introduces dedicated constraints for energy consumption and reference motion, enforced by the Lagrangian method, to achieve stable, symmetric, and energy-efficient walking for humanoid robots. We evaluated ECO against MPC, standard RL with reward shaping, and four state-of-the-art constrained RL methods. Experiments, including sim-to-sim and sim-to-real transfers on the kid-sized humanoid robot BRUCE, demonstrate that ECO significantly reduces energy consumption compared to baselines while maintaining robust walking performance. These results highlight a substantial advancement in energy-efficient humanoid locomotion. All experimental demonstrations can be found on the project website: https://sites.google.com/view/eco-humanoid.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.06445</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.06820</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 07:14:43 +0000</pubDate>
|
<pubDate>Fri, 06 Feb 2026 16:05:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>RelayGen: Intra-Generation Model Switching for Efficient Reasoning</title>
|
<title>ANCHOR: Branch-Point Data Generation for GUI Agents</title>
|
||||||
<link>https://arxiv.org/abs/2602.06454</link>
|
<link>https://arxiv.org/abs/2602.07153</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06454.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiwon Song, Yoongon Kim, Jae-Joon Kim</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks by generating long, multi-step reasoning trajectories, but inference-time scaling incurs substantial deployment cost. A key challenge is that generation difficulty varies within a single output, whereas existing efficiency-oriented approaches either ignore this intra-generation variation or rely on supervised token-level routing with high system complexity. We present RelayGen, a training-free, segment-level runtime model switching framework that exploits difficulty variation in long-form reasoning. Through offline analysis of generation uncertainty using token probability margins, we show that coarse-grained segment-level control is sufficient to capture difficulty transitions within a reasoning trajectory. RelayGen identifies model-specific switch cues that signal transitions to lower-difficulty segments and dynamically delegates their continuation to a smaller model, while preserving high-difficulty reasoning on the large model. Across multiple reasoning benchmarks, RelayGen substantially reduces inference latency while preserving most of the accuracy of large models. When combined with speculative decoding, RelayGen achieves up to 2.2times end-to-end speedup with less than 2\% accuracy degradation, without requiring additional training or learned routing components.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.06454</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.07153</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 07:35:01 +0000</pubDate>
|
<pubDate>Fri, 06 Feb 2026 19:55:26 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining</title>
|
<title>Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2602.07085</link>
|
<link>https://arxiv.org/abs/2602.07276</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07085.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jun Han, Shuo Zhang, Wei Li, Zhi Yang, Yifan Dong, Tu Hu, Jialuo Yuan, Xiaomin Yu, Yumo Zhu, Fangqi Lou, Xin Guo, Zhaowei Liu, Tianyi Jiang, Ruichuan An, Jingping Liu, Biao Wu, Rongze Chen, Kunyi Wang, Yifan Wang, Sen Hu, Xinbing Kong, Liwen Zhang, Ronghao Chen, Huacan Wang</p><p><b>Upvotes:</b> 140</p><p><b>Summary:</b> Financial markets are noisy and non-stationary, making alpha mining highly sensitive to noise in backtesting results and sudden market regime shifts. While recent agentic frameworks improve alpha mining automation, they often lack controllable multi-round search and reliable reuse of validated experience. To address these challenges, we propose QuantaAlpha, an evolutionary alpha mining framework that treats each end-to-end mining run as a trajectory and improves factors through trajectory-level mutation and crossover operations. QuantaAlpha localizes suboptimal steps in each trajectory for targeted revision and recombines complementary high-reward segments to reuse effective patterns, enabling structured exploration and refinement across mining iterations. During factor generation, QuantaAlpha enforces semantic consistency across the hypothesis, factor expression, and executable code, while constraining the complexity and redundancy of the generated factor to mitigate crowding. Extensive experiments on the China Securities Index 300 (CSI 300) demonstrate consistent gains over strong baseline models and prior agentic systems. When utilizing GPT-5.2, QuantaAlpha achieves an Information Coefficient (IC) of 0.1501, with an Annualized Rate of Return (ARR) of 27.75% and a Maximum Drawdown (MDD) of 7.98%. Moreover, factors mined on CSI 300 transfer effectively to the China Securities Index 500 (CSI 500) and the Standard & Poor's 500 Index (S&P 500), delivering 160% and 137% cumulative excess return over four years, respectively, which indicates strong robustness of QuantaAlpha under market distribution shifts.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07085</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.07276</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 08:08:04 +0000</pubDate>
|
<pubDate>Sat, 07 Feb 2026 00:00:50 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks</title>
|
<title>AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management</title>
|
||||||
<link>https://arxiv.org/abs/2602.07090</link>
|
<link>https://arxiv.org/abs/2602.07398</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07090.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu-Che Tsai, Hsiang Hsiao, Kuan-Yu Chen, Shou-De Lin</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Text embeddings enable numerous NLP applications but face severe privacy risks from embedding inversion attacks, which can expose sensitive attributes or reconstruct raw text. Existing differential privacy defenses assume uniform sensitivity across embedding dimensions, leading to excessive noise and degraded utility. We propose SPARSE, a user-centric framework for concept-specific privacy protection in text embeddings. SPARSE combines (1) differentiable mask learning to identify privacy-sensitive dimensions for user-defined concepts, and (2) the Mahalanobis mechanism that applies elliptical noise calibrated by dimension sensitivity. Unlike traditional spherical noise injection, SPARSE selectively perturbs privacy-sensitive dimensions while preserving non-sensitive semantics. Evaluated across six datasets with three embedding models and attack scenarios, SPARSE consistently reduces privacy leakage while achieving superior downstream performance compared to state-of-the-art DP methods.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07090</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.07398</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 09:28:55 +0000</pubDate>
|
<pubDate>Sat, 07 Feb 2026 06:28:51 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research</title>
|
<title>Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model</title>
|
||||||
<link>https://arxiv.org/abs/2602.06540</link>
|
<link>https://arxiv.org/abs/2602.07422</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06540.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yishan Li, Wentong Chen, Yukun Yan, Mingwei Li, Sen Mei, Xiaorong Wang, Kunpeng Liu, Xin Cong, Shuo Wang, Zhong Zhang, Yaxi Lu, Zhenghao Liu, Yankai Lin, Zhiyuan Liu, Maosong Sun</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Generating deep research reports requires large-scale information acquisition and the synthesis of insight-driven analysis, posing a significant challenge for current language models. Most existing approaches follow a plan-then-write paradigm, whose performance heavily depends on the quality of the initial outline. However, constructing a comprehensive outline itself demands strong reasoning ability, causing current deep research systems to rely almost exclusively on closed-source or online large models. This reliance raises practical barriers to deployment and introduces safety and privacy concerns for user-authored data. In this work, we present AgentCPM-Report, a lightweight yet high-performing local solution composed of a framework that mirrors the human writing process and an 8B-parameter deep research agent. Our framework uses a Writing As Reasoning Policy (WARP), which enables models to dynamically revise outlines during report generation. Under this policy, the agent alternates between Evidence-Based Drafting and Reasoning-Driven Deepening, jointly supporting information acquisition, knowledge refinement, and iterative outline evolution. To effectively equip small models with this capability, we introduce a Multi-Stage Agentic Training strategy, consisting of cold-start, atomic skill RL, and holistic pipeline RL. Experiments on DeepResearch Bench, DeepConsult, and DeepResearch Gym demonstrate that AgentCPM-Report outperforms leading closed-source systems, with substantial gains in Insight.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.06540</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.07422</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 09:45:04 +0000</pubDate>
|
<pubDate>Sat, 07 Feb 2026 07:42:07 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning</title>
|
<title>Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation</title>
|
||||||
<link>https://arxiv.org/abs/2602.06600</link>
|
<link>https://arxiv.org/abs/2602.07670</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06600.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuoyuan Hao, Zhuo Li, Wu Li, Fangming Liu, Min Zhang, Jing Li</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Test-time compute allocation in large reasoning models (LRMs) is widely used and has applications in mathematical problem solving, code synthesis, and planning. Recent work has addressed this problem by scaling self-consistency and parallel thinking, adding generic ``thinking tokens'' and prompting models to re-read the question before answering. Unfortunately, these approaches either inject task-agnostic tokens or mandate heuristics that do not explain -- and often ignore -- the spontaneous repetition that many LRMs exhibit at the head of their internal chains. In contrast, we analyze and harness the model's tendency to restate the question, which we term the Echo of Prompt (EOP), as a front-loaded, compute-shaping mechanism. We formalize its probabilistic cost by casting echo removal as rejection-based conditioning and defining the Echo Likelihood Gap ΔL as a computable proxy. This provides the missing theoretical link that links early repetition to likelihood gains and downstream accuracy. However, it does not by itself specify how to exploit EOP. Consequently, we develop Echo-Distilled SFT (ED-SFT) to instill an ``echo-then-reason'' pattern through supervised finetuning, and Echoic Prompting (EP) to re-ground the model mid-trace without training. While promising, quantifying benefits beyond verbosity is non-trivial. Therefore, we conduct length and suffix-controlled likelihood analyses together with layer-wise attention studies, showing that EOP increases answer to answer-prefix attention in middle layers, consistent with an attention refocusing mechanism. We evaluate on GSM8K, MathQA, Hendrycks-MATH, AIME24, and MATH-500 under identical decoding settings and budgets, and find consistent gains over baselines. Code is available at https://github.com/hhh2210/echoes-as-anchors.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.06600</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.07670</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 10:53:26 +0000</pubDate>
|
<pubDate>Sat, 07 Feb 2026 19:29:07 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models</title>
|
<title>Learning to Continually Learn via Meta-learning Agentic Memory Designs</title>
|
||||||
<link>https://arxiv.org/abs/2602.06694</link>
|
<link>https://arxiv.org/abs/2602.07755</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06694.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyochan Chong, Dongkyu Kim, Changdong Kim, Minseop Choi</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Weight-only quantization has become a standard approach for efficiently serving large language models (LLMs). However, existing methods fail to efficiently compress models to binary (1-bit) levels, as they either require large amounts of data and compute or incur additional storage. In this work, we propose NanoQuant, the first post-training quantization (PTQ) method to compress LLMs to both binary and sub-1-bit levels. NanoQuant formulates quantization as a low-rank binary factorization problem, and compresses full-precision weights to low-rank binary matrices and scales. Specifically, it utilizes an efficient alternating direction method of multipliers (ADMM) method to precisely initialize latent binary matrices and scales, and then tune the initialized parameters through a block and model reconstruction process. Consequently, NanoQuant establishes a new Pareto frontier in low-memory post-training quantization, achieving state-of-the-art accuracy even at sub-1-bit compression rates. NanoQuant makes large-scale deployment feasible on consumer hardware. For example, it compresses Llama2-70B by 25.8times in just 13 hours on a single H100, enabling a 70B model to operate on a consumer 8 GB GPU.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.06694</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.07755</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 13:26:44 +0000</pubDate>
|
<pubDate>Sun, 08 Feb 2026 01:20:49 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents</title>
|
<title>TodoEvolve: Learning to Architect Agent Planning Systems</title>
|
||||||
<link>https://arxiv.org/abs/2602.06855</link>
|
<link>https://arxiv.org/abs/2602.07839</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06855.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alisia Lupidi, Bhavul Gauri, Thomas Simon Foster, Bassel Al Omari, Despoina Magka, Alberto Pepe, Alexis Audran-Reiss, Muna Aghamelu, Nicolas Baldwin, Lucia Cipolina-Kun, Jean-Christophe Gagnon-Audet, Chee Hau Leow, Sandra Lefdal, Hossam Mossalam, Abhinav Moudgil, Saba Nazir, Emanuel Tewolde, Isabel Urrego, Jordi Armengol Estape, Amar Budhiraja, Gaurav Chaurasia, Abhishek Charnalia, Derek Dunfield, Karen Hambardzumyan, Daniel Izcovich, Martin Josifoski, Ishita Mediratta, Kelvin Niu, Parth Pathak, Michael Shvartsman, Edan Toledo, Anton Protopopov, Roberta Raileanu, Alexander Miller, Tatiana Shavrina, Jakob Foerster, Yoram Bachrach</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> LLM agents hold significant promise for advancing scientific research. To accelerate this progress, we introduce AIRS-Bench (the AI Research Science Benchmark), a suite of 20 tasks sourced from state-of-the-art machine learning papers. These tasks span diverse domains, including language modeling, mathematics, bioinformatics, and time series forecasting. AIRS-Bench tasks assess agentic capabilities over the full research lifecycle -- including idea generation, experiment analysis and iterative refinement -- without providing baseline code. The AIRS-Bench task format is versatile, enabling easy integration of new tasks and rigorous comparison across different agentic frameworks. We establish baselines using frontier models paired with both sequential and parallel scaffolds. Our results show that agents exceed human SOTA in four tasks but fail to match it in sixteen others. Even when agents surpass human benchmarks, they do not reach the theoretical performance ceiling for the underlying tasks. These findings indicate that AIRS-Bench is far from saturated and offers substantial room for improvement. We open-source the AIRS-Bench task definitions and evaluation code to catalyze further development in autonomous scientific research.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.06855</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.07839</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 16:45:02 +0000</pubDate>
|
<pubDate>Sun, 08 Feb 2026 06:37:01 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Optimal Turkish Subword Strategies at Scale: Systematic Evaluation of Data, Vocabulary, Morphology Interplay</title>
|
<title>CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution</title>
|
||||||
<link>https://arxiv.org/abs/2602.06942</link>
|
<link>https://arxiv.org/abs/2602.07918</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06942.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Duygu Altinok</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Tokenization is a pivotal design choice for neural language modeling in morphologically rich languages (MRLs) such as Turkish, where productive agglutination challenges both vocabulary efficiency and morphological fidelity. Prior studies have explored tokenizer families and vocabulary sizes but typically (i) vary vocabulary without systematically controlling the tokenizer's training corpus, (ii) provide limited intrinsic diagnostics, and (iii) evaluate a narrow slice of downstream tasks. We present the first comprehensive, principled study of Turkish subword tokenization; a "subwords manifest", that jointly varies vocabulary size and tokenizer training corpus size (data and vocabulary coupling), compares multiple tokenizer families under matched parameter budgets (WordPiece, morphology level, and character baselines), and evaluates across semantic (NLI, STS, sentiment analysis, NER), syntactic (POS, dependency parsing), and morphology-sensitive probes. To explain why tokenizers succeed or fail, we introduce a morphology-aware diagnostic toolkit that goes beyond coarse aggregates to boundary-level micro/macro F1, decoupled lemma atomicity vs. surface boundary hits, over/under-segmentation indices, character/word edit distances (CER/WER), continuation rates, and affix-type coverage and token-level atomicity. Our contributions are fourfold: (i) a systematic investigation of the vocabulary-corpus-success triad; (ii) a unified, morphology-aware evaluation framework linking intrinsic diagnostics to extrinsic outcomes; (iii) controlled comparisons identifying when character-level and morphology-level tokenization pay off; and (iv) an open-source release of evaluation code, tokenizer pipelines, and models. As the first work of its kind, this "subwords manifest" delivers actionable guidance for building effective tokenizers in MRLs and establishes a reproducible foundation for future research.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.06942</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.07918</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 18:41:14 +0000</pubDate>
|
<pubDate>Sun, 08 Feb 2026 11:34:08 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model</title>
|
<title>SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning</title>
|
||||||
<link>https://arxiv.org/abs/2602.07120</link>
|
<link>https://arxiv.org/abs/2602.08234</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07120.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jacqueline He, Jonathan Hayase, Wen-tau Yih, Sewoong Oh, Luke Zettlemoyer, Pang Wei Koh</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Modern language models (LMs) tend to memorize portions of their training data and emit verbatim spans. When the underlying sources are sensitive or copyright-protected, such reproduction raises issues of consent and compensation for creators and compliance risks for developers. We propose Anchored Decoding, a plug-and-play inference-time method for suppressing verbatim copying: it enables decoding from any risky LM trained on mixed-license data by keeping generation in bounded proximity to a permissively trained safe LM. Anchored Decoding adaptively allocates a user-chosen information budget over the generation trajectory and enforces per-step constraints that yield a sequence-level guarantee, enabling a tunable risk-utility trade-off. To make Anchored Decoding practically useful, we introduce a new permissively trained safe model (TinyComma 1.8B), as well as Anchored_{Byte} Decoding, a byte-level variant of our method that enables cross-vocabulary fusion via the ByteSampler framework (Hayase et al., 2025). We evaluate our methods across six model pairs on long-form evaluations of copyright risk and utility. Anchored and Anchored_{Byte} Decoding define a new Pareto frontier, preserving near-original fluency and factuality while eliminating up to 75% of the measurable copying gap (averaged over six copying metrics) between the risky baseline and a safe reference, at a modest inference overhead.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07120</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.08234</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 19:00:14 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 03:17:17 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Reasoning-Augmented Representations for Multimodal Retrieval</title>
|
<title>OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration</title>
|
||||||
<link>https://arxiv.org/abs/2602.07125</link>
|
<link>https://arxiv.org/abs/2602.08344</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07125.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianrui Zhang, Anirudh Sundara Rajan, Brandon Han, Soochahn Lee, Sukanta Ganguly, Yong Jae Lee</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Universal Multimodal Retrieval (UMR) seeks any-to-any search across text and vision, yet modern embedding models remain brittle when queries require latent reasoning (e.g., resolving underspecified references or matching compositional constraints). We argue this brittleness is often data-induced: when images carry "silent" evidence and queries leave key semantics implicit, a single embedding pass must both reason and compress, encouraging spurious feature matching. We propose a data-centric framework that decouples these roles by externalizing reasoning before retrieval. Using a strong Vision--Language Model, we make implicit semantics explicit by densely captioning visual evidence in corpus entries, resolving ambiguous multimodal references in queries, and rewriting verbose instructions into concise retrieval constraints. Inference-time enhancement alone is insufficient; the retriever must be trained on these semantically dense representations to avoid distribution shift and fully exploit the added signal. Across M-BEIR, our reasoning-augmented training method yields consistent gains over strong baselines, with ablations showing that corpus enhancement chiefly benefits knowledge-intensive queries while query enhancement is critical for compositional modification requests. We publicly release our code at https://github.com/AugmentedRetrieval/ReasoningAugmentedRetrieval.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07125</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.08344</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 19:01:54 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 07:29:13 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>On Randomness in Agentic Evals</title>
|
<title>Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning</title>
|
||||||
<link>https://arxiv.org/abs/2602.07150</link>
|
<link>https://arxiv.org/abs/2602.08382</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07150.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bjarni Haukur Bjarnason, André Silva, Martin Monperrus</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this assumption by collecting 60,000 agentic trajectories on SWE-Bench-Verified, spanning three models and two scaffolds. We find substantial variance: single-run pass@1 estimates vary by 2.2 to 6.0 percentage points depending on which run is selected, with standard deviations exceeding 1.5 percentage points even at temperature 0. This variance has critical implications: reported improvements of 2--3 percentage points may reflect evaluation noise rather than genuine algorithmic progress. Through token-level analysis, we show that trajectories diverge early, often within the first few percent of tokens, and that these small differences cascade into different solution strategies. To enable reliable evaluation of agentic systems, we recommend three concrete practices: (1) estimate pass@1 from multiple independent runs per task, especially when measuring small improvements, (2) use statistical power analysis to determine the number of runs needed to detect expected effect sizes, and (3) consider metrics like pass@k (optimistic bound) and pass^k (pessimistic bound) with k>1 to better characterize the full performance envelope. While these practices increase evaluation cost, they are essential for distinguishing genuine scientific progress from statistical noise.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07150</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.08382</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 19:49:13 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 08:33:11 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design</title>
|
<title>Prism: Spectral-Aware Block-Sparse Attention</title>
|
||||||
<link>https://arxiv.org/abs/2602.07491</link>
|
<link>https://arxiv.org/abs/2602.08426</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07491.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Isabella A. Stewart, Tarjei Paule Hage, Yu-Chuan Hsu, Markus J. Buehler</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large Language Models (LLMs) promise to accelerate discovery by reasoning across the expanding scientific landscape. Yet, the challenge is no longer access to information but connecting it in meaningful, domain-spanning ways. In materials science, where innovation demands integrating concepts from molecular chemistry to mechanical performance, this is especially acute. Neither humans nor single-agent LLMs can fully contend with this torrent of information, with the latter often prone to hallucinations. To address this bottleneck, we introduce a multi-agent framework guided by large-scale knowledge graphs to find sustainable substitutes for per- and polyfluoroalkyl substances (PFAS)-chemicals currently under intense regulatory scrutiny. Agents in the framework specialize in problem decomposition, evidence retrieval, design parameter extraction, and graph traversal, uncovering latent connections across distinct knowledge pockets to support hypothesis generation. Ablation studies show that the full multi-agent pipeline outperforms single-shot prompting, underscoring the value of distributed specialization and relational reasoning. We demonstrate that by tailoring graph traversal strategies, the system alternates between exploitative searches focusing on domain-critical outcomes and exploratory searches surfacing emergent cross-connections. Illustrated through the exemplar of biomedical tubing, the framework generates sustainable PFAS-free alternatives that balance tribological performance, thermal stability, chemical resistance, and biocompatibility. This work establishes a framework combining knowledge graphs with multi-agent reasoning to expand the materials design space, showcasing several initial design candidates to demonstrate the approach.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07491</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.08426</guid>
|
||||||
<pubDate>Sat, 07 Feb 2026 10:50:34 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 09:31:06 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion</title>
|
<title>Learning Self-Correction in Vision-Language Models via Rollout Augmentation</title>
|
||||||
<link>https://arxiv.org/abs/2602.07775</link>
|
<link>https://arxiv.org/abs/2602.08503</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07775.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haodong Li, Shaoteng Liu, Zhe Lin, Manmohan Chandraker</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Recently, autoregressive (AR) video diffusion models has achieved remarkable performance. However, due to their limited training durations, a train-test gap emerges when testing at longer horizons, leading to rapid visual degradations. Following Self Forcing, which studies the train-test gap within the training duration, this work studies the train-test gap beyond the training duration, i.e., the gap between the limited horizons during training and open-ended horizons during testing. Since open-ended testing can extend beyond any finite training window, and long-video training is computationally expensive, we pursue a training-free solution to bridge this gap. To explore a training-free solution, we conduct a systematic analysis of AR cache maintenance. These insights lead to Rolling Sink. Built on Self Forcing (trained on only 5s clips), Rolling Sink effectively scales the AR video synthesis to ultra-long durations (e.g., 5-30 minutes at 16 FPS) at test time, with consistent subjects, stable colors, coherent structures, and smooth motions. As demonstrated by extensive experiments, Rolling Sink achieves superior long-horizon visual fidelity and temporal consistency compared to SOTA baselines. Project page: https://rolling-sink.github.io/</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07775</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.08503</guid>
|
||||||
<pubDate>Sun, 08 Feb 2026 02:16:02 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 10:55:13 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Thinking Makes LLM Agents Introverted: How Mandatory Thinking Can Backfire in User-Engaged Agents</title>
|
<title>Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering</title>
|
||||||
<link>https://arxiv.org/abs/2602.07796</link>
|
<link>https://arxiv.org/abs/2602.08519</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07796.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiatong Li, Changdae Oh, Hyeong Kyu Choi, Jindong Wang, Sharon Li</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Eliciting reasoning has emerged as a powerful technique for improving the performance of large language models (LLMs) on complex tasks by inducing thinking. However, their effectiveness in realistic user-engaged agent scenarios remains unclear. In this paper, we conduct a comprehensive study on the effect of explicit thinking in user-engaged LLM agents. Our experiments span across seven models, three benchmarks, and two thinking instantiations, and we evaluate them through both a quantitative response taxonomy analysis and qualitative failure propagation case studies. Contrary to expectations, we find that mandatory thinking often backfires on agents in user-engaged settings, causing anomalous performance degradation across various LLMs. Our key finding reveals that thinking makes agents more ``introverted'' by shortening responses and reducing information disclosure to users, which weakens agent-user information exchange and leads to downstream task failures. Furthermore, we demonstrate that explicitly prompting for information disclosure reliably improves performance across diverse model families, suggesting that proactive transparency is a vital lever for agent optimization. Overall, our study suggests that information transparency awareness is a crucial yet underexplored perspective for the future design of reasoning agents in real-world scenarios. Our code is available at https://github.com/deeplearning-wisc/Thinking-Agent.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07796</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.08519</guid>
|
||||||
<pubDate>Sun, 08 Feb 2026 03:23:22 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 11:07:24 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis</title>
|
<title>Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems</title>
|
||||||
<link>https://arxiv.org/abs/2602.07803</link>
|
<link>https://arxiv.org/abs/2602.08847</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiale Qian, Hao Meng, Tian Zheng, Pengcheng Zhu, Haopeng Lin, Yuhang Dai, Hanke Xie, Wenxiao Cao, Ruixuan Shang, Jun Wu, Hongmei Liu, Hanlin Wen, Jian Zhao, Zhonglin Jiang, Yong Chen, Shunshun Yin, Ming Tao, Jianguo Wei, Lei Xie, Xinsheng Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> While recent years have witnessed rapid progress in speech synthesis, open-source singing voice synthesis (SVS) systems still face significant barriers to industrial deployment, particularly in terms of robustness and zero-shot generalization. In this report, we introduce SoulX-Singer, a high-quality open-source SVS system designed with practical deployment considerations in mind. SoulX-Singer supports controllable singing generation conditioned on either symbolic musical scores (MIDI) or melodic representations, enabling flexible and expressive control in real-world production workflows. Trained on more than 42,000 hours of vocal data, the system supports Mandarin Chinese, English, and Cantonese and consistently achieves state-of-the-art synthesis quality across languages under diverse musical conditions. Furthermore, to enable reliable evaluation of zero-shot SVS performance in practical scenarios, we construct SoulX-Singer-Eval, a dedicated benchmark with strict training-test disentanglement, facilitating systematic assessment in zero-shot settings.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07803</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.08847</guid>
|
||||||
<pubDate>Sun, 08 Feb 2026 03:51:23 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 16:13:39 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning</title>
|
<title>UI-Venus-1.5 Technical Report</title>
|
||||||
<link>https://arxiv.org/abs/2602.07845</link>
|
<link>https://arxiv.org/abs/2602.09082</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07845.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yalcin Tur, Jalal Naghiyev, Haoquan Fang, Wei-Chuan Tsai, Jiafei Duan, Dieter Fox, Ranjay Krishna</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Current Vision-Language-Action (VLA) models rely on fixed computational depth, expending the same amount of compute on simple adjustments and complex multi-step manipulation. While Chain-of-Thought (CoT) prompting enables variable computation, it scales memory linearly and is ill-suited for continuous action spaces. We introduce Recurrent-Depth VLA (RD-VLA), an architecture that achieves computational adaptivity via latent iterative refinement rather than explicit token generation. RD-VLA employs a recurrent, weight-tied action head that supports arbitrary inference depth with a constant memory footprint. The model is trained using truncated backpropagation through time (TBPTT) to efficiently supervise the refinement process. At inference, RD-VLA dynamically allocates compute using an adaptive stopping criterion based on latent convergence. Experiments on challenging manipulation tasks show that recurrent depth is critical: tasks that fail entirely (0 percent success) with single-iteration inference exceed 90 percent success with four iterations, while simpler tasks saturate rapidly. RD-VLA provides a scalable path to test-time compute in robotics, replacing token-based reasoning with latent reasoning to achieve constant memory usage and up to 80x inference speedup over prior reasoning-based VLA models. Project page: https://rd-vla.github.io/</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07845</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09082</guid>
|
||||||
<pubDate>Sun, 08 Feb 2026 07:21:01 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 18:43:40 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>dewi-kadita: A Python Library for Idealized Fish Schooling Simulation with Entropy-Based Diagnostics</title>
|
<title>iGRPO: Self-Feedback-Driven LLM Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2602.07948</link>
|
<link>https://arxiv.org/abs/2602.09000</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07948.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sandy H. S. Herho, Iwan P. Anwar, Faruq Khadami, Alfita P. Handayani, Karina A. Sujatmiko, Kamaluddin Kasim, Rusmawan Suwarman, Dasapta E. Irawan</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Collective motion in fish schools exemplifies emergent self-organization in active matter systems, yet computational tools for simulating and analyzing these dynamics remain fragmented across research groups. We present dewi-kadita, an open-source Python library implementing the three-dimensional Couzin zone-based model with comprehensive entropy diagnostics tailored for marine collective behavior research. The library introduces seven information-theoretic metrics -- school cohesion entropy, polarization entropy, depth stratification entropy, angular momentum entropy, nearest-neighbor entropy, velocity correlation entropy, and school shape entropy -- that characterize distinct organizational features inaccessible to classical order parameters. These metrics combine into an Oceanic Schooling Index (OSI) providing a single scalar measure of collective disorder. Validation across four canonical configurations (swarm, torus, dynamic parallel, highly parallel) confirms correct reproduction of known phase behaviors: the swarm maintains disorder with polarization P < 0.1 and OSI approx 0.71, while the highly parallel state achieves P = 0.998 with OSI = 0.24 and velocity correlation entropy vanishing to zero. The entropy framework successfully discriminates the torus and dynamic parallel configurations that exhibit comparable order parameter magnitudes through different organizational mechanisms. Numba just-in-time (JIT) compilation accelerates pairwise interaction calculations by 10--100times, enabling simulations of 150--250 agents over 1000--2000 time steps within five minutes on standard workstation hardware. NetCDF4 output ensures interoperability with oceanographic analysis tools. The library addresses the need for standardized, reproducible infrastructure in collective behavior modeling analogous to established molecular dynamics codes.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07948</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09000</guid>
|
||||||
<pubDate>Sun, 08 Feb 2026 12:43:59 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 18:45:11 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth</title>
|
<title>Contact-Anchored Policies: Contact Conditioning Creates Strong Robot Utility Models</title>
|
||||||
<link>https://arxiv.org/abs/2602.07962</link>
|
<link>https://arxiv.org/abs/2602.09017</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07962.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weihao Zeng, Yuzhen Huang, Junxian He</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Large language models (LLMs) are increasingly capable of carrying out long-running, real-world tasks. However, as the amount of context grows, their reliability often deteriorates, a phenomenon known as "context rot". Existing long-context benchmarks primarily focus on single-step settings that evaluate a model's ability to retrieve information from a long snippet. In realistic scenarios, however, LLMs often need to act as agents that explore environments, follow instructions and plans, extract useful information, and predict correct actions under a dynamically growing context. To assess language agents in such settings, we introduce LOCA-bench (a benchmark for LOng-Context Agents). Given a task prompt, LOCA-bench leverages automated and scalable control of environment states to regulate the agent's context length. This design enables LOCA-bench to extend the context length potentially to infinity in a controlled way while keeping the underlying task semantics fixed. LOCA-bench evaluates language agents as a combination of models and scaffolds, including various context management strategies. While agent performance generally degrades as the environment states grow more complex, advanced context management techniques can substantially improve the overall success rate. We open-source LOCA-bench to provide a platform for evaluating models and scaffolds in long-context, agentic scenarios: https://github.com/hkust-nlp/LOCA-bench</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07962</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09017</guid>
|
||||||
<pubDate>Sun, 08 Feb 2026 13:20:39 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 18:58:50 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Learning-guided Kansa collocation for forward and inverse PDEs beyond linearity</title>
|
<title>Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling</title>
|
||||||
<link>https://arxiv.org/abs/2602.07970</link>
|
<link>https://arxiv.org/abs/2602.09084</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.07970.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zheyuan Hu, Weitao Chen, Cengiz Öztireli, Chenliang Zhou, Fangcheng Zhong</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Partial Differential Equations are precise in modelling the physical, biological and graphical phenomena. However, the numerical methods suffer from the curse of dimensionality, high computation costs and domain-specific discretization. We aim to explore pros and cons of different PDE solvers, and apply them to specific scientific simulation problems, including forwarding solution, inverse problems and equations discovery. In particular, we extend the recent CNF (NeurIPS 2023) framework solver to multi-dependent-variable and non-linear settings, together with down-stream applications. The outcomes include implementation of selected methods, self-tuning techniques, evaluation on benchmark problems and a comprehensive survey of neural PDE solvers and scientific simulation applications.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.07970</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09084</guid>
|
||||||
<pubDate>Sun, 08 Feb 2026 13:44:36 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 18:59:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality</title>
|
<title>Autoregressive Image Generation with Masked Bit Modeling</title>
|
||||||
<link>https://arxiv.org/abs/2602.08004</link>
|
<link>https://arxiv.org/abs/2602.09024</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08004.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> George Ling, Shanshan Zhong, Richard Huang</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Agent skills extend large language model (LLM) agents with reusable, program-like modules that define triggering conditions, procedural logic, and tool interactions. As these skills proliferate in public marketplaces, it is unclear what types are available, how users adopt them, and what risks they pose. To answer these questions, we conduct a large-scale, data-driven analysis of 40,285 publicly listed skills from a major marketplace. Our results show that skill publication tends to occur in short bursts that track shifts in community attention. We also find that skill content is highly concentrated in software engineering workflows, while information retrieval and content creation account for a substantial share of adoption. Beyond content trends, we uncover a pronounced supply-demand imbalance across categories, and we show that most skills remain within typical prompt budgets despite a heavy-tailed length distribution. Finally, we observe strong ecosystem homogeneity, with widespread intent-level redundancy, and we identify non-trivial safety risks, including skills that enable state-changing or system-level actions. Overall, our findings provide a quantitative snapshot of agent skills as an emerging infrastructure layer for agents and inform future work on skill reuse, standardization, and safety-aware design.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08004</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09024</guid>
|
||||||
<pubDate>Sun, 08 Feb 2026 15:14:12 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 18:59:58 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Weak-Driven Learning: How Weak Agents make Strong Agents Stronger</title>
|
<title>SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes</title>
|
||||||
<link>https://arxiv.org/abs/2602.08222</link>
|
<link>https://arxiv.org/abs/2602.09153</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08222.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zehao Chen, Gongxun Li, Tianxiang Ai, Yifei Li, Zixuan Huang, Wang Zhou, Fuzhen Zhuang, Xianglong Liu, Jianxin Li, Deqing Wang, Yikun Ban</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training yields diminishing returns. While existing methods continue to reinforce target predictions, we find that informative supervision signals remain latent in models' own historical weak states. Motivated by this observation, we propose WMSS (Weak Agents Can Make Strong Agents Stronger), a post-training paradigm that leverages weak checkpoints to guide continued optimization. By identifying recoverable learning gaps via entropy dynamics and reinforcing them through compensatory learning, WMSS enables strong agents to improve beyond conventional post-training saturation. Experiments on mathematical reasoning and code generation datasets show that agents trained with our approach achieve effective performance improvements, while incurring zero additional inference cost.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08222</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09153</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 02:50:40 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 19:56:04 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning</title>
|
<title>Rethinking Global Text Conditioning in Diffusion Transformers</title>
|
||||||
<link>https://arxiv.org/abs/2602.08236</link>
|
<link>https://arxiv.org/abs/2602.09268</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08236.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shoubin Yu, Yue Zhang, Zun Wang, Jaehong Yoon, Huaxiu Yao, Mingyu Ding, Mohit Bansal</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Despite rapid progress in Multimodal Large Language Models (MLLMs), visual spatial reasoning remains unreliable when correct answers depend on how a scene would appear under unseen or alternative viewpoints. Recent work addresses this by augmenting reasoning with world models for visual imagination, but questions such as when imagination is actually necessary, how much of it is beneficial, and when it becomes harmful, remain poorly understood. In practice, indiscriminate imagination can increase computation and even degrade performance by introducing misleading evidence. In this work, we present an in-depth analysis of test-time visual imagination as a controllable resource for spatial reasoning. We study when static visual evidence is sufficient, when imagination improves reasoning, and how excessive or unnecessary imagination affects accuracy and efficiency. To support this analysis, we introduce AVIC, an adaptive test-time framework with world models that explicitly reasons about the sufficiency of current visual evidence before selectively invoking and scaling visual imagination. Across spatial reasoning benchmarks (SAT, MMSI) and an embodied navigation benchmark (R2R), our results reveal clear scenarios where imagination is critical, marginal, or detrimental, and show that selective control can match or outperform fixed imagination strategies with substantially fewer world-model calls and language tokens. Overall, our findings highlight the importance of analyzing and controlling test-time imagination for efficient and reliable spatial reasoning.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08236</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09268</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 03:21:48 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 23:06:58 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition</title>
|
<title>Effective Reasoning Chains Reduce Intrinsic Dimensionality</title>
|
||||||
<link>https://arxiv.org/abs/2602.08439</link>
|
<link>https://arxiv.org/abs/2602.09276</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08439.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Dong, Shulin Tian, Shuai Liu, Shuangrui Ding, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Jiaqi Wang, Ziwei Liu</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Despite the growing video understanding capabilities of recent Multimodal Large Language Models (MLLMs), existing video benchmarks primarily assess understanding based on models' static, internal knowledge, rather than their ability to learn and adapt from dynamic, novel contexts from few examples. To bridge this gap, we present Demo-driven Video In-Context Learning, a novel task focused on learning from in-context demonstrations to answer questions about the target videos. Alongside this, we propose Demo-ICL-Bench, a challenging benchmark designed to evaluate demo-driven video in-context learning capabilities. Demo-ICL-Bench is constructed from 1200 instructional YouTube videos with associated questions, from which two types of demonstrations are derived: (i) summarizing video subtitles for text demonstration; and (ii) corresponding instructional videos as video demonstrations. To effectively tackle this new challenge, we develop Demo-ICL, an MLLM with a two-stage training strategy: video-supervised fine-tuning and information-assisted direct preference optimization, jointly enhancing the model's ability to learn from in-context examples. Extensive experiments with state-of-the-art MLLMs confirm the difficulty of Demo-ICL-Bench, demonstrate the effectiveness of Demo-ICL, and thereby unveil future research directions.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08439</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09276</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 09:51:29 +0000</pubDate>
|
<pubDate>Mon, 09 Feb 2026 23:32:12 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>GISA: A Benchmark for General Information-Seeking Assistant</title>
|
<title>Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning</title>
|
||||||
<link>https://arxiv.org/abs/2602.08543</link>
|
<link>https://arxiv.org/abs/2602.09439</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08543.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yutao Zhu, Xingshuo Zhang, Maosen Zhang, Jiajie Jin, Liancheng Zhang, Xiaoshuai Song, Kangzhi Zhao, Wencong Zeng, Ruiming Tang, Han Li, Ji-Rong Wen, Zhicheng Dou</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> The advancement of large language models (LLMs) has significantly accelerated the development of search agents capable of autonomously gathering information through multi-turn web interactions. Various benchmarks have been proposed to evaluate such agents. However, existing benchmarks often construct queries backward from answers, producing unnatural tasks misaligned with real-world needs. Moreover, these benchmarks tend to focus on either locating specific information or aggregating information from multiple sources, while relying on static answer sets prone to data contamination. To bridge these gaps, we introduce GISA, a benchmark for General Information-Seeking Assistants comprising 373 human-crafted queries that reflect authentic information-seeking scenarios. GISA features four structured answer formats (item, set, list, and table), enabling deterministic evaluation. It integrates both deep reasoning and broad information aggregation within unified tasks, and includes a live subset with periodically updated answers to resist memorization. Notably, GISA provides complete human search trajectories for every query, offering gold-standard references for process-level supervision and imitation learning. Experiments on mainstream LLMs and commercial search products reveal that even the best-performing model achieves only 19.30\% exact match score, with performance notably degrading on tasks requiring complex planning and comprehensive information gathering. These findings highlight substantial room for future improvement.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08543</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09439</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 11:44:15 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 06:06:54 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CauScale: Neural Causal Discovery at Scale</title>
|
<title>P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads</title>
|
||||||
<link>https://arxiv.org/abs/2602.08629</link>
|
<link>https://arxiv.org/abs/2602.09443</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08629.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bo Peng, Sirui Chen, Jiaguo Tian, Yu Qiao, Chaochao Lu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Causal discovery is essential for advancing data-driven fields such as scientific AI and data analysis, yet existing approaches face significant time- and space-efficiency bottlenecks when scaling to large graphs. To address this challenge, we present CauScale, a neural architecture designed for efficient causal discovery that scales inference to graphs with up to 1000 nodes. CauScale improves time efficiency via a reduction unit that compresses data embeddings and improves space efficiency by adopting tied attention weights to avoid maintaining axis-specific attention maps. To keep high causal discovery accuracy, CauScale adopts a two-stream design: a data stream extracts relational evidence from high-dimensional observations, while a graph stream integrates statistical graph priors and preserves key structural signals. CauScale successfully scales to 500-node graphs during training, where prior work fails due to space limitations. Across testing data with varying graph scales and causal mechanisms, CauScale achieves 99.6% mAP on in-distribution data and 84.4% on out-of-distribution data, while delivering 4-13,000 times inference speedups over prior methods. Our project page is at https://github.com/OpenCausaLab/CauScale.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08629</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09443</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 13:21:32 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 06:28:08 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models</title>
|
<title>On the Optimal Reasoning Length for RL-Trained Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2602.08658</link>
|
<link>https://arxiv.org/abs/2602.09591</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08658.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingzi Cao, Xingwei Tan, Mahmud Akhter, Marco Valentino, Maria Liakata, Xi Wang, Nikolaos Aletras</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Deduction, induction, and abduction are fundamental reasoning paradigms, core for human logical thinking. Although improving Large Language Model (LLM) reasoning has attracted significant research efforts, the extent to which the fundamental paradigms induce generalization has yet to be systematically explored. In this study, we shed light on how the interplay between these core paradigms influences LLMs' reasoning behavior. To this end, we first collect a new dataset of reasoning trajectories from symbolic tasks, each targeting one of the three fundamental paradigms, to abstract from concrete world knowledge. Then, we investigate effective ways for inducing these skills into LLMs. We experiment with a battery of methods including simple fine-tuning, and more complex approaches to increase model depth, or transform a dense model to a mixture-of-experts. We comprehensively evaluate induced models on realistic out-of-domain tasks, that are entirely formulated in natural language and contain real-world knowledge. Our results reveal that our approach yields strong generalizability with substantial performance gains (up to 14.60) across realistic tasks.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08658</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09591</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 13:51:48 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 09:45:42 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LLaDA2.1: Speeding Up Text Diffusion via Token Editing</title>
|
<title>TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution</title>
|
||||||
<link>https://arxiv.org/abs/2602.08676</link>
|
<link>https://arxiv.org/abs/2602.09662</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tiwei Bie, Maosong Cao, Xiang Cao, Bingsen Chen, Fuyuan Chen, Kun Chen, Lun Du, Daozhuo Feng, Haibo Feng, Mingliang Gong, Zhuocheng Gong, Yanmei Gu, Jian Guan, Kaiyuan Guan, Hongliang He, Zenan Huang, Juyong Jiang, Zhonghui Jiang, Zhenzhong Lan, Chengxi Li, Jianguo Li, Zehuan Li, Huabin Liu, Lin Liu, Guoshan Lu, Yuan Lu, Yuxin Ma, Xingyu Mou, Zhenxuan Pan, Kaida Qiu, Yuji Ren, Jianfeng Tan, Yiding Tian, Zian Wang, Lanning Wei, Tao Wu, Yipeng Xing, Wentao Ye, Liangyu Zha, Tianze Zhang, Xiaolu Zhang, Junbo Zhao, Da Zheng, Hao Zhong, Wanli Zhong, Jun Zhou, Junlin Zhou, Liwang Zhu, Muzhi Zhu, Yihong Zhuang</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> While LLaDA2.0 showcased the scaling potential of 100B-level block-diffusion models and their inherent parallelization, the delicate equilibrium between decoding speed and generation quality has remained an elusive frontier. Today, we unveil LLaDA2.1, a paradigm shift designed to transcend this trade-off. By seamlessly weaving Token-to-Token (T2T) editing into the conventional Mask-to-Token (M2T) scheme, we introduce a joint, configurable threshold-decoding scheme. This structural innovation gives rise to two distinct personas: the Speedy Mode (S Mode), which audaciously lowers the M2T threshold to bypass traditional constraints while relying on T2T to refine the output; and the Quality Mode (Q Mode), which leans into conservative thresholds to secure superior benchmark performances with manageable efficiency degrade. Furthering this evolution, underpinned by an expansive context window, we implement the first large-scale Reinforcement Learning (RL) framework specifically tailored for dLLMs, anchored by specialized techniques for stable gradient estimation. This alignment not only sharpens reasoning precision but also elevates instruction-following fidelity, bridging the chasm between diffusion dynamics and complex human intent. We culminate this work by releasing LLaDA2.1-Mini (16B) and LLaDA2.1-Flash (100B). Across 33 rigorous benchmarks, LLaDA2.1 delivers strong task performance and lightning-fast decoding speed. Despite its 100B volume, on coding tasks it attains an astounding 892 TPS on HumanEval+, 801 TPS on BigCodeBench, and 663 TPS on LiveCodeBench.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08676</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09662</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 14:00:07 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 11:16:57 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MOVA: Towards Scalable and Synchronized Video-Audio Generation</title>
|
<title>Covo-Audio Technical Report</title>
|
||||||
<link>https://arxiv.org/abs/2602.08794</link>
|
<link>https://arxiv.org/abs/2602.09823</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08794.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> SII-OpenMOSS Team, Donghua Yu, Mingshu Chen, Qi Chen, Qi Luo, Qianyi Wu, Qinyuan Cheng, Ruixiao Li, Tianyi Liang, Wenbo Zhang, Wenming Tu, Xiangyu Peng, Yang Gao, Yanru Huo, Ying Zhu, Yinze Luo, Yiyang Zhang, Yuerong Song, Zhe Xu, Zhiyu Zhang, Chenchen Yang, Cheng Chang, Chushu Zhou, Hanfu Chen, Hongnan Ma, Jiaxi Li, Jingqi Tong, Junxi Liu, Ke Chen, Shimin Li, Songlin Wang, Wei Jiang, Zhaoye Fei, Zhiyuan Ning, Chunguo Li, Chenhui Li, Ziwei He, Zengfeng Huang, Xie Chen, Xipeng Qiu</p><p><b>Upvotes:</b> 131</p><p><b>Summary:</b> Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on cascaded pipelines, which increase cost, accumulate errors, and degrade overall quality. While systems such as Veo 3 and Sora 2 emphasize the value of simultaneous generation, joint multimodal modeling introduces unique challenges in architecture, data, and training. Moreover, the closed-source nature of existing systems limits progress in the field. In this work, we introduce MOVA (MOSS Video and Audio), an open-source model capable of generating high-quality, synchronized audio-visual content, including realistic lip-synced speech, environment-aware sound effects, and content-aligned music. MOVA employs a Mixture-of-Experts (MoE) architecture, with a total of 32B parameters, of which 18B are active during inference. It supports IT2VA (Image-Text to Video-Audio) generation task. By releasing the model weights and code, we aim to advance research and foster a vibrant community of creators. The released codebase features comprehensive support for efficient inference, LoRA fine-tuning, and prompt enhancement.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08794</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09823</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 15:31:54 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 14:31:11 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs</title>
|
<title>BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation</title>
|
||||||
<link>https://arxiv.org/abs/2602.08808</link>
|
<link>https://arxiv.org/abs/2602.09849</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08808.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yapei Chang, Kyle Lo, Mohit Iyyer, Luca Soldaini</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Generating step-by-step "how-to" procedures is a key LLM capability: how-to advice is commonly requested in chatbots, and step-by-step planning is critical for reasoning over complex tasks. Yet, measuring and improving procedural validity at scale on real-world tasks remains challenging and understudied. To address this, we introduce How2Everything, a scalable framework to evaluate and improve goal-conditioned procedure generation. Our framework includes How2Mine, which mines 351K procedures from 980K web pages across 14 topics and readily scales to larger corpora. From this pool we build How2Bench, a 7K-example evaluation set balanced across topics. To reliably score model outputs, we develop How2Score, an evaluation protocol that uses an LLM judge to detect whether a generation contains any critical failure that would prevent achieving the goal. For low-cost, reproducible evaluation, we distill a frontier model into an open 8B model, achieving 80.5% agreement with human annotators. How2Bench reveals clear scaling trends across model sizes and training stages, providing signal early in pretraining. Finally, RL using How2Score as a reward improves performance on How2Bench by >10 points across three models without systematic regressions on standard benchmarks, with gains robust to superficial source-document memorization or format compliance. Taken together, How2Everything shows how pretraining web data can support a closed loop of capability evaluation and improvement at scale.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08808</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09849</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 15:47:14 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 14:54:01 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models</title>
|
<title>Code2World: A GUI World Model via Renderable Code Generation</title>
|
||||||
<link>https://arxiv.org/abs/2602.08818</link>
|
<link>https://arxiv.org/abs/2602.09856</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08818.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Annemette Brok Pirchert, Jacob Nielsen, Mogens Henrik From, Lukas Galke Poech, Peter Schneider-Kamp</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent advances in mixture-of-experts architectures have shown that individual experts models can be trained federatedly, i.e., in isolation from other experts by using a common base model to facilitate coordination. However, we hypothesize that full-sized experts may not be necessary for all domains and that instead low-rank adapters may be sufficient. Here, we introduce FlexMoRE, a Flexible Mixture of Rank-heterogenous Experts, which may be either full-sized experts or adapters of a suitable rank. We systematically investigate the trade-off between expert rank and downstream task performance by evaluating 6 experts with ranks 2^0 to 2^{14} resulting in experiments covering 150 mixtures (96 with 2 experts, 54 with 7 experts) that are evaluated across 120 tasks. For our experiments, we build on FlexOlmo and turn its pre-trained experts into low-rank versions. Our regression analysis from expert rank to downstream task performance reveals that the best-performing rank is substantially higher for reasoning-heavy benchmarks than for knowledge-heavy benchmarks. These findings on rank sensitivity come with direct implications for memory efficiency: Using optimal ranks, FlexMoRE yields improved downstream task performance (average score 47.18) compared to the baseline FlexOlmo-style mixture of full-sized experts (average score 45.46) at less than one third the parameters (10.75B for FlexMoRE vs. 33.27B for FlexOlmo). All code will be made available.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08818</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09856</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 15:54:29 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 14:56:19 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>WildReward: Learning Reward Models from In-the-Wild Human Interactions</title>
|
<title>LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations</title>
|
||||||
<link>https://arxiv.org/abs/2602.08829</link>
|
<link>https://arxiv.org/abs/2602.09924</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08829.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Peng, Yunjia Qi, Xiaozhi Wang, Zijun Yao, Lei Hou, Juanzi Li</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Reward models (RMs) are crucial for the training of large language models (LLMs), yet they typically rely on large-scale human-annotated preference pairs. With the widespread deployment of LLMs, in-the-wild interactions have emerged as a rich source of implicit reward signals. This raises the question: Can we develop reward models directly from in-the-wild interactions? In this work, we explore this possibility by adopting WildChat as an interaction source and proposing a pipeline to extract reliable human feedback, yielding 186k high-quality instances for training WildReward via ordinal regression directly on user feedback without preference pairs. Extensive experiments demonstrate that WildReward achieves comparable or even superior performance compared to conventional reward models, with improved calibration and cross-sample consistency. We also observe that WildReward benefits directly from user diversity, where more users yield stronger reward models. Finally, we apply WildReward to online DPO training and observe significant improvements across various tasks. Code and data are released at https://github.com/THU-KEG/WildReward.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08829</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09924</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 16:00:30 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 15:57:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE</title>
|
<title>Chain of Mindset: Reasoning with Adaptive Cognitive Modes</title>
|
||||||
<link>https://arxiv.org/abs/2602.08961</link>
|
<link>https://arxiv.org/abs/2602.10063</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08961.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruijie Zhu, Jiahao Lu, Wenbo Hu, Xiaoguang Han, Jianfei Cai, Ying Shan, Chuanxia Zheng</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We introduce MotionCrafter, a video diffusion-based framework that jointly reconstructs 4D geometry and estimates dense motion from a monocular video. The core of our method is a novel joint representation of dense 3D point maps and 3D scene flows in a shared coordinate system, and a novel 4D VAE to effectively learn this representation. Unlike prior work that forces the 3D value and latents to align strictly with RGB VAE latents-despite their fundamentally different distributions-we show that such alignment is unnecessary and leads to suboptimal performance. Instead, we introduce a new data normalization and VAE training strategy that better transfers diffusion priors and greatly improves reconstruction quality. Extensive experiments across multiple datasets demonstrate that MotionCrafter achieves state-of-the-art performance in both geometry reconstruction and dense scene flow estimation, delivering 38.64% and 25.0% improvements in geometry and motion reconstruction, respectively, all without any post-optimization. Project page: https://ruijiezhu94.github.io/MotionCrafter_Page</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08961</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.10063</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 17:58:12 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 18:31:47 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery</title>
|
<title>Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning</title>
|
||||||
<link>https://arxiv.org/abs/2602.08990</link>
|
<link>https://arxiv.org/abs/2602.10090</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.08990.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiyang Feng, Runmin Ma, Xiangchao Yan, Yue Fan, Yusong Hu, Songtao Huang, Shuaiyu Zhang, Zongsheng Cao, Tianshuo Peng, Jiakang Yuan, Zijie Guo, Zhijie Zhong, Shangheng Du, Weida Wang, Jinxin Shi, Yuhao Zhou, Xiaohan He, Zhiyin Yu, Fangchen Yu, Qihao Zheng, Jiamin Wu, Mianxin Liu, Chi Zhang, Shaowei Hou, Shuya Li, Yankai Jiang, Wenjie Lou, Lilong Wang, Zifu Wang, Jiong Wang, Wanghan Xu, Yue Deng, Dongrui Liu, Yiheng Wang, Wenlong Zhang, Fenghua Ling, Shufei Zhang, Xiaosong Wang, Shuangjia Zheng, Xun Huang, Siqi Sun, Shuyue Hu, Peng Ye, Chunfeng Song, Bin Wang, Conghui He, Yihao Liu, Xin Li, Qibin Hou, Tao Chen, Xiangyu Yue, Bin Wang, Liang He, Dahua Lin, Bowen Zhou, Bo Zhang, Lei Bai</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architecture composed of three coordinated subsystems for generation, verification, and evolution. These subsystems are supported by foundational capabilities for deep research, solution optimization, and long horizon memory. The architecture allows InternAgent-1.5 to operate continuously across extended discovery cycles while maintaining coherent and improving behavior. It also enables the system to coordinate computational modeling and laboratory experimentation within a single unified system. We evaluate InternAgent-1.5 on scientific reasoning benchmarks such as GAIA, HLE, GPQA, and FrontierScience, and the system achieves leading performance that demonstrates strong foundational capabilities. Beyond these benchmarks, we further assess two categories of discovery tasks. In algorithm discovery tasks, InternAgent-1.5 autonomously designs competitive methods for core machine learning problems. In empirical discovery tasks, it executes complete computational or wet lab experiments and produces scientific findings in earth, life, biological, and physical domains. Overall, these results show that InternAgent-1.5 provides a general and scalable framework for autonomous scientific discovery.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.08990</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.10090</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 18:36:06 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 18:55:41 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Data Science and Technology Towards AGI Part I: Tiered Data Management</title>
|
<title>VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model</title>
|
||||||
<link>https://arxiv.org/abs/2602.09003</link>
|
<link>https://arxiv.org/abs/2602.10098</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09003.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yudong Wang, Zixuan Fu, Hengyu Zhao, Chen Zhao, Chuyue Zhou, Xinle Lin, Hongya Lyu, Shuaikang Xue, Yi Yi, Yingjiao Wang, Zhi Zheng, Yuzhou Zhang, Jie Zhou, Chaojun Xiao, Xu Han, Zhiyuan Liu, Maosong Sun</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The development of artificial intelligence can be viewed as an evolution of data-driven learning paradigms, with successive shifts in data organization and utilization continuously driving advances in model capability. Current LLM research is dominated by a paradigm that relies heavily on unidirectional scaling of data size, increasingly encountering bottlenecks in data availability, acquisition cost, and training efficiency. In this work, we argue that the development of AGI is entering a new phase of data-model co-evolution, in which models actively guide data management while high-quality data, in turn, amplifies model capabilities. To implement this vision, we propose a tiered data management framework, designed to support the full LLM training lifecycle across heterogeneous learning objectives and cost constraints. Specifically, we introduce an L0-L4 tiered data management framework, ranging from raw uncurated resources to organized and verifiable knowledge. Importantly, LLMs are fully used in data management processes, such as quality scoring and content editing, to refine data across tiers. Each tier is characterized by distinct data properties, management strategies, and training roles, enabling data to be strategically allocated across LLM training stages, including pre-training, mid-training, and alignment. The framework balances data quality, acquisition cost, and marginal training benefit, providing a systematic approach to scalable and sustainable data management. We validate the effectiveness of the proposed framework through empirical studies, in which tiered datasets are constructed from raw corpora and used across multiple training phases. Experimental results demonstrate that tier-aware data utilization significantly improves training efficiency and model performance. To facilitate further research, we release our tiered datasets and processing tools to the community.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.09003</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.10098</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 18:47:51 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 18:58:01 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>GEBench: Benchmarking Image Generation Models as GUI Environments</title>
|
<title>Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders</title>
|
||||||
<link>https://arxiv.org/abs/2602.09007</link>
|
<link>https://arxiv.org/abs/2602.10099</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09007.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haodong Li, Jingwei Wu, Quan Sun, Guopeng Li, Juanxi Tian, Huanyu Zhang, Yanlin Lai, Ruichuan An, Hongbo Peng, Yuhong Dai, Chenxi Li, Chunmei Qing, Jia Wang, Ziyang Meng, Zheng Ge, Xiangyu Zhang, Daxin Jiang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Recent advancements in image generation models have enabled the prediction of future Graphical User Interface (GUI) states based on user instructions. However, existing benchmarks primarily focus on general domain visual fidelity, leaving the evaluation of state transitions and temporal coherence in GUI-specific contexts underexplored. To address this gap, we introduce GEBench, a comprehensive benchmark for evaluating dynamic interaction and temporal coherence in GUI generation. GEBench comprises 700 carefully curated samples spanning five task categories, covering both single-step interactions and multi-step trajectories across real-world and fictional scenarios, as well as grounding point localization. To support systematic evaluation, we propose GE-Score, a novel five-dimensional metric that assesses Goal Achievement, Interaction Logic, Content Consistency, UI Plausibility, and Visual Quality. Extensive evaluations on current models indicate that while they perform well on single-step transitions, they struggle significantly with maintaining temporal coherence and spatial grounding over longer interaction sequences. Our findings identify icon interpretation, text rendering, and localization precision as critical bottlenecks. This work provides a foundation for systematic assessment and suggests promising directions for future research toward building high-fidelity generative GUI environments. The code is available at: https://github.com/stepfun-ai/GEBench.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.09007</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.10099</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 18:52:02 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 18:58:04 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>WorldCompass: Reinforcement Learning for Long-Horizon World Models</title>
|
<title>VideoWorld 2: Learning Transferable Knowledge from Real-world Videos</title>
|
||||||
<link>https://arxiv.org/abs/2602.09022</link>
|
<link>https://arxiv.org/abs/2602.10102</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09022.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zehan Wang, Tengfei Wang, Haiyu Zhang, Xuhui Zuo, Junta Wu, Haoyuan Wang, Wenqiang Sun, Zhenwei Wang, Chenjie Cao, Hengshuang Zhao, Chunchao Guo, Zhou Zhao</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> This work presents WorldCompass, a novel Reinforcement Learning (RL) post-training framework for the long-horizon, interactive video-based world models, enabling them to explore the world more accurately and consistently based on interaction signals. To effectively "steer" the world model's exploration, we introduce three core innovations tailored to the autoregressive video generation paradigm: 1) Clip-level rollout Strategy: We generate and evaluate multiple samples at a single target clip, which significantly boosts rollout efficiency and provides fine-grained reward signals. 2) Complementary Reward Functions: We design reward functions for both interaction-following accuracy and visual quality, which provide direct supervision and effectively suppress reward-hacking behaviors. 3) Efficient RL Algorithm: We employ the negative-aware fine-tuning strategy coupled with various efficiency optimizations to efficiently and effectively enhance model capacity. Evaluations on the SoTA open-source world model, WorldPlay, demonstrate that WorldCompass significantly improves interaction accuracy and visual fidelity across various scenarios.</p></description>
|
<description><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></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.09022</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.10102</guid>
|
||||||
<pubDate>Mon, 09 Feb 2026 18:59:47 +0000</pubDate>
|
<pubDate>Tue, 10 Feb 2026 18:58:19 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Olaf-World: Orienting Latent Actions for Video World Modeling</title>
|
||||||
|
<link>https://arxiv.org/abs/2602.10104</link>
|
||||||
|
<description><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></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.10104</guid>
|
||||||
|
<pubDate>Tue, 10 Feb 2026 18:58:41 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>SAGE: Scalable Agentic 3D Scene Generation for Embodied AI</title>
|
||||||
|
<link>https://arxiv.org/abs/2602.10116</link>
|
||||||
|
<description><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></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.10116</guid>
|
||||||
|
<pubDate>Tue, 10 Feb 2026 18:59:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user