748 lines
233 KiB
XML
748 lines
233 KiB
XML
<?xml version='1.0' encoding='UTF-8'?>
|
||
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
|
||
<channel>
|
||
<title>Hugging Face Daily Papers</title>
|
||
<link>https://huggingface.co/papers</link>
|
||
<description>Daily research papers curated by the Hugging Face community.</description>
|
||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||
<generator>python-feedgen</generator>
|
||
<language>en</language>
|
||
<lastBuildDate>Mon, 15 Jun 2026 00:41:56 +0000</lastBuildDate>
|
||
<item>
|
||
<title>WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models</title>
|
||
<link>https://arxiv.org/abs/2605.25077</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25077.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bohai Gu, Taiyi Wu, Yueyang Yuan, Jian Liu, Xiaocheng Lu, Dazhao Du, Jie Zhang, Jinxiang Lai, Shuai Yang, Xiaotong Zhao, Alan Zhao, Song Guo</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Recent video-based world models have made pixel-space environments interactive at the camera level: users can navigate viewpoints while the model generates coherent visual continuations. Yet their action spaces remain incomplete: users can move the camera, but cannot act on individual objects. Since real-world interaction is inherently object-centric, such models remain closer to passive scene observers than truly manipulable environments. We present WorldCraft, a framework that expands interactive video world models from camera navigation to object-level trajectory actions. Given a user click and a sketched path, WorldCraft generates future frames in which the selected object follows the prescribed trajectory while the camera continues to navigate the scene. WorldCraft achieves this through a trajectory-centric control pipeline: First, Normalized World Trajectory (NWT) represents user-drawn motion in a camera-invariant world coordinate system and dynamically re-projects it under the current camera pose, separating object motion from camera-induced screen-space displacement; Spatial-Pathway LoRA (SP-LoRA) then injects this world-space signal through the model's spatial-control pathway, adding object manipulation capability while preserving the pretrained camera controller; finally, Trajectory-Anchored State Persistence (TASP) treats the world trajectory as a persistent spatial state and refreshes autoregressive memory after trajectory-conditioned generation, allowing moved objects to reappear at their updated positions after leaving the camera view. Experiments show that WorldCraft enables accurate object control, preserves the video-based world model's camera fidelity under camera-only evaluation, and maintains object state across long autoregressive rollouts with off-camera excursions.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25077</guid>
|
||
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SIA: Self Improving AI with Harness & Weight Updates</title>
|
||
<link>https://arxiv.org/abs/2605.27276</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Prannay Hebbar, Yogendra Manawat, Samuel Verboomen, Alesia Ivanova, Selvam Palanimalai, Kunal Bhatia, Vignesh Baskaran</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them are written, tuned, and corrected by people. The long-horizon goal of an AI that can figure out how to improve itself remains open. Two largely disjoint research lines attack this bottleneck. The harness-update school has a meta-agent rewrite the scaffold of a task-specific agent (its tools, prompts, retry logic, and search procedure) while the model weights are held fixed. The test-time training school uses hand-written RL pipelines to update the model's own weights on task feedback while the harness is held fixed. These two silos operate in isolation. We propose SIA, a self-improving loop in which a language-model agent (the Feedback-Agent) updates both the harness and the weights of a task-specific agent. We evaluate across three contrasting domains: Chinese legal charge classification, low-level GPU kernel optimisation, and single-cell RNA denoising. Combining both levers outperforms scaffold iteration alone on all three benchmarks. The gains are 56.6% on LawBench, 91.9% runtime reduction on GPU kernels, and 502% on denoising over the initial baseline. Harness updates make the model agentic, shaping how it searches and acts, while weight updates build the domain intuition that no prompt or scaffold can instil.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.27276</guid>
|
||
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>DEI: Diversity in Evolutionary Inference for Quality-Diversity Search</title>
|
||
<link>https://arxiv.org/abs/2605.27130</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27130.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> John Donaghy, Shikhar Rastogi</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language models (LLMs) as mutation operators across peer nodes communicating with non-blocking collective operations. Unlike homogeneous parallel search, which replicates a single model's inductive biases across all workers, DEI treats each LLM's distinct creative prior as a complementary source of behavioral novelty. Extending the Digital Red Queen framework with DEI, nodes share local optimal solutions at the end of each round to seed the next round's population. This creates cross-model adversarial pressure that drives robustness beyond intra-model self-play. Evaluated on the Core War domain, a competitive programming benchmark in which Redcode warrior programs battle inside a simulated machine, a four-node heterogeneous ensemble (GPT-5.4-mini, Claude Sonnet 4.6, GPT-5.2, and Claude Haiku 4.5) achieves 124 percent higher merged-archive QD-Score (45.90 vs. 20.46) and 28 percent higher coverage (80.6 percent vs. 63.0 percent of cells) than a single-node baseline at equal total LLM-call budget. The heterogeneous ensemble also outperforms an equally-budgeted homogeneous ensemble on QD-Score, coverage, and held-out solution generality across all four model families. These results provide the first empirical evidence that model diversity, not merely parallelism, is the key driver of gain in distributed LLM-based QD search.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.27130</guid>
|
||
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research</title>
|
||
<link>https://arxiv.org/abs/2606.07591</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07591.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wanghan Xu, Shuo Li, Tianlin Ye, Qinglong Cao, Yixin Chen, Hengjian Gao, Yiheng Wang, Qi Li, Kun Li, Sheng Xu, Shengdu Chai, Fangchen Yu, Xiangyu Zhao, Zhangrui Zhao, Weijie Ma, Zijie Guo, Haoyu Zhou, Haoxiang Yin, Lixue Cheng, Chaofan Hu, Haoxuan Li, Lu Mi, Xuxuan Xie, Yifan Zhou, Ruizhe Chen, Zhiwang Zhou, Xingjian Guo, Yuhao Zhou, Xuming He, Shengyuan Xu, Xinyu Gu, Jiamin Wu, Mianxin Liu, Chunfeng Song, Fenghua Ling, Dongzhan Zhou, Shixiang Tang, Yuqiang Li, Mao Su, Peng Ye, Siqi Sun, Bin Wang, Xue Yang, Zhenfei Yin, Tianfan Fu, Guangtao Zhai, Wanli Ouyang, Bo Zhang, Lei Bai, Wenlong Zhang</p><p><b>Upvotes:</b> 87</p><p><b>Summary:</b> AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07591</guid>
|
||
<pubDate>Thu, 28 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Human Psychometric Questionnaires Mischaracterize LLM Behavior</title>
|
||
<link>https://arxiv.org/abs/2509.10078</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.10078.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Woojung Song, Dongmin Choi, Yoonah Park, Jongwook Han, Eun-Ju Lee, Yohan Jo</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> We examine whether human psychometric questionnaires can serve as reliable tools for characterizing and predicting LLM behavior in everyday user interactions. We analyze eight open-source LLMs by comparing their value and personality profiles derived from two different methods: Likert self-reports on established questionnaires (PVQ-40/21 and BFI-44/10) and generation probabilities over value-laden responses to everyday user queries. The two profiles diverge substantially. Within-construct item consistency, often cited as evidence of stable LLM dispositions, disappears in generation probabilities. We attribute this gap to the fact that explicit lexical cues in established questionnaire items allow models to recognize the target construct and respond in alignment-consistent, socially desirable ways, whereas realistic user queries provide no such cues. In addition, demographic persona prompts shift models' responses to human questionnaires in ways consistent with real human patterns, but no such shifts appear in the generation probabilities of responses to realistic user queries, showing their limited ability to simulate the behaviors of target demographics in real-world user interactions. Overall, our study shows that human psychometric questionnaires are insufficient tools for predicting LLM behavior and suggests generation-based profiling as a more accurate measure.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2509.10078</guid>
|
||
<pubDate>Fri, 29 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction</title>
|
||
<link>https://arxiv.org/abs/2606.02540</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.02540.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuting Ning, Zhehao Zhang, Yash Kumar Lal, Boyu Gou, Junyi Li, Weitong Ruan, Chentao Ye, Rahul Gupta, Diyi Yang, Yu Su, Huan Sun</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Agent skills occupy a privileged position in the agent workflow, as agents are expected to implicitly follow and execute them, rendering third-party skills a vulnerable attack surface. Existing studies have revealed unsafe agent behaviors induced by skill-based attacks, but they primarily evaluate poisoned skills within a single task execution and enumerate harms through ad-hoc risk lists. To bridge these gaps, we introduce SkillHarm, a benchmark of skill-based attacks across the skill-use lifecycle, paired with a systematic taxonomy of skill-relevant risks. SkillHarm evaluates two attack scenarios: Fixed-Payload Poisoning (FPP), where a fixed poisoned skill package directly compromises any task session that invokes it, and Self-Mutating Poisoning (SMP), where an initially benign execution silently mutates persistent skill content, deferring harm until a subsequent reuse. It further defines 12 risk types based on the agent workflow component targeted by the harm: data pipelines, system environments, and agent autonomy. To instantiate these attacks at scale, we build AutoSkillHarm, an automated construction pipeline with coding agents driven by natural-language harnesses. The resulting benchmark contains 879 attack samples across 71 skills. Experiments show that current agents remain vulnerable with attack success rates up to 86.3% in FPP and 69.3% in SMP. Our analysis further reveals a latent risk: many apparent attack failures stem from the agent failing to engage with the poisoned file rather than genuine resistance, and current defenses still fail to reliably mitigate the threat.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.02540</guid>
|
||
<pubDate>Mon, 01 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Text-to-Image Models Need Less from Text Encoders Than You Think</title>
|
||
<link>https://arxiv.org/abs/2606.03715</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.03715.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nurit Spingarn, Noa Cohen, Tamar Rott Shaham, Tomer Michaeli</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Text-to-image models rely on text prompts as their primary interface to human intent. Prompts are encoded by a text encoder into embeddings that condition the image generation process. Beyond individual token meanings, text embeddings encode contextual information across the full prompt, such as compositionality and attribute binding. However, whether image models actually exploit this richer information remains underexplored. Here, we address the question: Which aspects of text representation are essential for image generation? We show that text-to-image diffusion transformer-based models commonly rely only on two relatively straightforward aspects of text representations: (i) the merging of adjacent tokens into a word representation, for words spanning multiple tokens, and (ii) word order, which is imprinted by the positional embedding of the text-encoder. To show this, we construct a new text embedding that encodes only individual word meanings and order but lacks any contextual information about the full prompt. We find that this bag of position-tagged words representation is sufficient to successfully guide image generation, achieving visual quality and text fidelity that are on par with full text embedding-guided generation. This demonstrates that, contrary to common belief, text-to-image models often do not use the rich information encoded in the text embedding beyond individual word meanings and word order. Instead, the decoding of complex linguistic structures is performed by the image model itself. Project webpage: https://nsping13.github.io/contextless-TTI/</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.03715</guid>
|
||
<pubDate>Tue, 02 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning</title>
|
||
<link>https://arxiv.org/abs/2606.03108</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.03108.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guhong Chen, Yingcheng Shi, Yongbin Li, Binhua Li, Xander Xu, Hu Wei, Shiwen Ni, Min Yang, Jieping Ye</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human-engineered RL references under the same data, codebase, and evaluation protocol, with the largest gain on long-horizon agentic SWE. Trajectory analyses show that retained strategies diverge across domains, evolving diagnostics prevent invalid high-scoring branches from being promoted, and reusable skills shape later search. Autonomous LLM RL should move beyond recipe search toward joint evolution of policies and the training harnesses that interpret them.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.03108</guid>
|
||
<pubDate>Tue, 02 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Why Muon Outperforms Adam: A Curvature Perspective</title>
|
||
<link>https://arxiv.org/abs/2606.04662</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.04662.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuche Wang, Fengzhuo Zhang, Jiaxiang Li, Dirk Bergemann, Zhuoran Yang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Muon improves training efficiency over Adam in large language-model training by about two times, but the local geometric source of this advantage remains unclear. Our work takes a first step toward demystifying Muon's superiority over Adam from a curvature perspective. First, we apply a second-order Taylor approximation to the training landscape and show that Muon achieves a larger one-step loss decrease than Adam at matched validation loss. The two optimizers have comparable first-order gains, but Muon consistently incurs a smaller second-order curvature penalty. Second, we decompose this curvature penalty into the squared update norm and Normalized Directional Sharpness (NDS). We find that Muon and Adam have comparable update norms, so Muon's smaller curvature penalty is driven by lower NDS, not update scale. Third, we study how training data and model structure shape Muon's NDS advantage. Using Zipf-Probabilistic Context-Free Grammar (PCFG) data with controlled imbalance, we show that data imbalance amplifies Muon's NDS advantage over Adam. A within-/cross-layer decomposition further shows that, in the middle and late stages of training, Muon's lower NDS is mainly sustained by smaller within-layer curvature. Beyond empirical evidence, we analyze stylized quadratic problems with heterogeneous curvature and gradient alignment toward high-curvature modes. We prove that Muon attains a smaller average NDS than GD by balancing update energy across curvature groups; when curvature heterogeneity is sufficiently strong, this also yields lower local quadratic loss after the same number of steps.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.04662</guid>
|
||
<pubDate>Wed, 03 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval</title>
|
||
<link>https://arxiv.org/abs/2606.04391</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.04391.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxi Li, Ke Deng, Yun Wang, Jingyuan Huang, Yucheng Shi, Qiaoyu Tan, Jin Lu, Ninghao Liu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Language agents increasingly rely on reusable skills to improve multi-step web automation across related tasks. A growing line of work studies online skill learning, where agents continually induce skills from previous task trajectories and reuse them in future tasks on the fly. However, existing methods mainly reuse skills at the task-level: a fixed set of skills is retrieved based on the initial task instruction and then held fixed throughout execution. This static strategy is misaligned with web execution, where the appropriate next action depends not only on the task goal but also on the current webpage state, which often transitions into situations that the initial skills fail to cover. To address this gap, we propose State-Grounded Dynamic Retrieval (SGDR), an online skill learning method that enables stepwise skill reuse for web agents. SGDR consists of three components: a sliding-window extraction process that turns completed trajectories into reusable sub-procedures invokable at intermediate execution states, a dual text-code representation that connects skill retrieval with executable action, and a state-grounded dynamic retrieval mechanism that matches skills to both the task goal and the current webpage state. Experiments on WebArena across five domains show that SGDR consistently outperforms strong baselines, achieving average success rates of 37.5% with GPT-4.1 and 24.3% with Qwen3-4B, corresponding to relative gains of 10.6% and 10.0% over the strongest baseline, respectively. The code is available at https://github.com/plusnli/skill-dynamic-retrieval.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.04391</guid>
|
||
<pubDate>Wed, 03 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>GENEB: Why Genomic Models Are Hard to Compare</title>
|
||
<link>https://arxiv.org/abs/2606.04525</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.04525.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daria Ledneva, Mikhail Nuridinov, Denis Kuznetsov</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Progress in genomic foundation models is difficult to assess due to fragmented benchmarks, incompatible evaluation protocols, and task-specific reporting. As a result, claims of superiority or generality across models are often not directly comparable. We introduce GENEB, a large-scale diagnostic benchmark that evaluates frozen representations from 40 genomic foundation models across 100 tasks spanning 13 functional categories under a unified probing-based protocol, including few-shot regimes. GENEB enables controlled comparison across model scale, architecture, tokenization, and pretraining data while explicitly exposing task-level trade-offs. Our analysis shows that aggregate leaderboards are unstable: model rankings vary sharply across task categories, scale provides only modest and inconsistent gains, and architectural and pretraining alignment frequently outweigh parameter count. These results highlight limitations of current evaluation practices and position GENEB as a reference framework for principled comparison and category-aware model selection in genomic machine learning.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.04525</guid>
|
||
<pubDate>Wed, 03 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models</title>
|
||
<link>https://arxiv.org/abs/2606.03988</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.03988.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mahtab Bigverdi, Linjie Li, Weikai Huang, Yiming Liu, Jaemin Cho, Jieyu Zhang, Tuhin Kundu, Chris Dangjoo Kim, Zelun Luo, Linda Shapiro, Ranjay Krishna</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable. Many such problems require imaginative perception: inferring what would be seen from an unseen viewpoint, tracing paths through occluded spaces, or integrating partial observations into a coherent spatial representation. We introduce Imaginative Perception Tokens (IPT), intermediate perceptual representations that externalize what a VLM would perceive under alternative spatial configurations while remaining consistent with the observed input. To study this capability, we formulate three tasks, Perspective Taking (PET), Path Tracing (PT), and Multiview Counting (MVC), and construct datasets of approximately 20K examples with ground truth imaginations, answers, and evaluation benchmarks. Using the unified VLM BAGEL as the backbone, IPT supervision consistently improves spatial reasoning and often outperforms textual chain of thought training, even without generating images at inference time. On MVC, IPT improves accuracy by 3.4% and achieves competitive performance with strong closed-source models on PT. We further find that combining IPT and label-only supervision yields additional gains, whereas textual chain of thought can substantially degrade performance, suggesting a modality mismatch when spatial computation is forced through language. Overall, IPT provides a principled supervision signal for reasoning about unobserved spatial structure, improving generalization while producing interpretable intermediate representations.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.03988</guid>
|
||
<pubDate>Wed, 03 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Agents' Last Exam</title>
|
||
<link>https://arxiv.org/abs/2606.05405</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.05405.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiyou Sun, Xinyang Han, Weichen Zhang, Yuanbo Pang, Tianyu Wang, Yuhan Cao, Yixiao Huang, Chris Duroiu, Haoyun Zhang, Jeffrey Lin, Weishu Zhang, Tyler Zeng, Ying Yan, Bo Liu, Hanson Wen, Mingyang Xu, Xiaoyuan Liu, Zimeng Chen, Weiyan Shi, Amanda Dsouza, Vincent Sunn Chen, Patrick Bryant, Carl Boettiger, Yamini Rangan, Bradley Rothenberg, Kyle Steinfeld, Arvind Rao, Tapio Schneider, Georgios Yannakakis, Laure Zanna, Kaan Ozbay, Ida Sim, Tarek Zohdi, George Em Karniadakis, Jack Gallant, Teresa Head-gordon, Yushan Li, Wenxi Deng, Tao Sun, Huiqi Wang, Zhun Wang, Justin Xu, Chris Yuhao Liu, Yafei Cheng, Rongwang Hu, Aras Bacho, Shengcao Cao, Zengyi Qin, Yixiong Chen, Hengduan Fan, Hao Liu, Lin Zeng, Shashank Muralidhar Bharadwaj, Litian Gong, Yingxuan Yang, Maojia Song, Ruheng Wang, Zongzheng Zhang, Honglin Bao, Shuo Lu, Jianhong Tu, Zhonghua Wang, Zheng Zhang, Zijiao Chen, yanqiong Jiang, Zhendong Li, Bohan Lyu, Chang Ma, Peiran Xu, Benran Zhang, Shangding Gu, Haoyue Hua, Haoyang Li, Wanzhe Liao, Chengzhi Liu, Junbo Peng, Haoran Sun, Zechen Xu, Bo Chen, Jiayi Cheng, Yi Jiang, Keying Kuang, Yuan Li, Youbang Pan, Ziyan Rao, Alexander Schubert, Yifan Shen, Vincent Siu, Xiatao Sun, Kangqi Zhang, Xiaopan Zhang, Yuchen Zhu, Ishaan Singh Chandok, Lei Ding, Jingxuan Fan, Andrew Glover, Jiaming Hu, Yiran Hu, Wenbo Huang, Zixin Jiang, Haoran Jin, Lukas Kim, Ming Liu, Yang Liu, Alireza Rafiei, Xuhuan Shen, Kunyang Sun, Sophia Sun, Ting Sun, Eric Wang, Yixin Wang, Hanwen Xing, Sihan Xu, Yuzheng Xu, Zhongxing Xu, Zhiling Yan, Boqin Yuan, Ruiqi Zhang, Yifan Zhang, Zibo Zhao, Liana, Santanu Bosu Antu, Haoyue Bai, Carlo Bosio, Joseph Cavanagh, Patricia Cavazos-Rehg, Tianxing Chen, Xuewen Chen, Yipu Chen, Zhu Chenyu, Chen Dai, Stefano De Castro, Yunfu Deng, Kaustubh Dhole, Jiayuan Ding, Chenchen Du, Zhehang Du, Hao Fan, Run-ze Fan, Hengyu Fu, Shi Gu, Yifan Gu, Charlie Guo, Baihe Huang, Baixiang Huang, Rimika Jaiswal, Zhihan Jiang, Ran Jin, Erin Kasson, Xin Lan, Joseph Lee, Deren Lei, Chenyu Li, Daofeng Li, Haitao Li, Hongwei Li, Jingyan Li, Xiao Li, Yi Li, Yinsheng Li, Yuangang Li, Zhixu Li, Wenyu Liang, Longtai Liao, Kevin Qinghong Lin, AndyZeyi Liu, Che Liu, Jiaming Liu, Kaiyuan Liu, Xuan Liu, Pan Lu, Wenbo Lv, Yicheng Lv, Qiuyang Mang, Kyle Montgomery, Yuzhou Nie, Ruoxi Ning, Jorin Overwiening, Xu Pan, Layna Paraboschi, Core Francisco Park, Justin Purnomo, Swati Rajwal, Scott Rankin, Bixuan Ren, Yiren Rong, HaoYang Shang, Ventus Shaw, Fiona Shen, Jiawei Shen, Minqi Shi, Qiu Shi, Huaxiu Yao, Tianneng Shi, Jonah So, Vladislav Susoy, Hannah Szlyk, Haocheng Wang, Jialu Wang, Wei Wang, Xinyu Wang, Zehao Wang, Dowling Wong, Angela Wu, Dehao Wu, Fangyu Wu, Mengyuan "Millie" Wu, Yu Wu, Yuchen Wu, Yuhao Wu, Qingpo Wuwu, Weihang Xiao, Yongyi Xiong, Fan Xu, Ruiling Xu, Mingxuan Yan, Benjamin Yang, Jirong Yang, Sen Yang, Xiaoli Yang, Yushi Yang, Haoran Ye, Xiaohu Yu, Zhengming Yu, Chenlong Zhang, Chi Zhang, Hanning Zhang, Hanwen Zhang, Junge Zhang, Kunpeng Zhang, Song Zhang, Wenjin Zhang, Wenshuo Zhang, Ying Zhang, Yizhi Zhang, Brian Zhao, Qijian Zhao, Yimin Zhao, Yuhaohua Zheng, Liwei Zhou, Tianyue Zhou, Sichen Zhu, Siqi Zhu, Yan Zhu, Yishu Zhu, Jierui Zuo, Chonghao Cai, Helena Casademunt, Wenjia Chen, Benjamin Cheng, Nawen Deng, Rao Fu, Tianfu Fu, Yifan Han, Ren He, Zhenyu He, Qiao Jin, Lang Lang, Yuetai Li, Sylvia Liu, Lu Lu, Qing Lu, Subhabrata Mukherjee, Yunqi Ouyang, Yin Ren, Dawei Shi, Haoran Wu, Zhiyue Wu, Hannah Yao, Zhuoran Yi, Jenny Yu, Rhea Zhan, Hang Zhou, Blake Zhu, Junfan Zhu, Alan Yuille, Yang Liu, Russell Alan Poldrack, Jiachen Li, Zhenglu Li, Molei Tao, Jing Huang, Wenqi Shi, Costas Spanos, Lichao Sun, Chenguang Wang, Orson Xu, Zhen Dong, Hector Gomez, Aylin Caliskan, Ali Emami, Haimin Hu, Zhi Li, Lihui Liu, Murphy Niu, Yi Shao, Jianxin Sun, Mikko Tolonen, Ting Wang, Sanjiv Das, Yanjun Gao, Wenbo Guo, Erika J Schneider, Zhiyong Lu, Mark Mueller, Radha Poovendran, Somayeh Sojoudi, Dawn Song</p><p><b>Upvotes:</b> 335</p><p><b>Summary:</b> Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 subfields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is 2.6%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP-relevant impact.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.05405</guid>
|
||
<pubDate>Wed, 03 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback</title>
|
||
<link>https://arxiv.org/abs/2606.06113</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.06113.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huaisong Zhang, Hao Yu, Yuxuan Zhang, Jiahe Wang, Xinrui Chen, Haoxiang Cao, Feng Lu, Wendong Zhang, Changqian Yu, Chun Yuan</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality. While recent dense-feedback methods move beyond scalar supervision, their heatmap-centric representations still formulate diagnosis as pixel-field regression, making it difficult to localize variable-cardinality defects and bind semantic reasons to individual failures. To address this representation bottleneck, we propose Structured Defect Grounding (SDG), which casts T2I diagnosis as structured set prediction by modeling each defect as a (location, type, reason, importance) tuple. To make this formulation trainable and measurable, we introduce SDG-30K, a 30K-image dataset with box-grounded annotations across four modern T2I generators, together with a dedicated evaluation protocol, SDG-Eval. Building on this structured representation, we further present a diagnosis-to-alignment framework in which a Vision-Language Model (VLM) serves as the SDG detector, and BoxFlow-GRPO converts predicted defect sets into box-derived, importance-weighted spatial rewards for diffusion model alignment. Extensive experiments show that our SDG detector outperforms leading proprietary VLMs on structured defect grounding, while SDG-guided rewards consistently improve T2I alignment and support localized image refinement. These results establish SDG as a unified, instance-level interface for diagnosing, evaluating, and enhancing modern generative models.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.06113</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators</title>
|
||
<link>https://arxiv.org/abs/2606.06476</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.06476.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenming Zhu, Jingli Lin, Yilin Long, Peizhou Cao, Tai Wang, Jiangmiao Pang, Xihui Liu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> While Vision-Language Models (VLMs) have shown strong visual reasoning capabilities, their spatial reasoning abilities remain largely constrained to the observed images and text-oriented chain-of-thought. They often struggle to infer unobserved layouts, maintain cross-view consistency, and reason from alternative viewpoints when only limited egocentric observations are available. In this work, we study this problem as thinking with imagination, where a VLM actively acquires imagined visual evidence by interacting with a world simulator during reasoning. We propose Astra, an agentic spatial reasoning framework that empowers VLMs with action-conditioned visual imagination. Specifically, Astra couples Astra-VL, an RL-trained VLM policy, with Astra-WM, a Bagel-based world simulator that generates novel-view observations from context images and natural-language camera motions. To provide reliable imagined evidence, Astra-WM is trained with view consistency tuning to improve pose and content consistency across views. In the RL stage, we propose a world-simulator-in-the-loop two-phase RL curriculum to stabilize tool-use exploration and advance the model's ability to invoke the simulator only when imagined observations improve over direct answering. Experiments demonstrate that both the world simulator and the agentic policy are necessary: Astra-WM improves simulator-augmented Gemini-3-Flash on MMSI-Bench from 45.1 to 49.5, while Astra-VL improves the Qwen3-VL backbone from 29.8 to 38.8 on MMSI-Bench and from 36.8 to 42.7 on MindCube. These results show that imagined observations can provide useful spatial evidence, but effective world-model-augmented reasoning requires learning when, where, and how to imagine.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.06476</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>LLM Explainability with Counterfactual Chains and Causal Graphs</title>
|
||
<link>https://arxiv.org/abs/2606.05972</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.05972.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nirit Nussbaum-Hoffer, Nitay Calderon, Liat Ein-Dor, Roi Reichart</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Causal graphs provide a high-level language for making mechanisms transparent. Recent work uses Large Language Models (LLMs) to recover causal graphs of external-world processes. Instead, in this paper, we use causal graphs to model LLM inference itself, providing stakeholders with a transparent view of how the model perceives and organizes high-level concepts to produce a prediction. We propose a four-phase method for constructing such graphs. Given a target LLM and a set of textual examples, our method discovers class-discriminative, human-interpretable concepts and maps each input to LLM-perceived concept states. We then introduce an MCMC-inspired counterfactual augmentation procedure that expands the sparse observational data through chains of counterfactuals. This enables stable causal discovery with σ-CG, yielding informative, interpretable graphs. We apply our method to three LLMs across disease diagnosis, sentiment analysis, and LLM-as-a-judge classification tasks. We evaluate the learned graphs for predictive fidelity and structural stability, and the MCMC-inspired augmentation for convergence and downstream utility. Our results show that the discovered causal graphs capture meaningful dependencies consistent with LLMs' reasoning. Together, this paper provides a foundation for concept-level explainability of LLMs.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.05972</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents</title>
|
||
<link>https://arxiv.org/abs/2606.05761</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.05761.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenxuan Wang, Haoyu Sun, Fukuan Hou, Mingyang Song, Weinan Zhang, Yu Cheng, Yang Yang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Persistent AI assistants, such as OpenClaw, accumulate large collections of related memories over long-term interactions. As these memories grow, they may reinforce one another, diverge across contexts, or directly conflict, making correct assistance depend on memory relations rather than isolated recall. Existing long-term memory benchmarks rarely probe how agents preserve and utilize such relations during downstream tasks. To address this gap, we introduce SubtleMemory, a benchmark for fine-grained relational memory discrimination in long-running AI agents. SubtleMemory constructs relation-controlled latent semantic artifacts whose variants instantiate complementary, nuanced, or contradictory relations, and embeds them into realistic user-agent histories, requiring agents to recover distributed relational structures during later queries and instructions. The benchmark contains 1,522 evaluation instances over 10 long histories, grounded in 1,090 relation-controlled memory-variant sets and spanning user-related and non-user-related queries. Evaluating six standalone memory systems, two Claw-style agents with native memory modules, and three Claw-style agents with plugin memory modules, we find that current systems remain weak on fine-grained relational memory discrimination. We further introduce diagnostic protocols that reveal distinct capability profiles across memory preservation, retrieval, and downstream reasoning stages.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.05761</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs</title>
|
||
<link>https://arxiv.org/abs/2606.06622</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.06622.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amirhossein Abaskohi, Amirhossein Dabiriaghdam, Liang Luo, Ellie Dingqiao Wen, Lele Wang, Giuseppe Carenini, Peter West</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> We introduce UnpredictaBench, an evaluation that tests the ability of large language models (LLMs) to capture true underlying distributions. As LLMs are increasingly used as substitutes for other entities (e.g., for humans in economic simulations), the tendency of many models to collapse towards a single plausible answer means a failure to capture the unpredictability of real systems. Recent work on improving output diversity is insufficient for this setting: simulation requires samples that are calibrated to a target distribution, not merely varied outputs. UnpredictaBench isolates a simplified but fundamental version of this problem: sampling outcomes from individual target distributions, including canonical statistical distributions, distributions induced by stochastic programs, and natural-language scenarios that describe random processes. We introduce 448 such problems together with KS@N, a general-purpose evaluation metric that quantifies how well a model outputs approximate black-box target distributions via the Kolmogorov-Smirnov statistical test. This is the rate at which we fail to reject model samples of size N against ground-truth samples, with larger N indicating greater difficulty. Tested across open and proprietary models, we find a large spread in distributional capabilities. For instance, when models generate samples of size 100 (KS@100, our standard metric), scores range from near 0 to over 20%. No model is able to achieve over 40% at KS@100, showing significant headroom in distributional sampling as a capability. Although adding reasoning can somewhat increase scores, we find no immediate solution for this issue. UnpredictaBench shows that even simple distributional simulation remains challenging, making it a necessary first step toward using LLMs as stand-ins for complex systems.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.06622</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>A Geometric Account of Activation Steering through Angle-Norm Decomposition</title>
|
||
<link>https://arxiv.org/abs/2606.06735</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.06735.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Georgii Aparin, Tatiana Gaintseva</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Linear activation steering has gained popularity as a simple and empirically effective way to control language model behavior. More recently, spherical steering paradigms have been proposed to address limitations of additive interventions, often motivated by the assumption that hidden-state norm does not carry concept-relevant information. In this work, we revisit this assumption through a controlled empirical study designed to disentangle the roles of angular and radial components. We show that steering methods differ mainly in how they couple two geometric effects: changing a token's angular alignment with a concept direction and changing its hidden-state norm. Across seven language models, we find that concepts are represented primarily in angular structure, supporting the motivation for spherical methods, but that norm remains important for the stability and downstream effects of steering. Our results explain why interventions with similar concept-level effects can behave differently, and suggest that activation steering should be parameterized by interpretable angular and radial components of the intervention, rather than by a single additive coefficient that entangles these two effects.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.06735</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents</title>
|
||
<link>https://arxiv.org/abs/2606.05806</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.05806.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongsheng Zhu, Xuchen Ma, Yucheng Shen, Xiang Li, Yukun Zhao, Shuaiqiang Wang, Lingyong Yan, Dawei Yin</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Existing benchmarks evaluate Tool-Integrated Reasoning (TIR) in LLMs on idealized ''happy paths'', largely overlooking real-world tool failures. We introduce ToolMaze, a benchmark for dynamic path discovery and error recovery in TIR agents. To separate systematic replanning from blind trial-and-error, ToolMaze adopts a two-dimensional design: DAG-based topological complexity and a 2 times 2 taxonomy of tool perturbations (explicit/implicit, transient/permanent). Evaluations show that perturbations degrade performance across nearly all models, with the sharpest drops under implicit semantic failures. Driven by systemic over-trust in corrupted outputs, Perturbation Recovery Rate (PRR) plummets by around 37\% in these scenarios, while complex topologies trap agents in futile trial-and-error loops. Crucially, agentic fault-tolerance improves with model scale 3.66times slower than basic task execution, highlighting dynamic replanning as a distinct bottleneck unaddressed by model scaling or prompting. Data and code are available at https://github.com/Zhudongsheng75/ToolMaze.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.05806</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Direct 3D-Aware Object Insertion via Decomposed Visual Proxies</title>
|
||
<link>https://arxiv.org/abs/2606.06601</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.06601.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingbo Gong, Yikai Wang, Yushi Lan, Yuhao Wan, Ziheng Ouyang, Rui Zhao, Ming-Ming Cheng, Qibin Hou, Chen Change Loy</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Object insertion aims to seamlessly composite a reference object into a specified region of a background image. Recent diffusion-based methods achieve high visual quality but formulate insertion as a simple 2D inpainting task, providing no explicit control over the object's 3D pose and limiting their practical applicability. We propose DIRECT (Decomposed Injection for Reference Composition and Target-integration), a novel framework that integrates interactive pose manipulation with high-fidelity 2D image synthesis to enable pose-controllable object insertion. Our method decomposes the insertion conditions into three complementary components: appearance guidance capturing visual details from the reference object, geometry guidance derived from the user-adjusted 3D proxy, and context guidance from the target background. By injecting them through separate pathways, DIRECT avoids feature entanglement and simultaneously preserves reference appearance, follows the user-specified pose, and adapts the object to the target scene. We also introduce an automated data construction pipeline to improve the diversity and quality of training data. Experiments show that DIRECT outperforms previous methods in both geometric controllability and visual quality.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.06601</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>OpenSkill: Open-World Self-Evolution for LLM Agents</title>
|
||
<link>https://arxiv.org/abs/2606.06741</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.06741.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiling Yan, Dingjie Song, Hanrong Zhang, Wei Liang, Yuxuan Zhang, Yutong Dai, Lifang He, Philip S. Yu, Ran Xu, Xiang Li, Lichao Sun</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Self-evolving agents requires adaptation after deployment, but existing approaches assume a usable learning loop, such as curated skills, successful trajectories, or verifier signals. Real open-world deployments may provide none of these, offering only a task prompt. In this work, we study open-world self-evolution, where an agent must build both its skills and its own verification signals from scratch, using open-world resources but no target-task supervision. We propose OpenSkill, a framework that bootstraps this loop: it acquires grounded knowledge and verification anchors from documentation, repositories, and the web, synthesizes them into transferable skills, and refines those skills against self-built virtual tasks grounded in the anchors rather than in target answers. The open world thus supplies both the knowledge to be learned and a supervision-independent practice environment, with target-task supervision reserved for final evaluation. Across three benchmarks and two target agents, OpenSkill attains the best automated pass rate while satisfying the no-supervision constraint. Analysis shows its skills transfer across models without model-specific adaptation, and its self-built verifier aligns with ground-truth outcomes despite never accessing them.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.06741</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Robots Need More than VLA and World Models</title>
|
||
<link>https://arxiv.org/abs/2606.06556</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.06556.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Elis Karcini, Faisal Mehrban, Quang Nguyen, Mac Schwager, Arash Ajoudani, Cesar Cadena, Jan Peters, Marco Hutter, Haitham Bou-Ammar</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Generalist robot intelligence is often framed as a policy-scaling problem: collect more robot demonstrations, train larger Vision-Language-Action (VLA) models, and expect broader generalisation. In this position paper, we argue that this framing is incomplete. The central bottleneck is not only policy learning, but the absence of mechanisms that convert the world's abundant unstructured behavioural data into grounded robot supervision. Human motion, internet video, simulation rollouts, and interactive demonstrations contain rich information about tasks, goals, contacts, failures, and physical constraints, yet most of this information is not directly usable by robot policies because it lacks embodiment-specific action labels, task semantics, and reward structure. We identify four missing components for the next generation of robotics: data interfaces for autolabelling unstructured behaviour, embodiment interfaces for retargeting human motion to robot actions, world-model interfaces for physics-grounded 3D reasoning, and reward interfaces for inferring task progress and success from video and language. We survey recent progress in robot foundation models, cross-embodiment datasets, learning from video, world models, and reward modelling, and propose a research agenda for building robotics systems that can learn not only from robot demonstrations, but from the broader physical world.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.06556</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations</title>
|
||
<link>https://arxiv.org/abs/2606.05563</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.05563.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taewon Yun, Hyeonseong Park, Jeonghwan Choi, Hayoon Park, Yeeun Choi, Hwanjun Song</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by disputants' shifting emotions, intentions, and context. Existing testbeds rely on a few expert-authored domains, vary mainly strategic posture, and score every turn against every topic, introducing off-topic noise. We introduce SoCRATES, a benchmark for evaluating proactive LLM mediators in realistic, multi-domain testbeds. It constructs scenarios from real conflicts through an agentic pipeline across eight domains, probes five socio-cognitive adaptation axes (strategic posture, party composition, history length, emotional reactivity, and cultural identity), and scores each topic only on the turns that advance it via a topic-localized evaluator. The evaluator reaches 0.82 alignment with human experts, more than doubling a per-turn baseline. Benchmarking eight frontier LLMs, we find that even the strongest mediator closes only about a third of the unmediated consensus gap under diverse and realistic testbeds, with performance varying sharply by socio-cognitive axis, highlighting that progress lies in social adaptation to diverse conditions.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.05563</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents</title>
|
||
<link>https://arxiv.org/abs/2606.06087</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.06087.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aofan Yu, Chenyu Zhou, Tianyi Xu, Zihan Guo, Rong Shan, Zhihui Fu, Jun Wang, Weiwen Liu, Yong Yu, Weinan Zhang, Jianghao Lin</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context overhead and exposes skill content as plaintext. We present LatentSkill, a framework that converts textual skills into plug-and-play LoRA adapters through a pretrained hypernetwork. LatentSkill stores skill knowledge in weight space rather than context space, removing per-step skill tokens while preserving modular loading, scaling, and composition. On ALFWorld and Search-QA, LatentSkill outperforms the corresponding in-context skill baseline while using substantially fewer prefill tokens: it improves ALFWorld success by 21.4 and 13.4 points on the seen and unseen splits with 64.1% fewer prefill tokens, and improves Search-QA exact match by 3.0 points with 72.2% lower skill-token overhead. Further analysis shows that generated skill LoRAs form a structured semantic geometry, can be precisely controlled via the LoRA scaling coefficient, and can be composed through parameter-space arithmetic when skill components are aligned. These findings suggest that weight-space skills provide an efficient, modular, and less exposed substrate for extending LLM agents.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.06087</guid>
|
||
<pubDate>Thu, 04 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts</title>
|
||
<link>https://arxiv.org/abs/2606.05922</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.05922.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenbo Pan, Shujie Liu, Chin-Yew Lin, Jingying Zeng, Xianfeng Tang, Xiangyang Zhou, Yan Lu, Xiaohua Jia</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing optimization methods typically require ground-truth validation sets, yet such labeled data is difficult to acquire in practical deployment settings. To address this problem, we introduce Retrospective Harness Optimization (RHO), a self-supervised method that optimizes the agent harness using only past trajectories. Specifically, RHO selects a diverse coreset of challenging tasks from past trajectories and re-solves them in parallel. The agent analyzes these rollouts using self-validation and self-consistency, then generates candidate harness updates and selects the most effective one by its own pairwise self-preference. We evaluate RHO across three diverse domains, spanning software engineering, technical work, and knowledge work. Notably, a single optimization round improves the pass rate on SWE-Bench Pro from 59% to 78% without any external grading. Furthermore, our analysis demonstrates that RHO effectively targets prior failure modes. As a result, the optimized harness alters the agent's behavior patterns and sustains higher accuracy during long-horizon sessions.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.05922</guid>
|
||
<pubDate>Thu, 04 Jun 2026 09:26:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills</title>
|
||
<link>https://arxiv.org/abs/2606.07412</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07412.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chuan Xiao, Zhengbo Jiao, Shaobo Wang, Wei Wang, Bing Zhao, Hu Wei, Linfeng Zhang, Lin Qu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks. Existing synthetic data methods typically create tasks through fixed mutation or bug-injection procedures, making the resulting distributions largely independent of the agent's own weaknesses and training progress. We introduce Socratic-SWE, a closed-loop self-evolution framework that reuses the agent's historical solving traces as a source of training signal. Rather than treating traces only as evidence for reward computation, Socratic-SWE distills them into structured agent skills that summarize recurring failures and effective repair patterns. These skills then guide the generation of targeted repair tasks in real repositories. Candidate tasks are checked through execution-based validation and scored with a solver-gradient alignment reward, so that the retained tasks are both verifiable and useful for improving the Solver. The updated Solver produces new traces, enabling the task curriculum to adapt over successive rounds. Across SWE-bench Verified, SWE-bench Lite, SWE-bench Pro, and Terminal-Bench 2.0, Socratic-SWE consistently improves over self-evolving baselines under the same compute budget, reaching 50.40% on SWE-bench Verified after three iterations. These results suggest that solving traces can serve as a scalable substrate for self-evolving SWE agents.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07412</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams</title>
|
||
<link>https://arxiv.org/abs/2606.07454</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07454.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fuqiang Wang, Song Tan, Zheng Guo, Jiaohao Fu, Xinglong Xu, Bihui Yu, Jie Dong, Zheng Sun, Siyuan Li, Jingxuan Wei, Cheng Tan</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which interests shift and feedback accumulates. We introduce PaperFlow, a framework that organizes it into three coupled stages: Profiling, which constructs and maintains a structured, inspectable scholarly profile from heterogeneous cold-start evidence; Recommending, which ranks each date-specific paper stream through multi-signal aggregation under a fixed display budget; and Adapting, which updates user state from semantically distinct feedback signals and models interest drift across days. We further define a longitudinal user-day benchmark that fixes users, dates, candidate pools, visible inputs, and hidden simulated relevance labels under a shared temporal information boundary. The benchmark contains 24 simulated research users, 50 daily paper streams, 1,200 user-day episodes, 20,727 unique papers, and 497,448 episode-paper records. We additionally specify a blind human-evaluation protocol to validate alignment between automatic metrics and expert judgments. Experiments against five scientific recommendation baselines show that PaperFlow achieves the strongest oracle-based ranking, the highest behavioral alignment with simulated reading selections, and the best blind human-evaluation score.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07454</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>UniSHARP: Universal Sharp Monocular View Synthesis</title>
|
||
<link>https://arxiv.org/abs/2606.07514</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07514.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meixi Song, Dizhe Zhang, Hao Ren, Ruiyang Zhang, Bo Du, Ming-Hsuan Yang, Lu Qi</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across a continuum of camera systems, from conventional perspective cameras to wide-field-of-view, fisheye and omnidirectional panoramic settings. To overcome the pinhole-specific assumptions of SHARP, our key idea is to align various images in a unified omnidirectional latent space. Thus, we propose UniSHARP, which performs implicit alignment in both feature and Gaussian spaces. Specifically, Gaussian primitives are arranged along rays and radial distances in a ray-based universal representation, while 2D semantic and 3D spatial features extracted from UniK3D-inspired encoders are jointly decoded to generate the complete Gaussian cloud. To comprehensively evaluate our method, we construct a benchmark covering diverse imaging systems across various scenes. The benchmark is further stratified by field of view (FoV) to enable fine-grained assessment of the universal monocular rendering task. Extensive experiments on the proposed benchmark demonstrate the effectiveness of UniSHARP, outperforming alternative methods by a large margin. The project page can be found at: https://insta360-research-team.github.io/Unisharp-website/</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07514</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>dots.tts Technical Report</title>
|
||
<link>https://arxiv.org/abs/2606.07080</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07080.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shi Lian, Changtao Li, Bohan Li, Hankun Wang, Da Zheng, Junfeng Tian, Yufeng Ma, Colin Zhang, Kai Yu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We present dots.tts, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuous autoregressive models, our key innovations are threefold. First, we train an AudioVAE with multiple objectives to build a semantically structured and prediction-friendly continuous speech space. Second, we use full-history conditioning in the flow-matching head to preserve long-range consistency and reduce drift during generation. Third, we apply reward-free self-corrective post-training to the flow-matching head to further improve robustness and acoustic quality. After being trained on a large-scale multilingual corpus, dots.tts achieves the best average performance on Seed-TTS-Eval, with WERs of 0.94%/1.30%/6.60% and SIM scores of 81.0/77.1/79.5 on the zh/en/zh-hard test sets, respectively. Across other benchmarks, dots.tts also consistently demonstrates open-source state-of-the-art performance, exhibiting strong generation stability, voice cloning ability, and emotional expressiveness. For efficient inference, we further apply CFG-aware MeanFlow distillation, enabling low-latency speech generation with first-packet latencies of 85/54 ms in output streaming and dual-streaming modes, respectively. To facilitate reproducible research and practical deployment, we release the training and inference code, together with the pretrained, post-trained, and MeanFlow-distilled checkpoints, under the Apache 2.0 license.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07080</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders</title>
|
||
<link>https://arxiv.org/abs/2606.07473</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07473.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Georgii Aparin, Vadim Popov, Tasnima Sadekova, Assel Yermekova</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Whisper, a widely adopted ASR model, is known to suffer from hallucinations - coherent transcriptions generated for non-speech audio entirely disconnected from the input. We investigate whether hallucinations can be detected and mitigated through Whisper's internal representations. We extract audio encoder activations and evaluate two representation spaces: raw Whisper activations and Sparse AutoEncoder (SAE) latents. We show that both spaces encode linearly separable hallucination-related information, with discriminative power concentrated in a sparse feature subset and increasing toward deeper encoder layers. We propose two steering strategies: activation-space steering and SAE latent-space steering. SAE-based steering reduces hallucination rate from 72.63% to 14.11% for Whisper small and from 86.88% to 27.33% for Whisper large-v3 on the full non-speech test set, with small WER degradation on speech data, approaching the performance of fine-tuning-based methods.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07473</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>LIMMT: Less is More for Motion Tracking</title>
|
||
<link>https://arxiv.org/abs/2606.06953</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.06953.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Guan, Zekun Qi, Chenghuai Lin, Xuchuan Chen, Dairu Liu, Wenyao Zhang, Jilong Wang, Xinqiang Yu, He Wang, Li Yi</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We argue that high-quality motion data can steer tracking policies toward better optimization trajectories early in training. In this work, we introduce LIMMT (Less Is More for Motion Tracking). To our knowledge, this is the first data-centric study for physics-based humanoid motion tracking. We go beyond simply removing low-quality and erroneous clips, but define motion data quality through three dimensions: physics feasibility, diversity, and complexity. We show that even training with under 3% of AMASS yields better tracking performance than training with the full dataset. We further conduct data cleaning on the estimated web-sourced mocap data. Extensive experiments and analyses validate the effectiveness of our framework.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.06953</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Watch, Remember, Reason: Human-View Video Understanding with MLLMs</title>
|
||
<link>https://arxiv.org/abs/2606.07433</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07433.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Meng, Yue Tan, Qi Xu, Kuan Gao, Weisong Liu, Yanwei Li, Jason Li, Lingdong Kong, Haochen Wang, Qianyu Zhou, Jiangning Zhang, Guangliang Cheng, Yunhai Tong, Lu Qi, Minghsuan Yang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video scenarios. These scenarios require models to handle sparse evidence, long-range dependencies, multimodal alignment, and reliable inference under limited computational budgets. This work presents a human-view perspective on LLM-based video understanding, organized around three functional abilities: watching, remembering, and reasoning. Rather than treating video tasks as isolated benchmarks, this view provides a unified structure for analyzing how video MLLMs acquire evidence, preserve context, and produce grounded outputs. We introduce a formulation that characterizes video understanding systems by their perceptual representations, memory states, reasoning traces, and final predictions. Based on this formulation, we identify challenges in spatio-temporal perception, efficient long-video processing, memory modeling, streaming understanding, and faithful reasoning. Representative methods are organized by their roles in video MLLM systems. Watching covers fine-grained, comprehensive, audio-visual, and efficient perception. Remembering includes offline and streaming memory, while reasoning covers text-only reasoning and thinking with videos. We further examine application domains such as egocentric, sports, instructional, medical, and narrative videos, and cover training datasets and evaluation benchmarks across task types, supervision formats, modalities, and capability dimensions. Finally, we outline open problems and future directions for scalable, memory-aware, and evidence-grounded video intelligence. Related works will be continuously traced at https://github.com/marinero4972/Awesome-HumanView-VideoUnderstanding.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07433</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization</title>
|
||
<link>https://arxiv.org/abs/2606.07326</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07326.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Li, Menghan Xia, Gongye Liu, Xintao Wang, Conglang Zhang, Lei Ke, Yuxuan Lin, Ruihang Chu, Pengfei Wan, Kun Gai, Yujiu Yang</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we present AnchorWorld, a framework that advances egocentric simulation through enhanced interaction integrity and a flexible mechanism for world customization. First, we utilize 3D human motion as the primary interaction modality. To complement the out-of-view or truncated body parts in egocentric views, we introduce an auxiliary training supervision that incorporates exogenous viewpoints decoupled from the agent's first-person sensorium. It allows the model to observe the agent's full-body positioning relative to the environment, facilitating a more robust spatial grounding of human-world interactions. Furthermore, we propose a simple yet effective mechanism for customizing self-evolving worlds. This is achieved by defining anchor views within a unified world coordinate system, coupled with textual descriptions dictating the dynamic evolution of local scenes. Experimental results show that AnchorWorld significantly outperforms state-of-the-art baselines, while ablation studies validate the effectiveness of our key designs. Notably, our customization scheme exhibits promising spatio-temporal geometric consistency and adheres strictly to the prescribed evolutionary dynamics.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07326</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism</title>
|
||
<link>https://arxiv.org/abs/2606.07512</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07512.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cong Chen, Guo Gan, Kaixiang Ji, ChaoYang Zhang, Zhen Yang, Guangming Yao, Hao Chen, Jingdong Chen, Yi Yuan, Chunhua Shen</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic exploration process. As a plug-and-play framework, it incrementally streams videos to construct a Hierarchical Graph Memory, a top-down three-tier architecture for semantic abstraction, anchored by a foundational graph capturing spatiotemporal and causal relations. During inference, the reasoning model employs agentic tool-augmented retrieval, navigating hierarchies, searching nodes, and traversing logical edges via an Observation-Reason-Action loop. Experiments show MemDreamer achieves SOTA results across four mainstream benchmarks, narrowing the gap with human experts to only 3.7 points. It constrains the reasoning context window to merely 2% of full-context ingestion while delivering a 12.5 point absolute accuracy gain. Furthermore, statistical analysis uncovers a strong positive linear correlation between an VLM's performance on logic reasoning and long-video understanding benchmarks, establishing agentic capability scaling as a new paradigm for multimodal comprehension.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07512</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MMAE: A Massive Multitask Audio Editing Benchmark</title>
|
||
<link>https://arxiv.org/abs/2606.07229</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07229.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyang Ma, Ruiqi Yan, Ruiyang Xu, Jie Fang, Zhikang Niu, Yi-Wen Chao, Wenming Tu, Tianrui Wang, Auden, Qi Chen, Wenxi Chen, Jiaying Chi, Yanru Huo, Zixuan Jiang, Xiquan Li, Yalin Li, Junxi Liu, Minghao Liu, Binghao Qiang, Yijia Shan, Zheshu Song, Tian Tan, Zixiang Wang, Zeyu Xie, Zhifei Xie, Xiaoyu Xing, Qixiang Xu, Chen Yang, Guanrou Yang, Shan Yang, Yifan Yang, Steve Yves, Haotian Zhang, Haina Zhu, Kai Yu, Liefeng Bo, Eng-Siong Chng, Xie Chen</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing. Spurred by the shift toward intelligent creation, interactive editing has rapidly expanded from visual domains, pioneered by models like Nano-banana 2 for images and Gemini-Omni for video, into audio. However, the current evaluation infrastructure lags severely, remaining highly fragmented and restricted to specific subdomains or basic operations. Unlike existing benchmarks that are limited in scope, MMAE extends to a broad spectrum of real-world scenarios, encompassing 7 distinct audio modalities, including sound, speech, music, and their mixtures. Furthermore, we establish a comprehensive taxonomy spanning 6 levels of task complexity, from basic modifications to multi-hop reasoning and multi-round editing, 2 levels of granularity, and 8 distinct operation types. Meticulously curated through human-agent collaboration, MMAE comprises 2,000 high-fidelity samples paired with a pioneering rubric-based evaluation framework. By decomposing free-form tasks into 17,741 verifiable criteria, this robust rubric-based paradigm enables a precise, multi-dimensional assessment of both instruction following and context consistency. Our extensive evaluation of leading models reveals that current systems remain far from achieving reliable edits. Strikingly, the Exact Match Rate (EMR) consistently falls below 5% and plummets to an absolute 0% in complex, mixed-modality tasks, exposing critical bottlenecks in precise execution and structural robustness. We hope MMAE will serve as a catalyst for future advances in the intelligent creation community, providing a clear diagnostic roadmap and establishing a standardized, long-lasting evaluation paradigm for next-generation audio editing systems.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07229</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>On the Geometry of On-Policy Distillation</title>
|
||
<link>https://arxiv.org/abs/2606.07082</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07082.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhennan Shen, Yanshu Li, Qingyu Yin, Chak Tou Leong, Zhilin Wang, Yanxu Chen, Rongduo Han, Sunbowen Lee, Yi R. Fung</p><p><b>Upvotes:</b> 71</p><p><b>Summary:</b> On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of OPD updates in parameter space and compare it with supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR). A suite of parameter-space diagnostics consistently places OPD in a relaxed off-principal regime: compared with SFT, its updates affect fewer weights and avoid principal directions more strongly, while compared with RLVR, they remain less tightly constrained. Beyond this static localization, OPD exhibits subspace locking: its cumulative updates rapidly enter a narrow low-dimensional channel. Constraining training to the update subspace formed early in training preserves OPD performance but substantially degrades SFT, indicating that the locked subspace is functionally sufficient for OPD. Control experiments further show that sparsifying the update tokens and shifting rollout generation off-policy preserve the rank dynamics, whereas mixing the OPD objective with RLVR changes them. Overall, these results suggest that OPD is not merely an intermediate point between SFT and RLVR, but induces its own update geometry in parameter space.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07082</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings</title>
|
||
<link>https://arxiv.org/abs/2606.07502</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07502.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songhao Wu, Zhongxin Chen, Yuxuan Liu, Heng Cui, Cong Li, Rui Yan</p><p><b>Upvotes:</b> 91</p><p><b>Summary:</b> Large language models exhibit impressive zero-shot capabilities across a wide range of downstream tasks. However, they struggle to function as off-the-shelf embedding models, leading to suboptimal performance on massive text embedding benchmarks. In this paper, we identify a potential cause underlying this deficiency. Our motivation stems from an unexpected observation: text embeddings tend to align with frequent but uninformative tokens when projected onto the vocabulary space. We argue that this excessive expression of high-frequency tokens suppresses the model's ability to capture nuanced semantics. To address this, we introduce EmbedFilter, a simple linear transformation designed to refine text embeddings derived from LLMs directly. Specifically, we uncover that the unembedding matrix within LLMs encodes a latent space that is actively writing these frequent tokens into embedding space. By filtering out this subspace, EmbedFilter suppress the influence of high-frequency tokens, thereby enhancing semantic representations. As a compelling byproduct, this enables an inherent dimensionality reduction, lowering index storage and speedup retrieval while fully preserving the refined embedding quality. Our experiments across multiple LLM backbones demonstrate that LLMs equipped with EmbedFilter achieve superior zero-shot downstream performance even with significantly reduced embedding dimensions. We hope our findings provide deeper insights into the mechanisms of LLM-based representations and inspire more principled designs to improve text embeddings training. Our code is available at https://github.com/CentreChen/EmbFilter.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07502</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SWE-Explore: Benchmarking How Coding Agents Explore Repositories</title>
|
||
<link>https://arxiv.org/abs/2606.07297</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07297.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaoqiu Zhang, Yuhang Wang, Jialiang Liang, Yuling Shi, Wenhao Zeng, Maoquan Wang, Shilin He, Ningyuan Xu, Siyu Ye, Kai Cai, Xiaodong Gu</p><p><b>Upvotes:</b> 110</p><p><b>Summary:</b> Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresolved), neglecting fine-grained agent capabilities such as repository understanding, context retrieval, code localization, and bug diagnosis. In this paper, we introduce SWE-Explore, a benchmark that isolates the evaluation of repository exploration, a critical capability of coding agents. Given a repository and an issue, SWE-Explore asks an explorer to return a ranked list of relevant code regions under a fixed line budget. SWE-Explore covers 848 issues across 10 programming languages and 203 open-source repositories. For each instance, we derive line-level ground truth from independent agent trajectories that successfully solved the same issue, distilling the specific code regions their solution paths actually consulted. We evaluate exploration along coverage, ranking, and context-efficiency dimensions, showing that these metrics strongly track downstream repair behavior. Across a broad set of retrieval methods, general coding agents, and specialized localizers, we find that agentic explorers form a clear tier above classical retrieval. While file-level localization is already strong for modern methods, line-level coverage and efficient ranking remain the key axes differentiating state-of-the-art explorers.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07297</guid>
|
||
<pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning</title>
|
||
<link>https://arxiv.org/abs/2606.07436</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.07436.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyuan Li, Zhengdong Hu, Jun Wang, Hehe Fan, Yi Yang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> This paper explores agentic 3D spatial understanding, i.e., MLLM agents performing 3D reasoning through tool use. Existing methods often misuse tools and exhibit biased tool preferences under 3D scenarios, leaving the agentic paradigm with only marginal gains over non-agentic strategies. We reveal that 3D spatial reasoning tasks are heterogeneous across scenes, while these agents apply a uniform tool-use strategy to all scenes rather than selecting tools according to the specific scene and task. To address this, we propose Skill-3D, a framework that learns self-evolving scene-aware skills. Specifically, Skill-3D identifies the task scene and records the agent's tool-use trajectory into a Scene Memory, where successful trajectories from similar scenes are aggregated and distilled into a reusable scene-aware skill, with failed ones attached to the skill as lessons. During training, once a similar scene recurs, the corresponding skill is injected to guide the agent, producing new trajectories whose successes and failures further refine the skill, forming a loop in which the memory and the skill library co-evolve. Experiments show that Skill-3D substantially improves tool utilization in 3D spatial reasoning (from 39% to 78% on VSI-Bench), driving the agent toward correct and sufficient tool use. For instance, it improves Gemini-3-Flash by 67% on MMSI-Bench. Furthermore, we conduct agentic post-training over skill-guided trajectories, which boosts Qwen3-VL-8B by 43% on VSI-Bench.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.07436</guid>
|
||
<pubDate>Fri, 05 Jun 2026 16:33:44 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Light-WAM: Efficient World Action Models with State-Fusion Action Decoding</title>
|
||
<link>https://arxiv.org/abs/2606.08242</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.08242.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziang Li, Dongzhou Cheng, Yibin Wang, Shiyue Wang, Xiaoyang Xu, Lingxuan Weng, Juan Wang, Jiaqi Wang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> World Action Models (WAMs) extend robot policy learning by incorporating future prediction as an additional training objective, encouraging the policy to encode task-relevant temporal structure in its representations. Current WAMs often rely on large-scale generative architectures that incur high training costs and inference latency, making them difficult to deploy as efficient closed-loop policies. We propose Light-WAM, a lightweight World Action Model for efficient robot manipulation. Specifically, it is built with a compact video backbone and performs future-video supervision in a downsampled latent space, reducing the cost of video co-training while retaining its benefits for representation learning. For action prediction, Light-WAM introduces the StateFusionActionExpert, which reads adapted states from multiple backbone layers, fuses them through learned-query pooling, and directly predicts action chunks in a single forward pass. This design provides an efficient interface between video backbone representations and robot actions, avoiding the need for heavy generative action experts. Experiments demonstrate that Light-WAM maintains strong performance on LIBERO and achieves usable multi-task performance on RoboTwin 2.0, while using only 0.44B trainable parameters. It also achieves 72.03ms inference latency with 4.1GiB peak GPU memory and improved training throughput.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.08242</guid>
|
||
<pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses</title>
|
||
<link>https://arxiv.org/abs/2606.08348</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.08348.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaojun Wu, Cehao Yang, Honghao Liu, Xueyuan Lin, Wenjie Zhang, Zhichao Shi, Xuhui Jiang, Chengjin Xu, Jia Li, Jian Guo</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> LLM agents increasingly rely on external inference conditions: prompts, tools, memory, SOPs, skills, and harness feedback. These assets can improve task execution without changing model weights, but they are often revised by heuristic reflection or by reusing observed successes and failures as if counts alone were reliable belief. We introduce Bayesian-Agent, a native and cross-harness framework that treats reusable skills and SOPs as hypotheses about whether a frozen model will succeed under a particular prompt, context, and harness environment. Bayesian-Agent records verified trajectory evidence, maintains a feature-conditioned categorical posterior over each skill, and maps posterior state into inspectable actions such as patch, split, compress, retire, and explore. Model-facing prompts receive executable guardrails and failure-mode patches, while posterior summaries remain available for audit. With deepseek-v4-flash, incremental repair improves SOP-Bench from 80\% to 95\%, Lifelong AgentBench from 90\% to 100\%, and RealFin-Bench from 45\% to 65\%. We further evaluate Bayesian-Agent's native backend and optional GenericAgent, mini-swe-agent, and Claude Code backends. The results include positive, negative, saturated, and case-study settings, suggesting that agent skill evolution is best viewed as posterior-guided harness optimization rather than uncalibrated prompt accumulation. The source code is available at https://github.com/DataArcTech/Bayesian-Agent.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.08348</guid>
|
||
<pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning</title>
|
||
<link>https://arxiv.org/abs/2606.08035</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.08035.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hangui Lin, Yan Shu, Zhengyang Liang, Chi Liu, Xiangrui Liu, Minghao Qin, Teng Long, Zheng Liu, Nicu Sebe</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a leading paradigm for enhancing visual reasoning in Multimodal Large Language Models (MLLMs). However, existing RLVR methods optimize primarily for the reasoning outcome, fundamentally overlooking the fine-grained cross-modal coordination required during the generation process. Through token-level analyses and controlled interventions, we reveal that during Chain-of-Thought (CoT) reasoning, MLLMs frequently fail to dynamically alternate between extracting visual evidence and synthesizing textual context-a coordination breakdown that is causally linked to reasoning failures. Motivated by these findings, we propose DyCo-RL, which integrates dynamic cross-modal coordination into RLVR optimization. Specifically, DyCo-RL uses the Fisher-Rao geodesic distance to measure within-modality attention shifts, assigning tokens to either visually-oriented or text-oriented functional roles. It then evaluates the alignment between a token's actual attention allocation and its assigned role, leveraging this score for alignment-guided advantage reweighting during policy optimization. Extensive experiments demonstrate that the algorithm-agnostic DyCo-RL, when applied to Qwen2.5-VL-3B/7B, consistently improves four representative RLVR algorithms across seven benchmarks spanning visual-centric and mathematical reasoning.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.08035</guid>
|
||
<pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?</title>
|
||
<link>https://arxiv.org/abs/2606.08063</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.08063.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Tang, Jianmin Chen, Youyang Zhai, Wei Wei, Runtao Liu, Mengjie Zhao, Xiangyu Wu, Qingfa Xiao, Qifeng Chen</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions. While existing robustness enhancement approaches exist, they are limited: black-box feature alignment lacks interpretability, and white-box text-based reasoning cannot restore lost pixel-level details. This work investigates a fundamental research question: Can MLLMs recover corrupted visual content by themselves? To address this, we propose Robust-U1, a novel framework that equips MLLMs with explicit visual self-recovery capability for robust understanding. The approach comprises three core stages: supervised fine-tuning for initial reconstruction, reinforcement learning with dual rewards (pixel-level SSIM and semantic-level CLIP similarity) for aligning high visual quality, and multimodal reasoning that jointly considers both the corrupted input and the recovered image. Extensive experiments demonstrate that Robust-U1 achieves state-of-the-art robustness on the real-world corruption benchmark and maintains superior performance under adversarial corruptions on general VQA benchmarks. Analysis confirms that high-quality visual recovery directly enhances reasoning performance, establishing self-recovery as a critical mechanism for robust visual understanding. The source code is available at https://github.com/jqtangust/Robust-U1.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.08063</guid>
|
||
<pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning</title>
|
||
<link>https://arxiv.org/abs/2606.08572</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.08572.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Wang, An Ping, Yanghai Wang, Yuanxing Zhang, Shihao Li, Hanyan Bian, Yichi Ren, Yize Zhang, Han Wang, Haowen Chen, Junze Li, Jiaqi Wang, Yiyang Hu, Zhuze Xu, Zijie Zhang, Jiaheng Liu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> While Omni-modal Large Language Models (OLLMs) have demonstrated impressive capabilities in jointly processing audio and visual streams, their ability to strictly adhere to complex, multi-faceted user instructions remains largely unexplored. Existing benchmarks primarily focus on holistic video understanding or text-only instruction following, failing to capture the intricate interplay between modalities and user constraints. To bridge this gap, we introduce OmniCap-IF, the first comprehensive benchmark specifically designed to evaluate instruction-following capabilities in omni-modal captioning. OmniCap-IF incorporates a systematic framework that assesses captions on two dimensions: format correctness and content correctness. Our benchmark encompasses 50 distinct constraint types across pure visual, pure audio, and audio-visual modalities, while integrating Temporal Grounding to assess spatio-temporal precision. Extensive evaluations of prominent models on 1,920 high-quality samples reveal significant performance disparities. Furthermore, our analysis uncovers a critical "format-content tradeoff", demonstrating that increasing formatting complexity directly degrades models' omni-modal reasoning abilities. Finally, to advance the field, we curate a 54K instruction-tuning dataset, OmniCap-IF-54K and present OmniCaptioner-IF, which achieves notable improvements in both complex instruction adherence and general omni-modal captioning performance.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.08572</guid>
|
||
<pubDate>Sun, 07 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>CoVEBench: Can Video Editing Models Handle Complex Instructions?</title>
|
||
<link>https://arxiv.org/abs/2606.08415</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.08415.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiangtao Wu, Jiaming Wang, Yiwen He, Yuanxing Zhang, Shihao Li, Dunyuan Liu, Xuedong Zhao, Jialu Chen, Zekun Moore Wang, Jiaheng Liu</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> While recent text-guided video editing models excel at elementary tasks (e.g., style transfer, object insertion), real-world user requests are highly compositional. A single prompt often demands multiple coupled edits, such as modifying subjects, actions, and camera views, while strictly preserving unrelated spatiotemporal content. Existing benchmarks, heavily constrained by isolated edits and coarse global metrics, fail to diagnose how models handle such complex workflows. To address this gap, we introduce CoVEBench, a compositional video editing benchmark comprising 416 curated source videos, 626 multi-point editing instructions, and 9,990 fine-grained checklist items. Covering diverse editing dimensions, CoVEBench evaluates models via MLLM-judged instruction compliance and video fidelity, alongside automated metrics for video quality. Extensive experiments reveal that compositional editing remains a profound challenge: current models frequently omit edits, violate preservation constraints, or introduce artifacts when handling multiple operations simultaneously. CoVEBench provides a challenging, diagnostic testbed to advance video editing toward realistic user workflows.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.08415</guid>
|
||
<pubDate>Sun, 07 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing</title>
|
||
<link>https://arxiv.org/abs/2606.09811</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09811.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jisong Cai, Long Ling, Shiwei Chu, Zhongshan Liu, Jiayue Kang, Zhixuan Liang, Wenjie Xu, Yinan Mao, Weinan Zhang, Xiaokang Yang, Ru Ying, Ran Zheng, Yao Mu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> World-action models have emerged as a promising paradigm for robot manipulation, jointly modeling visual scene dynamics and actions to inject physical priors into policy learning. However, existing world-action models couple world prediction and action execution at the same temporal resolution, forcing the world branch to model near-term frame variations that are redundant and weakly informative. We posit that strictly binding world prediction and action execution to the same temporal rhythm may underutilize the potential of the video branch for embodied control. Therefore, we propose AHA-WAM, an Asynchronous Horizon-Adaptive World-Action Model built on a dual Diffusion Transformer (DiT) architecture that reorganizes world-action modeling around this temporal asymmetry. AHA-WAM instantiates the video DiT as a low-frequency world planner that maintains rolling key-value memory over past observations and exposes reusable layerwise latent context encoding long-horizon scene evolution, while a high-frequency action DiT executes short action chunks in closed loop by querying this context through layerwise joint attention. To support asynchronous execution, we introduce horizon-adaptive offset training and Observation-Guided Video-Context Routing (OVCR), which together let the action expert exploit long-horizon world context while remaining responsive to real-time execution state without rerunning the video DiT. Experiments on RoboTwin and real-world manipulation tasks show that AHA-WAM achieves state-of-the-art performance without any robot-data pretraining, attaining 92.80% average success on RoboTwin and 78.3% success across 4 real-world tasks, while reaching 24.17 Hz closed-loop control with a 4.59x speedup over Fast-WAM.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09811</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SwiftVR: Real-Time One-Step Generative Video Restoration</title>
|
||
<link>https://arxiv.org/abs/2606.09516</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09516.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Yan, Xiangyu Chen, Xinlin Zhong, Haibin Huang, Chi Zhang, Jie Liu, Jiantao Zhou, Xuelong Li</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Real-time video restoration (VR) for live streams requires high-resolution outputs under strict per-frame latency constraints. Existing one-step diffusion-based VR models remain difficult to deploy on consumer-grade GPUs due to two main bottlenecks: quadratic spatial attention at high resolutions and the latency-memory overhead of large video autoencoders. We present SwiftVR, a streaming one-step generative VR framework that reduces both bottlenecks under a causal chunk-wise protocol. For attention, mask-free shifted-window self-attention gathers each spatial window into a dense tensor via deterministic indexing, keeping all attention calls on the dense scaled dot-product attention path without masks, cyclic shifts, padding, or hardware-specific sparse kernels. Because SwiftVR uses only standard dense SDPA calls, the trained model transfers to consumer GPUs without retraining or custom kernels. For autoencoding, a lightweight Restoration-aware Autoencoder enables fast chunk-wise decoding while preserving reconstruction quality. On a single H100, SwiftVR sustains 31~FPS at 2560x1440 and 14~FPS at 3840x2160, whereas all compared diffusion-based VR baselines exceed the memory limit at 4K. On a consumer RTX~5090, SwiftVR reaches 26~FPS at 1920x1080. To our knowledge, SwiftVR is the first generative VR model to achieve real-time 1080p streaming on a consumer-grade GPU, while attaining strong no-reference perceptual quality with lower inference cost. Project is available at https://h-oliday.github.io/SwiftVR.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09516</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics</title>
|
||
<link>https://arxiv.org/abs/2606.09826</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09826.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingxian Lin, Shengju Qian, Yuqi Liu, Yi-Hua Huang, Yiyu Wang, Wei Huang, Yitang Li, Fan Zhang, Zeyu Hu, Lingting Zhu, Xin Wang, Xiaojuan Qi</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Vision-language model (VLM) agents are increasingly deployed in interactive game environments. Yet game benchmarks for VLM agents typically report a single first-attempt score per (agent, game) pair, focus on single-agent Solo play, and lack unified protocols for evaluating heterogeneous agent classes (commercial VLMs, open-weight VLMs, and specialized game policies) on the same footing. We address these gaps with OmniGameArena, a real-time benchmark of twelve newly built Unreal Engine 5 games spanning Solo (7), PvP (3), and Coop (2) with unified action interfaces, and the Improvement Dynamics Curve (IDC), an agentic-reflection harness in which a tool-using reflector LLM autonomously refines a bounded skill prompt across multiple rounds. Beyond cold-start leaderboard scores, IDC exposes two additional observables for each (agent, game) pair: how the score evolves across reflection rounds, and how the learned skill behaves on held-out task variants. We report these observables for twelve VLM agents on the cold-start leaderboard and four top agents under IDC.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09826</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>End-to-End Context Compression at Scale</title>
|
||
<link>https://arxiv.org/abs/2606.09659</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09659.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ang Li, Sean McLeish, Haozhe Chen, Nimit Kalra, Zaiqian Chen, Artem Gazizov, Venkata Anoop Suhas Kumar Morisetty, Bhavya Kailkhura, Harshitha Menon, Zhuang Liu, Brian R. Bartoldson, Tom Goldstein, Sanae Lotfi, Micah Goldblum, Pavel Izmailov</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt. Furthermore, many methods require the input to fit within the target model's context window, and are generally incompatible with modern production inference engines. Encoder-decoder compressors, which map a long token sequence to a shorter sequence of latent embeddings consumed by a decoder, are an appealing alternative in principle. However, existing approaches are not competitive with KV cache compression on the accuracy-efficiency frontier. In this work, we revisit encoder-decoder compression and close this gap. We first perform an architecture search, pre-training many variants from scratch to determine how best to design and train encoder-decoder compressors. Guided by our findings, we continually pre-train a family of 0.6B-encoder, 4B-decoder models on over 350B tokens each, at compression ratios of 1:4, 1:8, and 1:16. We introduce Latent Context Language Models (LCLMs), a family of compressors that improve the Pareto frontier across general-task performance, compression speed, and peak memory usage. We demonstrate that LCLMs serve as efficient backbones for long-horizon agents, letting the agent skim through a compressed long context and adaptively expand relevant segments on demand.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09659</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Echo-Memory: A Controlled Study of Memory in Action World Models</title>
|
||
<link>https://arxiv.org/abs/2606.09803</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wayne King, Zeyue Xue, Yuxuan Bian, Jie Huang, Haoran Li, Yaowei Li, Yaofeng Su, Yuming Li, Haoyu Wang, Shiyi Zhang, Songchun Zhang, Yuwei Niu, Sihan Xu, Junhao Zhuang, Haoyang Huang, Nan Duan</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We present Echo-Memory, a controlled study of memory mechanisms in action-conditioned world models. These models generate multi-segment videos from a first frame, text prompt, and camera-action sequence, but their central failure is often memory rather than local image synthesis: after the camera leaves and returns, the scene or salient object may silently change. Existing memory designs are hard to compare because gains are entangled with backbone, training, retrieval, and evaluation differences. Echo-Memory fixes the action-to-video interface and varies only how history is stored and read by the generator. Under a shared video diffusion backbone, optimizer, camera-action representation, sampler, and evaluation pipeline, we compare raw context, compression-based memory, spatial summaries with different read-out paths, and state-space recurrence. This matched matrix separates four otherwise conflated axes: capacity, compression, read-out, and recurrence. We also evaluate memory through a three-branch protocol: replay quality, in-domain loop revisit, and open-domain return probes. The branches routinely disagree, showing that replay fidelity is not a sufficient proxy for remembering a world. Three findings follow. Raw context is a strong capacity baseline and improves open-domain return far more than it improves replay metrics. Compactness is not a free substitute for capacity: aggressive spatial and hybrid-compression memories lose the salient evidence needed for return. Finally, block-wise state-space recurrence is the strongest open-domain return mechanism in our matrix, showing that the structure of implicit memory matters as much as the decision to use it. These results provide a compact protocol for studying memory in action world models beyond isolated replay metrics.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09803</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Rethinking the Divergence Regularization in LLM RL</title>
|
||
<link>https://arxiv.org/abs/2606.09821</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09821.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiarui Yao, Xiangxin Zhou, Penghui Qi, Wee Sun Lee, Liefeng Bo, Tianyu Pang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Reinforcement learning (RL) has become a key component of post-training large language models (LLMs). In practice, LLM RL is often off-policy because of training-inference mismatch and policy staleness, making trust-region control essential for stable optimization. Mainstream methods such as PPO and GRPO approximate this control with a ratio-clipping mechanism, but the importance ratio can be a poor proxy for distributional shift in long-tailed vocabularies. Recent work such as DPPO addresses this mismatch by replacing ratio-based clipping with a divergence-based mask, yielding a trust region defined by the sampled token's absolute probability shift. However, DPPO still relies on a hard mask: once a token crosses the trust-region boundary in a harmful direction, its gradient is discarded rather than corrected. To address this, we propose Divergence Regularized Policy Optimization (DRPO), which replaces the hard mask with a smooth advantage-weighted quadratic regularizer on policy shift. DRPO preserves the same trust-region geometry as DPPO while inducing bounded, continuous gradient weights that attenuate diverging updates and provide corrective signals beyond the boundary. Experiments across model scales, architectures, and precision settings show that DRPO improves the stability and efficiency of LLM RL training.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09821</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks</title>
|
||
<link>https://arxiv.org/abs/2606.09669</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09669.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongcheng Gao, Hailong Qu, Jingyi Tang, Jiahao Wang, Zihao Huang, Hengkang Qiao, Shihong Huang, Junming Yang, Yi Li, Hongyixuan Yuan, Wenjie Li, Bohan Zeng, Wenbo Li, Bo Wang, Jianhui Liu, Olive Huang, Haoyang Huang, Wentao Zhang, Guoqing Huang, Nan Duan, Yinpeng Dong</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Spatial reasoning is a foundational capability for multimodal large language models (MLLMs) to perceive and operate within the physical world. However, existing benchmarks predominantly rely on passive evaluation (e.g., static VQA) or simulator-specific pipelines, failing to assess general interactive spatial understanding. We introduce SpatialWorld, a unified benchmark designed specifically for evaluating the interactive spatial understanding of multimodal agents in complex real-world tasks. Integrating eight heterogeneous simulation backends under a shared, simulator-agnostic protocol, SpatialWorld features 760 human-annotated tasks across diverse domains (e.g., household routines, travel, social collaboration). Agents must solve tasks under vision-only partial observability, actively gathering egocentric visual evidence and expressing decisions via a unified, text-based action interface native to MLLMs. For reliable evaluation, each task includes a human-validated initial state, a reference trajectory, and a terminal-state verifier. Evaluating 15 advanced agents reveals that robust spatial task solving remains challenging: the strongest model, GPT-5, achieves an average task success rate (TSR) of only 17.4%, while the leading open-source model, Qwen-3.5, reaches 14.1%. Further analysis exposes a clear mismatch between task success and execution efficiency, alongside substantial domain-specific performance variations. These bottlenecks in active exploration and long-horizon planning position SpatialWorld as a rigorous testbed for future spatial agents.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09669</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research</title>
|
||
<link>https://arxiv.org/abs/2606.09730</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09730.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pu Ning, Quan Chen, Kun Tao, Xinyu Tang, Tianshu Wang, Qianggang Cao, Xinyu Kong, Zujie Wen, Zhiqiang Zhang, Jun Zhou</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows remain inherently finite. Recent work explores a paradigm where a main agent decomposes tasks and dispatches subtasks to subagents, which execute and return only summarized results, conserving the main agent's context budget. However, performing this well requires delegation intelligence: the ability to decompose complex tasks, determine when and what to delegate, and integrate returned results into the ongoing workflow. Training data for this capability is scarce in naturally occurring text, and to our knowledge, how to synthesize such data and train models to acquire this capability remains largely unexplored in the open-source community. To bridge this gap, we present a preliminary exploration targeting deep research, a representative long-horizon agent task. Specifically, we design a harness that guides the model toward high-quality task decomposition and delegation, while constraining subagents to return results properly to support the main agent's workflow. The harness-guided trajectories naturally encode correct delegation decisions, which we use as supervised fine-tuning data to internalize delegation intelligence into model weights. Our resulting model, SearchSwarm-30B-A3B, achieves 68.1 on BrowseComp and 73.3 on BrowseComp-ZH, the best results among all models of comparable scale. We will release our harness, model weights, and training data to facilitate future research.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09730</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders</title>
|
||
<link>https://arxiv.org/abs/2606.09323</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09323.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Pang, Xiangru Jian, Hehan Li, Zhixuan Yu, Alex Xue, Jinyang Li, Zhengyuan Dong, Xinjian Zhao, Hao Xu, Chao Zhang, Reynold Cheng, M. Tamer Özsu, Tianshu Yu</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare directly even when they operate on similar tabular signals. We introduce TRL-Bench, a multi-granular tabular representation learning (TRL) benchmark that standardizes cross-paradigm representation-level evaluation: each encoder exports row-, column-, or table embeddings through its supported wrapper, and shared lightweight heads probe them across three suites: TRL-CTbench (column/table), TRL-Rbench (row), and TRL-DLTE (compositional Data-Lake Table Enrichment spanning all three granularities). To support this standardized setting, we release curated benchmark assets and task reformulations, including 50 OpenML tables with 123 verified targets, 16 row-pair linkage rewrites, and a 47,772-table DLTE lake derived from 1,379 parent tables. Across 20 models and 16 tasks, TRL-Bench shows that once downstream conditions are standardized, encoder quality is capability-specific rather than captured by a single leaderboard. In TRL-CTbench, generic text encoders often lead on tasks with strong surface-text signal, while tabular specialists win where their pretraining objective aligns with the task. In TRL-Rbench, within-table prediction and cross-table linkage favor different training regimes, with atomic linkage performance correlating strongly with the row-matching stage of DLTE pipelines. In TRL-DLTE, the strongest pipelines combine capability-matched specialists rather than reuse a single encoder, and top end-to-end quality depends on non-additive compositional fit rather than per-stage marginal rank alone. TRL-Bench provides a common protocol for measuring reusable signal in exported tabular representations under shared downstream conditions. Code and data: https://github.com/LOGO-CUHKSZ/TRL-Bench</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09323</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions</title>
|
||
<link>https://arxiv.org/abs/2606.09076</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09076.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Jin, Huanqia Cai, Zhen Li, Zechao Zhan, Dengyang Jiang, Aiming Hao, Yuming Jiang, Chunle Guo, Peng Gao, Ming-Ming Cheng, Steven C. H. Hoi</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Reward models are central to text-to-image post-training, but visual preference is subjective and better represented as a distribution over rubric scores than as a deterministic scalar. Existing scalar, score-token, and pairwise reward models over-compress uncertainty and fine-grained score differences, while reasoning-based generative rewards provide stronger judgments but are costly to deploy and difficult to use as direct optimization signals. We propose Z-Reward, a teacher-student reward modeling framework that decouples reasoning-heavy judgment from efficient reward deployment. The teacher is a large VLM that uses reasoning to infer rubric-aligned score distributions, and is trained with Group-wise Direct Score Optimization (GDSO), which combines policy-gradient rewards from distribution expectations with direct pointwise and pairwise supervision on score distributions and score gaps. The student is trained with Reasoning-Internalized Score Distillation (RISD), which transfers the teacher's reasoning-conditioned score distribution into a compact VLM without requiring explicit reasoning chains at inference time. On our internally annotated evaluation set, the 27B GDSO teacher reaches 89.6% human preference accuracy, outperforming SFT, RewardDance, and GRPO, while the 9B RISD student reaches 88.6%, outperforming the OPD baseline and closely matching the larger teacher. We further show that Z-Reward can serve as a differentiable reward signal for text-to-image optimization, yielding a 41.3% net human-preference improvement over the SFT baseline.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09076</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention</title>
|
||
<link>https://arxiv.org/abs/2606.09079</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09079.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Wang, Qifan Zhang, Jiachen Yu, Tian Liang, Dongyang Ma, Xiang Hu, Zibo Lin, Chunyang Li, Zhichao Wang, Jia Li, Yujiu Yang, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose Lookahead Sparse Attention (LSA), a novel inference paradigm powered by a Neural Memory Indexer built upon the DeepSeek-V4 architecture. Rather than passively attending to all historical tokens, LSA proactively predicts future context demands and preserves only the query-critical KV chunks in the GPU memory. Crucially, we instantiate this architecture via a backbone-free decoupled training strategy. By formulating the indexer as a standard dual-encoder architecture, we train it independently using standard retrieval training frameworks without ever loading the massive backbone model into GPU memory. We demonstrate that this "less is more" paradigm significantly maximizes serving efficiency while acting as an effective attention denoiser in tasks that rely on long-term global memory. Across primary long-context evaluation suites (e.g., LongBench-v2, LongMemEval, and RULER), FM-DS-V4 compresses the average physical KV cache footprint down to merely 13.5% of the full-context baseline, while consistently preserving or slightly elevating downstream accuracy (+0.6% absolute margin on average). Crucially, at extreme 500K scales, FlashMemory suppresses the physical KV cache overhead by over 90% without destabilizing the backbone's core reasoning capacities.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09079</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Latent Spatial Memory for Video World Models</title>
|
||
<link>https://arxiv.org/abs/2606.09828</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09828.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weijie Wang, Haoyu Zhao, Yifan Yang, Feng Chen, Zeyu Zhang, Yefei He, Zicheng Duan, Donny Y. Chen, Yuqing Yang, Bohan Zhuang</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> Video world models that maintain 3D spatial consistency across generated frames typically rely on explicit point cloud memory constructed in RGB space. This design is both computationally expensive, requiring repeated rendering and VAE encoding, and inherently lossy, as the round trip through pixel space discards rich features of the learned latent representation. In this paper, we introduce latent spatial memory for video world models, a persistent 3D cache that stores scene information directly in the diffusion latent space, avoiding pixel-space reconstruction. Building on this, we propose Mirage, a latent-space spatial memory framework that constructs the memory by lifting latent tokens into 3D via depth-guided back-projection and queries it by synthesizing novel views through direct latent-space warping. This unified formulation eliminates both the information loss of pixel-space reconstruction and the computational burden of repeated encoding and rendering. Experiments show that latent spatial memory achieves up to 10.57times faster end-to-end video generation and 55times reduction in memory footprint relative to explicit 3D baselines. Leveraging the geometric prior of the diffusion model, Mirage attains state-of-the-art performance on WorldScore and strong reconstruction quality on RealEstate10K.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09828</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces</title>
|
||
<link>https://arxiv.org/abs/2606.09426</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wanli Li, Bowen Zhou, Yunyao Yu, Zhou Xu, Yifan Yang, Dongsheng Li, Caihua Shan</p><p><b>Upvotes:</b> 97</p><p><b>Summary:</b> Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools. Existing benchmarks, however, often evaluate these interfaces as separable capabilities, leaving long-horizon cross-interface orchestration under-tested. Thus, we introduce WeaveBench, a long-horizon hybrid-interface benchmark with 114 tasks across 8 real-world work domains, grounded in real user requests and publicly verifiable artifacts. Each task requires agents to combine GUI observations/actions with CLI/code operations within a single trajectory. We evaluate these tasks on a real Ubuntu desktop inside deployed CLI-agent runtimes, augmented with a minimal desktop-control plugin. We also propose a companion trajectory-aware judge that inspects deliverables, files, screenshots, logs, and action traces, while detecting shortcut behaviors such as fabricated visual evidence or hard-coded metrics. Across frontier model-runtime pairings, the best PassRate reaches only 41.2%, showing the benchmark remains far from saturated. The trajectory-aware judge further reveals that outcome-only grading substantially overestimates agent performance. Overall, WeaveBench exposes a critical gap in CUA evaluation and provides an effective testbed to measure whether agents can orchestrate GUI, CLI, and code operations across long-horizon real-world tasks.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09426</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ABot-Earth 0.5: Generative 3D Earth Model</title>
|
||
<link>https://arxiv.org/abs/2606.09967</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.09967.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Qian, Tianjian Ouyang, Mingchao Sun, Zijian Wang, Jincheng Xiong, Jiarong Han, Yongchang Zhang, Jiawei Zhang, Xu Wang, Yu Liu, Luyang Tang, Fei Yu, Zengye Ge, Mengmeng Du, Yuan Liu, Nianfei Fan, Song Wang, Yingliang Peng, Chunxue Jia, Yang Liu, Shiying Zeng, Haozhe Shi, Junnan Lai, Hongyu Pan, Zheng Wu, Ning Guo, Mu Xu, Hang Zhang</p><p><b>Upvotes:</b> 463</p><p><b>Summary:</b> We present ABot-Earth 0.5, a generative 3D framework designed to synthesize vast, seamless 3D environments from ubiquitous, geospatially referenced satellite imagery. To achieve this, we propose a novel generative model formulated directly with the 3D Gaussian Splatting (3DGS) representation. The model is trained on a diverse corpus of existing real-world urban reconstructions, learning to generate realistic geometry and textures. At inference, it synthesizes novel 3D scenes conditioned solely on satellite imagery at a scalable rate of under 10 minutes per square kilometer, while demonstrating exceptional realism. The framework is designed for accessibility, with integrated hierarchical level-of-detail (LOD) structures that permit real-time, interactive visualization on web-based map engines. This high-fidelity simulation sandbox effectively mitigates the sim-to-real domain gap, enabling critical downstream Embodied AI applications like closed-loop UAV navigation. By providing an ultra-low-cost and high-efficiency solution, ABot-Earth 0.5 significantly lowers the technical and financial barriers to large-scale 3D reconstruction and empowers the future of global digital earth visualization.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.09967</guid>
|
||
<pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders</title>
|
||
<link>https://arxiv.org/abs/2606.10029</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.10029.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikita Koriagin, Georgii Aparin, Nikita Balagansky, Daniil Gavrilov</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Language models increasingly serve as the backbone of text-to-speech (TTS) systems, yet we understand little about the representations they build when text and generated speech tokens share a single residual stream. We train BatchTopK sparse autoencoders on the LM backbone of CosyVoice3 and introduce a modality-aware auto-interp pipeline that labels each feature from where it fires-text-prefix context, 1-second speech clips, or both. The recovered features are interpretable, spanning phonemes, laughter, accent prompts and speaker gender. Steering through the SAE latent space shows these features are causal rather than merely descriptive: targeted interventions raise laughter probability from 0.02 to 0.79, flip perceived speaker gender, and control speech rate while preserving spoken content. SAE features thus serve both as interpretability objects and as control directions for TTS synthesis.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.10029</guid>
|
||
<pubDate>Mon, 08 Jun 2026 18:09:37 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models</title>
|
||
<link>https://arxiv.org/abs/2606.11324</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11324.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifu Yuan, Yaoting Huang, Xianze Yao, Yutong Li, Shuoheng Zhang, Linqi Han, Pengyi Li, Jiangeng Sun, Wenting Jia, Zhao Zhang, Yuhao Liu, Ruihao Liao, Yucheng Hu, Qiyu Wu, Yuxiao Li, Zibin Dong, Fei Ni, Yan Zheng, Shuyang Gu, Yi Ma, Hongyao Tang, Han Hu, Jianye Hao</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We introduce Embodied-R1.5, a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities, spanning embodied cognition, task planning, correction, and pointing, within a single architecture toward general physical intelligence. Leveraging three automated data construction pipelines to significantly expand the data coverage of critical capabilities, we build a large-scale data system of over 15B tokens, and design a multi-task balanced RL recipe to alleviate heterogeneous task conflicts. We further introduce a Planner-Grounder-Corrector (PGC) closed-loop framework that enables a single model to autonomously execute and self-correct over long-horizon tasks. With only 8B parameters, Embodied-R1.5 achieves SOTA on 16 out of 24 embodied VLM benchmarks, surpassing leading models like Gemini-Robotics-ER-1.5 and GPT-5.4. Benefiting from the internalized embodied capabilities, Embodied-R1.5 can be fine-tuned into a VLA with only a small amount of data, outperforming leading VLA models like π_{0.5} across 4 popular manipulation benchmark suites. We further conduct extensive zero-shot real-robot experiments, validating performance in instruction following, affordance grounding, articulated object manipulation, and long-horizon complex tasks, demonstrating strong generalization to the physical world. We open-source model weights, datasets, training code, and EmbodiedEvalKit, an evaluation framework tailored for embodied tasks, to facilitate future research in EFMs.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11324</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It</title>
|
||
<link>https://arxiv.org/abs/2606.11052</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11052.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Zhou, Boyu Zhu, Yi Xu, Zhiwei Li, Yingfa Chen, Huiming Wang, Zhijiang Guo</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-context recall in hybrid linear-attention models. Across architectures including HypeNet and Jet-Nemotron, retrieval performance on Needle-In-A-Haystack (NIAH) deteriorates substantially after CoT-SFT, and the degradation becomes more severe under harder retrieval settings and longer context windows. For example, HypeNet-9B on NIAH-S2@256K decreases from 67.2% to 9.4%. We attribute this to CoT-SFT biasing attention gradients toward short-range patterns, disrupting query-key projections (W_Q, W_K) that are responsible for long-range routing. Motivated by this observation, we propose QK-Restore, a training-free method that restores only W_Q and W_K from the pre-SFT checkpoint while preserving all other post-SFT parameters. We further introduce a Procrustes variant to balance routing preservation and reasoning adaptation. Across architectures, QK-Restore consistently restores long-context capability at zero training cost while preserving reasoning performance; for instance, on HypeNet-5B it improves S3@256K from 65.4% to 76.4% while maintaining strong reasoning performance.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11052</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics</title>
|
||
<link>https://arxiv.org/abs/2606.10479</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.10479.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shunkai Zhang, Haoran Zhang, Yun Luo, Qianjia Cheng, Haodi Lei, Yizhuo Li, Runzhe Zhan, Zhilin Wang, Bangjie Xu, Yucheng Su, Xinmiao Han, Xiaoye Qu, Dongrui Liu, Zhouchen Lin, Yu Qiao, Ning Ding, Yafu Li, Yu Cheng</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Combinatorics is central to Olympiad-level mathematical problem solving, requiring deep discrete reasoning, creative constructions, and rigorous structural insight. Recent evidence suggests that even today's strongest frontier models remain uneven on Olympiad combinatorics, revealing a gap in creative mathematical reasoning. We introduce ComBench, an Olympiad-level combinatorics benchmark for evaluating and diagnosing the combinatorial reasoning capabilities of large language models. ComBench contains 100 human-annotated competition-level problems organized around two complementary settings: analysis-centric problems, which primarily require rigorous mathematical arguments, and construction-centric problems, which require explicit constructions in addition to correctness justifications. The evaluation protocol combines rubric-guided proof grading with deterministic construction verification, exposing cases where proof quality and construction validity diverge. Experiments on frontier open- and closed-source models show that ComBench is far from saturated: the strongest model reaches 65.4% overall Avg. and 75.3% overall Best@4. We further find that Rigorous Proof Reasoning and Constructive Realization are distinct capabilities: Kimi-K2.6 trails GPT-5.5 on analysis-centric proof grading but surpasses it on construction-centric Best@4, while Existence and Construction problems remain consistently hardest across representative frontier models.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.10479</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields</title>
|
||
<link>https://arxiv.org/abs/2606.11042</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11042.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liya Zhu, Jingzhe Ding, Jian Zhang, Jianbo Xue, Shihao Liang, Ge Zhang, Xiang Gao, Qingshui Gu, Mailun Gao, Huimin Che, Yan Zhao, Peiheng Zhou, Haojun Wang, Chaobo Xian, Lili Le, Chi Wu, Yiwei Liu, Shengda Long, Jiale Yang, Fangzhi Xu, Sijin Wu, Haodong Duan, Yi Zhu, Chao He, Zhaojian Li, Minchao Wang, Huan Zhou, Jiani Hou, Chuqian Yu, Weiran Shi, Hongwan Gao, Jiamin Chen, Guanhong Chen, Tingqin Luo, Kaiyuan Zhang, Zhixin Yao, Qing Hua, Yuhao Jiang, Jin Chen, Pu Chen, Zhenyu Hu, Xingyu Li, Zhengxuan Jiang, Meng Cao, Tianfeng Long, Haozhe Wang, Mingzhang Wang, Yichen Zhang, Yiming Dai, Chenchen Zhang, Jiaying Wang, Zhiyong Wu, Shen Yan, Yujia Qin, Wenhao Huang, Zaiyuan Wang, Xiaolong Chang</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. Current GUI benchmarks still predominantly focus on general-purpose software, relatively simple applications, and short-horizon tasks, leaving it largely unknown whether modern agents can follow user instructions to autonomously operate domain-specific professional software and accomplish economically valuable work in an end-to-end manner. To bridge this gap, we introduce Workflow-GYM, a benchmark for long-horizon GUI tasks centered on professional domains and specialized software environments. Through extensive experiments on state-of-the-art models, we find that even the strongest models achieve only slightly above 30% success rates, highlighting that professional long-horizon GUI workflows remain highly challenging for current GUI agents. Further analysis reveals that current agents struggle to maintain long-horizon workflow consistency, frequently exhibiting workflow stage omission, error propagation, objective drift, and insufficient understanding of professional software environments. Our findings provide important insights into the limitations of current agent systems and suggest key directions for the next generation of GUI-agent research.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11042</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization</title>
|
||
<link>https://arxiv.org/abs/2606.10768</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.10768.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xukun Zhu, Hang Yu, Peng Di, Linchao Zhu</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> The success of Large Language Models in mathematical reasoning relies heavily on the generation of diverse and valid solution paths during the rollout phase. However, current rollout techniques face a fundamental trade-off: token-level sampling often yields redundant trajectories that differ only in rephrasing, while embedding-level methods utilizing random noise frequently disrupt semantic consistency. To resolve this, we introduce N-GRPO, a novel exploration strategy integrated into the Group Relative Policy Optimization (GRPO) framework. Rather than relying on token-level sampling or native embedding-level noise, our approach leverages Semantic Neighbor Mixing. This mechanism dynamically constructs input representations by mixing the embeddings of an anchor token and its nearest semantic neighbors, thereby injecting diversity while strictly adhering to the local semantic manifold. Experimental evaluations on the DeepSeek-R1-Distill-Qwen models across different sizes show that N-GRPO not only achieves consistent improvements over strong baselines on math reasoning benchmarks but also exhibits robust generalization capabilities on out-of-distribution tasks.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.10768</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations</title>
|
||
<link>https://arxiv.org/abs/2606.11188</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11188.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junke Wang, Xiao Wang, Jiacheng Pan, Xuefeng Hu, Feng Li, Jingxiang Sun, Chaorui Deng, Zilong Chen, Yunpeng Chen, Kaibin Tian, Matthew Gwilliam, Hao Chen, Danhui Guan, Kun Xu, Weilin Huang, Zuxuan Wu, Haoqi Fan, Yu-Gang Jiang, Zhenheng Yang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> This paper introduces ARM, a discrete representation-based AutoRegressive Model that unifies image understanding, generation, and editing within a next-token prediction framework. ARM is built on three efforts: first, we train a discrete semantic visual tokenizer that maps images into compact token sequences. Our tokenizer is supervised with multiple objectives that jointly promote semantic discriminability, language alignment and faithful reconstruction, thereby supporting diverse tasks in a shared latent space. With this, we train a 7B autoregressive model over large-scale text and image token sequences, seamlessly developing vision-language perception and generation capabilities. Finally, to further improve preference-aligned behavior for text-to-image generation and instruction-guided editing, ARM applies reinforcement learning (RL) to optimize task-level objectives such as visual quality, instruction adherence, and edit consistency. Surprisingly, the results show that RL not only substantially improves performance on the target tasks (e.g., raising WISE overall from 0.50 to 0.56, GEdit-Bench-EN G_O from 5.75 to 6.68), but also induces cross-task synergy between text-to-image generation and editing. Collectively, these findings highlight autoregressive modeling, when paired with strong representations and preference optimization, as a scalable foundation for multimodal intelligence. Code: https://github.com/wdrink/ARM.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11188</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>WorldOlympiad: Can Your World Model Survive a Triathlon?</title>
|
||
<link>https://arxiv.org/abs/2606.11129</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11129.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuke Zhao, Wangbo Zhao, Weijie Wang, Zeyu Zhang, Dakai An, Akide Liu, Yinghao Yu, Jiasheng Tang, Fan Wang, Wei Wang, Bohan Zhuang</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> We introduce WorldOlympiad, a benchmark for diagnosing video-based world models across physical faithfulness, geometric consistency, and interaction fidelity. While existing benchmarks often focus on visual quality, semantic alignment, or short-term temporal coherence, they provide limited insight into whether generated videos obey physical rules, preserve coherent 3D structure, and sustain controllable interactions over long horizons. To address this gap, WorldOlympiad decomposes world-model evaluation into three complementary dimensions. The physical track uses object segmentation and MLLM-as-judge to assess whether generated videos follow interpretable rules in mechanics, thermal phenomena, and material properties. The geometry track reconstructs generated videos with Gaussian splatting and evaluates structural consistency, cross-view coherence, and camera-trajectory alignment. The interaction track assesses whether generated rollouts follow complex action prompts and maintain smooth, coherent transitions across consecutive video chunks. WorldOlympiad further covers three major downstream scenarios, including gaming, robotics, and general real-world videos, capturing diverse challenges from interactive control and embodied manipulation to open-domain motion and camera dynamics. Together, these tracks and scenarios form a scalable and interpretable evaluation suite that exposes failure modes beyond generic video quality. Experiments on state-of-the-art models reveal substantial gaps in physical reasoning, 3D consistency, and long-horizon interaction, underscoring the need for more structured evaluation protocols for generative world models.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11129</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch</title>
|
||
<link>https://arxiv.org/abs/2606.10728</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.10728.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiale Zhao, Guoxin Chen, Fanzhe Meng, Wayne Xin Zhao, Ruihua Song, Ji-Rong Wen, Kai Jia</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> As the capabilities of LLM-based code agents continue to advance, their expected role is expanding beyond localized bug fixing in existing codebases toward architecting and implementing complete software repositories from high-level specifications. However, training agents for such long-horizon software engineering tasks remains difficult due to the scarcity of large-scale, verifiable whole-repository generation data. In this paper, we introduce DeNovoSWE, a large-scale dataset for whole-repository generation. DeNovoSWE comprises 4,818 high-quality instances, where each instance requires generating a complete repository from documentation. Our dataset is automatically constructed through a carefully designed sandboxed agentic workflow, enabling scalable curation without human annotation. DeNovoSWE is constructed with "divide and conquer" and critic-repair philosophy. To balance data quality and diversity, we further introduce a difficulty-aware trajectory filtering strategy. Fine-tuning Qwen3-30B-A3B on DeNovoSWE substantially improves long-horizon SWE performance, raising its score on the challenging BeyondSWE-Doc2Repo benchmark from 5.8% to 47.2%.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.10728</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models</title>
|
||
<link>https://arxiv.org/abs/2606.11025</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11025.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Ping, Xiangxin Zhou, Penghui Qi, Minnan Luo, Liefeng Bo, Tianyu Pang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Recent work has demonstrated that online reinforcement learning (RL) can substantially improve the quality and alignment of flow matching models for image and video generation. Methods such as Flow-GRPO and CPS cast the denoising process as a Markov Decision Process and apply PPO-style ratio clipping to enforce a trust region. However, we argue that ratio clipping is structurally ill-suited for flow models: the probability ratio between new and old policies is a noisy, single-sample estimate of the true policy divergence, leading to over-constraining in some regions of the trajectory and under-constraining in others. We propose Flow-DPPO (Flow Divergence Proximal Policy Optimization), which replaces ratio clipping with a divergence proximal constraint. A key observation is that the per-step policy in flow models is Gaussian, enabling exact and cheap computation of the KL divergence between old and new policies. Flow-DPPO employs an asymmetric divergence mask that blocks gradient updates only when they simultaneously move away from the trusted region and violate the divergence threshold. Experiments show that Flow-DPPO achieves higher rewards with better KL-proximal efficiency, alleviates catastrophic forgetting, promotes balanced multi-objective optimization, and enables stable multi-epoch training where ratio clipping degrades. Code and models are available at https://github.com/Tencent-Hunyuan/UniRL/tree/main/FlowDPPO.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11025</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning</title>
|
||
<link>https://arxiv.org/abs/2606.10804</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.10804.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenhao Yan, Fengjia Guo, Zhuoyi Yang, Jie Tang</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Controlled character animation requires transferring motion from a driving sequence to a reference character. Prior works heavily rely on intermediate representations, including pose skeletons to represent motion or masked background to represent environment, which inevitably leads to information loss. To address this, we present SCAIL-2, an framework that bypasses those intermediates and achieves end-to-end character animation. By directly concatenating driving videos to the sequence, the model can obtain all the required visual information from the input video. To address lack of end-to-end data, we unify sub-tasks of character animation with decoupled conditions and then curate a pipeline to synthesize MotionPair-60K, an end-to-end motion transfer dataset containing heterogeneous tasks of character animation. To archive the unification, we utilize in-context mask conditioning and mode-specific RoPE as soft guidance beyond textual instructions and raw visual information. To address synthetic discrepancy in detailed regions, we propose Bias-Aware DPO to construct preference items to mitigate the errors. Extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches in various character animation tasks. A large subset of synthetic data as well as model weights will be released at our project page: https://teal024.github.io/SCAIL-2/.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.10804</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Kwai Keye-VL-2.0 Technical Report</title>
|
||
<link>https://arxiv.org/abs/2606.10651</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.10651.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kwai Keye Team, Bin Wen, Changyi Liu, Chengru Song, Chongling Rao, Guowang Zhang, Han Li, Haonan Fan, Hengrui Ju, Jiankang Chen, Jiapeng Chen, Jiawei Yuan, Kaixuan Yang, Kaiyu Jiang, Kun Gai, Lingzhi Zhou, Na Nie, Sen Na, Tianke Zhang, Tingting Gao, Xuanyu Zheng, Yulong Chen, Fan Yang, Haixuan Gao, Lele Yang, Mingqiao Liu, Muxi Diao, Qi Zhang, Qile Su, Wei Chen, Wentao Hong, Xingyu Lu, Yancheng Long, Yankai Yang, Yingxin Li, Yiyang Fan, Yu Xia, Yuzhe Chen, Ziliang Lai, Chuan Yi, Haonan Jia, Tianming Liang, Weixin Xu, Xiaoxiao Ma, Yang Tian, Yufei Han, Feng Han, Hang Li, Jing Wang, Jinghui Jia, Junmin Chen, Junyu Shi, Ruilin Zhang</p><p><b>Upvotes:</b> 183</p><p><b>Summary:</b> We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To address the challenges of ultra-long contexts, information redundancy, and prohibitive computational costs inherent in hour-level videos, Keye-VL-2.0 is the first to adapt DeepSeek Sparse Attention (DSA) to GQA-based multimodal architectures, enabling lossless 256K context processing while capturing critical frames and long-range temporal dependencies. This architecture is underpinned by a highly optimized training and inference infrastructure, including scalable video I/O, heterogeneous ViT-LM parallelism, and custom DSA kernels that significantly maximize throughput and minimize computational overhead. Furthermore, to overcome the algorithmic dilemma of catastrophic forgetting during multi-task alignment, we introduce Cross-Modal Multi-Teacher On-Policy Distillation (MOPD) paired with Context-RL and Video-RL. By distilling dense token-level teacher feedback from on-policy rollouts back into the MoE backbone, which activates only 3B parameters, Keye-VL-2.0 natively empowers advanced agent collaboration across Code, Tool, and Search scenarios with multimodal self-correction. Extensive evaluations across video understanding, temporal grounding, reasoning, STEM, and agent benchmarks demonstrate that Keye-VL-2.0-30B-A3B achieves state-of-the-art performance among models of similar scale, particularly excelling in fine-grained temporal localization on TimeLens and long-video comprehension on Video-MME-v2 and LongVideoBench. We release our model checkpoints to accelerate community progress toward scalable and robust multimodal agentic applications.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.10651</guid>
|
||
<pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA</title>
|
||
<link>https://arxiv.org/abs/2606.10572</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.10572.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhi Zheng, Ziqiao Meng, Hao Luan, Wei Liu, Wee Sun Lee</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal evidence. However, existing memory paradigms represent each memory item in raw text and image forms, so retrieval-based systems must pass the retrieved text or images to the generation LLMs/VLMs, resulting in high token consumption and storage pressure, making it unaffordable for resource-constrained applications. We propose Latent Memory, a latent-space memory paradigm that replaces each raw text or image evidence item with a single high-dimensional latent token produced by a small compressor LLM/VLM. Rather than retrieving raw evidence for generation, Latent Memory operates in a unified latent representation space: the query is embedded into this space to retrieve relevant latent tokens, and the retrieved latent tokens are directly prompted to a pretrained LLM or VLM for answer generation. To make each latent token simultaneously informative for reconstruction, retrieval, and generation, we train the compressor with reconstruction, contrastive, and distillation objectives in a unified end-to-end manner. Latent Memory is evaluated on seven text-only QA benchmarks (e.g., HotpotQA) and multimodal QA benchmarks, where it achieves competitive QA performance compared to advanced RAG baselines while consuming 3x to 10x fewer generator tokens. It can also deliver the strongest image-grounded QA performance on WebQA. Code is available at https://github.com/zz1358m/Latent-Memory-Master.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.10572</guid>
|
||
<pubDate>Tue, 09 Jun 2026 08:36:08 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution</title>
|
||
<link>https://arxiv.org/abs/2606.10917</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.10917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xucong Wang, Ziyu Ma, Shidong Yang, Tongwen Huang, Pengkun Wang, Yong Wang, Xiangxiang Chu</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interaction feedback and static training environments, which hinder broader generalization. To address these limitations, this paper introduces Role-Agent, black{a framework} that harnesses a single LLM to function concurrently as both the agent and the environment, enabling a bootstrapped co-evolution. Role-Agent comprises two synergistic components: World-In-Agent (WIA) and Agent-In-World (AIW). In WIA, the LLM acts as the agent and predicts future states after each action; the alignment between predicted and actual states is then used as a process reward, encouraging environment-aware reasoning. In AIW, the LLM analyzes failure modes from failed trajectories and retrieves tasks with similar failure patterns, thereby reshaping the training data distribution for targeted practice. Experiments on multiple benchmarks show that Role-Agent consistently improves performance, yielding an average gain of over 4\% over strong baselines.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.10917</guid>
|
||
<pubDate>Tue, 09 Jun 2026 14:28:07 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning</title>
|
||
<link>https://arxiv.org/abs/2606.11119</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11119.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Heming Zou, Qi Wang, Yun Qu, Yuhang Jiang, Lizhou Cai, Yixiu Mao, Ru Peng, Xin Xu, Weijie Liu, Kai Yang, Saiyong Yang, Xiangyang Ji</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. However, rollout-intensive policy optimization is often limited by insufficient reward contrast, arising when overly simple or complex prompts generate low-variance feedback and when outcome-only rewards assign the same terminal assessment to every decision in a multi-turn rollout. Past efforts have focused on allocating available rollout resources to promising prompts, yet they only leverage sample informativeness at the prompt level and neglect variation in prefix-level informativeness across turns within the same rollout. This work targets multi-turn agentic RL by modeling each ReAct-style thought-action-observation turn as a semantically distinct node, allowing budget allocation to extend from prompt roots to turn-level prefixes with further continuations, which naturally forms tree-structured rollouts. We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework that enhances reward contrast within a fixed sampling budget. Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards. A shared generalizable predictor estimates conditional success probability at these anchors from prefix histories to guide this allocation. The resulting adaptive tree structure enriches outcome-only feedback and amplifies the policy-update signal. Empirically, TRACE achieves competitive performance and efficiency gains on typical agentic benchmarks, e.g., improving Qwen3-14B Multi-Hop QA average accuracy by 2.8 points over competitive baselines at equal sampling cost.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11119</guid>
|
||
<pubDate>Tue, 09 Jun 2026 17:16:03 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization</title>
|
||
<link>https://arxiv.org/abs/2606.11180</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11180.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Paul Hyunbin Cho, Jinhyuk Jang, SeokYoung Lee, Joungbin Lee, Siyoon Jin, Heeseong Shin, Jung Yi, Yunjin Park, Chulmin Park, Seungryong Kim</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Diffusion-based lip synchronization models achieve strong visual quality and audio-visual alignment, but full-sequence bidirectional attention and many denoising steps make them impractical for real-time inference. We present Lip Forcing, to our knowledge the first autoregressive diffusion method for video-to-video (V2V) lip synchronization, which distills a 14B audio-conditioned bidirectional video diffusion teacher into causal students. At inference, the students generate each chunk in only two denoising steps without inference-time CFG, enabling real-time lip synchronization. A lip-sync-specific teacher-trajectory analysis reveals a CFG fidelity-sync tradeoff: no-CFG predictions favor reference fidelity, whereas CFG-guided predictions favor synchronization within a mid-trajectory band. Lip Forcing translates this finding into three analysis-derived components: Sync-Window DMD, a two-step inference schedule, and a SyncNet-based reward. We validate Lip Forcing at two student scales, both distilled from the 14B teacher. The 1.3B student crosses into real-time streaming at 31 FPS, 17.6times faster than its same-scale bidirectional model. The 14B student, the largest diffusion model reported for V2V lip synchronization, runs 39.8times faster than its teacher at comparable reference fidelity. Time-to-first-frame is sub-millisecond at both scales, far below every diffusion baseline.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11180</guid>
|
||
<pubDate>Tue, 09 Jun 2026 17:56:36 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents</title>
|
||
<link>https://arxiv.org/abs/2606.11182</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11182.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weixian Xu, Shilong Liu, Mengdi Wang</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> In this paper, we propose EEVEE, the first multi-dataset test-time prompt learning framework for LLM agents, enabling test-time prompt learning under real-world task streams. Existing methods are largely designed for single-dataset settings, while real-world applications require models to handle heterogeneous input streams drawn from multiple datasets, domains, and task distributions, limiting their practical applicability. To mitigate cross-dataset interference, EEVEE introduces a router that partitions incoming inputs into task clusters and assigns them to suitable prompt configurations. This design is optimized via a router-prompt co-evolution strategy, which employs interleaved router and prompt learning phases to address their mutual dependency. Experiments across multiple datasets demonstrate that the framework improves robustness under heterogeneous data streams while maintaining single-benchmark learning capability and efficiency. Specifically, EEVEE improves average multi-benchmark scores by 10.38 and 24.32 points over Qwen3-4B-Instruct and DeepSeek-V3.2, surpassing SOTA methods GEPA and ACE by up to 37.2% and 48.2%.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11182</guid>
|
||
<pubDate>Tue, 09 Jun 2026 17:57:16 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>World Model Self-Distillation: Training World Models to Solve General Tasks</title>
|
||
<link>https://arxiv.org/abs/2606.12072</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12072.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sebastian Stapf, Pablo Acuaviva Huertos, Aram Davtyan, Paolo Favaro</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Pretrained video generators are promising visual world models that exhibit emergent task-solving abilities; however, their reliance on detailed textual descriptions limits their direct use for planning and decision-making. Existing approaches either outsource this reasoning to language or vision-language models, or rely on supervised fine-tuning with paired task-execution videos, which are costly to collect and difficult to scale. We propose a scalable framework that elicits task-solving ability in such models by combining self-distillation with reinforcement learning. Given an unlabeled scene image, a vision-language model generates a candidate task and a detailed step-by-step solution. The solution conditions a pretrained video diffusion model, the Demonstrator; we distill its behavior into an Executor conditioned only on the image and a short task prompt. This transfers execution knowledge from caption-guided generation to instruction-conditioned task solving without curated task-video supervision. We further improve the Executor with reinforcement learning from VLM feedback, exploiting the asymmetry between judging whether a sampled video satisfies a task and generating the solution. Experiments on our proposed WorldTasks-Benchmark and the DreamGen robotics benchmark show that the Executor surpasses the Demonstrator under our VLM-based evaluation protocol and transfers competitively to robotic tasks.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12072</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ICA Lens: Interpreting Language Models Without Training Another Dictionary</title>
|
||
<link>https://arxiv.org/abs/2606.11722</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11722.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sida Liu, Feijiang Han</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior. Sparse autoencoders (SAEs) have become the standard tool for this purpose, but using them as the default first lens often requires training, storing, and evaluating large overcomplete dictionaries. This bottleneck limits rapid exploration and raises a fundamental question: how much interpretable structure is already visible from activation geometry before training another neural dictionary? Our intuition is simple: many interpretable directions are selective on tokens, and these directions should look less Gaussian than random directions. We therefore revisit independent component analysis (ICA), a classical method for finding non-Gaussian directions, as a compact lens for language-model interpretability. We find that ICA has been underestimated for LLM interpretability, because prior uses often relied on off-the-shelf ICA implementations that are brittle on LLM activations and lacked systematic tools for inspecting and evaluating the recovered directions. To bridge these gaps, we introduce ICALens, the first practical workflow for stable, efficient, and auditable ICA analysis of LLM representations. It combines an optimized GPU-parallel FastICA pipeline with LLM-specific stability recipes and better fitting diagnostics, enabling efficient and reliable layer-wise analysis. Across GPT-2 Small, Gemma 2 2B, and Qwen 3.5 2B Base, ICALens efficiently recovers compact, human-interpretable directions without per-layer gradient-based dictionary training. On SAEBench, ICA is competitive with public SAEs in sparse probing and outperforms them in targeted probe perturbation under small-to-medium budgets. These results suggest that ICA should not be viewed as a weak baseline, but as an efficient and complementary first lens for exploring language-model representations.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11722</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code</title>
|
||
<link>https://arxiv.org/abs/2606.11817</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11817.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yitong Zhang, Shiteng Lu, Jia Li</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding (GCD) has been widely adopted to improve the reliability of LLM-generated code by enforcing syntactic validity. In this paper, we reveal a counterintuitive risk: this reliability-oriented technique can itself become an attack surface. We uncover a new jailbreak attack, termed CodeSpear, that exploits GCD to induce LLMs into generating malicious code. Our experiments show that simply applying a benign code grammar constraint can effectively jailbreak LLMs. To address this vulnerability, we propose CodeShield, a safety alignment approach that robustly preserves safe behavior even under attacker-controlled grammar constraints. CodeShield aligns the model in the code modality by teaching it to generate honeypot code under GCD. Such code is semantically harmless, so it does not implement the malicious request, and structurally diverse, so it is difficult to suppress through grammar tightening. At the same time, CodeShield still preserves natural-language refusals when natural language is available. Experiments on 10 popular LLMs across 4 benchmarks show that CodeSpear outperforms representative jailbreak baselines and increases the attack success rate by more than 30 percentage points on average. CodeShield also restores safety under CodeSpear while preserving benign utility. Our findings reveal a fundamental risk of GCD and call for greater attention to its potential security implications.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11817</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models</title>
|
||
<link>https://arxiv.org/abs/2606.12412</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12412.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng-Yu Yang, Shao-Yuan Lo, Yu-Lun Liu</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computation and KV-cache memory. Existing visual-token reduction methods largely follow a rank-and-remove paradigm: they score visual tokens, keep a compact subset, and permanently discard the rest. We show that this irreversible action is fragile because visual-token importance changes across decoder depth; tokens ranked low at one stage may become relevant in later layers, especially for grounding-sensitive queries. We propose Reroute, a training-free plug-in that replaces removal with recoverable routing. At each routing stage, selected vision tokens pass through decoder blocks, while deferred tokens bypass the stage and re-enter the candidate pool at the next routing decision. Reroute reuses existing attention-score ranking rules and stage-wise schedules, preserving the theoretical TFLOPs and KV-cache budget class of the pruning method it augments. Across FastV, PDrop, and Nüwa variants on LLaVA-1.5 and Qwen backbones, reroute improves grounding under aggressive token reduction while maintaining general VQA performance. These results suggest that VLM token reduction should not be viewed only as irreversible pruning, but also as recoverable routing. The code can be found here: https://github.com/elmma/mllm-reroute/</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12412</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling</title>
|
||
<link>https://arxiv.org/abs/2606.12370</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12370.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yucheng Li, Huiqiang Jiang, Yang Xu, Jianxin Yang, Yi Zhang, Yizhong Cao, Yuhao Shen, Fan Zhou, Rui Men, Jianwei Zhang, An Yang, Bowen Yu, Bo Zheng, Fei Huang, Junyang Lin, Dayiheng Liu, Jingren Zhou</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-Token Prediction (MTP) offers a natural solution to accelerate rollouts through speculative decoding, many studies have observed that MTP acceptance rates degrade significantly during RL training, leading to limited speedup performance. To address this bottleneck, we present Bebop, a systematic study of MTP in LLM post-training, and offer practical recipes to integrate MTP into large-scale RL pipelines. First, we reveal that the MTP acceptance rate is fundamentally bounded by the fluctuation of model entropy, which demonstrates a clear negative linear relationship with the rise of entropy in the RL stage. Second, we show that probabilistic rejection sampling largely alleviates the disturbance introduced by entropy in RL compared to greedy draft sampling. We further identify that the conventional MTP training objectives (cross-entropy or KL) are suboptimal in such settings, and therefore we propose a novel end-to-end TV loss that directly optimizes multi-step rejection sampling acceptance rate, yielding ~10% acceptance rate improvements, achieving up to 95% acceptance rates and up to 25% extra inference throughput gains across mathematical reasoning, code generation, and agentic tasks. Third, we test various online MTP training strategies during RL and show that pre-RL MTP training with e2e TV loss and rejection sampling achieves a consistent acceptance rate and speedup throughout the entire RL, eliminating the need for costly online MTP updating. We provide extensive experiments and analysis that validate our findings. Experimental results show our method achieves up to 1.8x end-to-end acceleration in async RL training of Qwen3.5, Qwen3.6, and Qwen3.7 models.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12370</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning</title>
|
||
<link>https://arxiv.org/abs/2606.12195</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12195.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziang Yan, Sheng Xia, Jiashuo Yu, Yue Wu, Tianxiang Jiang, Songze Li, Kanghui Tian, Yicheng Xu, Yinan He, Kai Chen, Limin Wang, Yu Qiao, Yi Wang</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Recent progress in foundation models has shifted toward agentic behavior involving multi-step reasoning and tool use. However, open-source efforts largely focus on text-dominant settings, leaving long-horizon multimodal tasks underexplored. This gap is evident in video tasks requiring sustained temporal understanding and iterative interaction. We present InternVideo3, a framework enhancing these capabilities via Multimodal Contextual Reasoning (MCR). MCR treats understanding as a closed-loop process over a shared, evolving context containing observations, instructions, reasoning, tool actions, and memory. This frames long-video understanding as evidence accumulation and verification. To ensure efficiency, we introduce Multimodal Multi-head Latent Attention (M^2LA), a token-preserving reparameterization compressing KV-cache states while retaining the full token stream. Our staged training includes continued pretraining, short-to-long supervised fine-tuning, rule-based reinforcement learning, and on-policy distillation. Experiments show InternVideo3 achieves strong performance on benchmarks like Video-MME, MLVU, and EgoSchema. We further instantiate the model as a video agent with retrieval tools, demonstrating robust evidence-grounded behavior. Our results suggest that efficient context handling and closed-loop reasoning are vital for adapting open multimodal models toward long-horizon visually grounded agency.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12195</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>World Pilot: Steering Vision-Language-Action Models with World-Action Priors</title>
|
||
<link>https://arxiv.org/abs/2606.12403</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12403.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zefu Lin, Rongxu Cui, Junjia Xu, Xiaojuan Jin, Wenling Li, Lue Fan, Zhaoxiang Zhang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Vision-Language-Action (VLA) models inherit semantic grounding from large-scale pretraining and perform competently across in-distribution manipulation tasks. This grounding, however, is built on static image-text pairs, whereas manipulation is a continuous, contact-rich process whose dynamics this pretraining cannot capture. We present World Pilot, a VLA framework that augments the policy with priors from a World-Action Model (WAM), routed into the decision chain through two complementary pathways. Latent Steering conditions the perception layer on a scene-evolution latent, and Action Steering supplies an anticipated trajectory as a motion prior to the action generator. Together the two priors equip the VLA with an anticipated view of the scene and a trajectory-level motion hint alongside its semantic conditioning, and the scene-evolution prior remains effective even when supplied by a video-pretrained world model that has not been action-post-trained. World Pilot attains a state-of-the-art Total success rate of 84.7% on the LIBERO-Plus zero-shot OOD benchmark and the highest success rate on every real-robot setting across four manipulation tasks, with the largest margins under shifts in viewpoint, geometry, deformable state, and pose. Project Website: https://world-pilot.github.io/</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12403</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning</title>
|
||
<link>https://arxiv.org/abs/2606.11683</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11683.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chaofan Ma, Zhenjie Mao, Yuhuan Yang, Fanqin Zeng, Yue Shi, Yingjie Zhou, Xiaofeng Cao, Jiangchao Yao</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory. Existing methods rely on single-turn inference, forcing models to resolve geometric ambiguity through semantic priors rather than verifiable evidence. We argue that spatial reasoning should be revisitable: conclusions formed under limited evidence should remain open to revision when complementary viewpoints become available. Building on this insight, we propose Reason, then Re-reason (ReRe), a training-free, inference-time framework with two phases: in the Reason Phase, an MLLM forms a spatial hypothesis from the original video; in the Re-reason Phase, it verifies or revises the hypothesis by observing a synthesized novel-view video. To enable effective cross-view revisiting, we design a Geometry-to-Video pipeline that renders strategically complementary novel views from predicted 3D geometry. These views feature an elevated, oblique perspective with scene-spanning coverage, while preserving the MLLM's native video interface without architectural modifications. Extensive evaluations on VSI-Bench and STI-Bench demonstrate that ReRe substantially boosts open-source MLLMs to rival proprietary state-of-the-art performance. Project page: https://zhenjiemao.github.io/ReRe/</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11683</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion</title>
|
||
<link>https://arxiv.org/abs/2606.12303</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12303.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Xian, Yunqiu Xu, Yang He, Yi Yang</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Multimodal image fusion aims to integrate complementary information from different modalities into a fused image that preserves rich local details while maintaining globally consistent appearance. Existing approaches build shared representations on 2D feature grids, which excel at modeling local structures but offer limited leverage over image-level global appearance factors. To balance these objectives, we introduce a compact 1D token interface based on a frozen pretrained image tokenizer for modeling non-local appearance/base factors. Rather than using the tokenizer as a reconstruction backbone, our design uses the 1D token space as a global carrier while retaining the 2D spatial pathway for local structure restoration. Specifically, we introduce Selective Token Editing (STE), which sparsely updates/replaces a small set of critical tokens, providing a lightweight mechanism to steer global appearance coherence while keeping the fusion backbone unchanged and avoiding extra losses. Experiments on four commonly used benchmarks show that our method achieves the best overall performance, with consistent, multi-metric improvements in both global coherence and local fidelity. Project page: https://zju-xyc.github.io/1D-Fusion-Project-Page/</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12303</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>VIA-SD: Verification via Intra-Model Routing for Speculative Decoding</title>
|
||
<link>https://arxiv.org/abs/2606.12243</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12243.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Xian, Yang He, Yunqiu Xu, Yi Yang</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel. Existing draft-verify methods use binary decisions: accept or fully recompute. Yet we find that many rejected tokens can be verified correctly by a slim submodel derived from the full verifier via intra-model routing, instead of the full verifier. This motivates our slim-verifier to handle tokens requiring moderate verification resources, reducing expensive large-model calls. We propose Verification via Intra-Model Routing for Speculative Decoding (VIA-SD), a multi-tier framework using a routed slim-verifier. Draft tokens are processed hierarchically: direct acceptance for high-confidence cases, slim-verifier regeneration for medium-confidence cases, and full-model verification for uncertain cases. Across four representative tasks and multiple model families, VIA-SD reduces rejection rates by 0.10-0.22 and delivers 10-20% speedups over strong SD baselines, while achieving 2.5-3x acceleration over non-drafting decoding. Moreover, VIA-SD is compatible with existing SD frameworks without modifying their training procedures. Our results suggest multi-tier SD as a general paradigm for scalable and efficient LLM inference. Project page: https://zju-xyc.github.io/VIA-SD-Project-Page/</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12243</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application</title>
|
||
<link>https://arxiv.org/abs/2606.12191</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12191.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiachun Li, Zhuoran Jin, Tianyi Men, Yupu Hao, Kejian Zhu, Lingshuai Wang, Dongqi Huang, Longxiang Wang, Shengjia Hua, Lu Wang, Jinshan Gao, Hongbang Yuan, Ruilin Xu, Kang Liu, Jun Zhao</p><p><b>Upvotes:</b> 60</p><p><b>Summary:</b> Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, existing work lacks a systematic categorization and deep analysis. This paper systematically studies current researches on agentic environments from the perspective of the environment engineering lifecycle, covering their modeling, synthesis, evaluation and application. Specifically, the paper first introduces representative environments from the perspectives of eight attributes and eight domains, providing detailed analyses of their development paths and highlighting their core capabilities. Second, for automated environment synthesis, two paradigms are introduced, such as symbolic synthesis and neural synthesis. This paper also shows different environment evaluation methods in each paradigm. Thirdly, the corresponding environment applications from the perspective of agent-environment co-evolution are discussed. In specific, the paper characterizes the primary pathways for agent evolution in dynamic environments from four complementary perspectives: memory-centric experience evolution, orchestration-centric workflow evolution, trajectory-centric offline evolution, and exploration-centric online evolution. And three paradigms of environment evolution are identified, namely neural-driven, difficulty-driven, and scaling-driven approaches. At last, several promising future directions are discussed, including Environment-as-a-Service, Multi-agent Environments, and Neural-Symbolic Environments.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12191</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks</title>
|
||
<link>https://arxiv.org/abs/2606.12344</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12344.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengyu Zheng, Kai Han, Boxun Li, Haiyang Xu, Yuchuan Tian, Wei He, Hang Zhou, Jianyuan Guo, Hailin Hu, Lin Ma, Chao Xu, Guohao Dai, Lixue Xia, Yunchao Wei, Yunhe Wang, Yu Wang</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring. We introduce Claw-SWE-Bench, a multilingual SWE-bench-style benchmark and adapter protocol that makes heterogeneous agent harnesses, or claws, comparable under fair settings including a fixed prompt, runtime budget, workspace contract, patch extraction procedure, and evaluator. The full benchmark contains 350 GitHub issue-resolution instances across 8 languages and 43 repositories, drawn from SWE-bench-Multilingual and SWE-bench-Verified-Mini after future-commit cleanup. We also release Claw-SWE-Bench Lite for faster validation, which is an 80-instance subset selected by a cost-aware, rank-aware procedure over 17 calibration columns. On the full benchmark, OpenClaw with a minimal direct-diff adapter scores only 19.1% Pass@1, whereas the full adapter reaches 73.4% with the same GLM 5.1 backbone, showing that adapter design is essential for enabling OpenClaw-style harnesses to perform coding tasks effectively. Across an OpenClaw times nine-model sweep and a five-claw times two-model sweep, model choice changes Pass@1 by 29.4 pp and harness choice by 27.4 pp under fixed models; systems with similar accuracy can differ substantially in total API cost. Claw-SWE-Bench therefore treats harness and cost accounting as first-class axes of SWE-style coding-agent evaluation, providing both a full benchmark and a low-cost reference set for reproducible comparison. The data is available at https://github.com/opensquilla/claw-swe-bench and https://huggingface.co/datasets/TokenRhythm/Claw-SWE-Bench.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12344</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents</title>
|
||
<link>https://arxiv.org/abs/2606.12087</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12087.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jia Deng, Yimeng Chen, Xiaoqing Xiang, Ziyang Zeng, Shuo Tang, Wayne Xin Zhao, Feng Chang, Chuan Hao, Yuan Wei, Ran Tao, Bryan Dai, Ji-Rong Wen</p><p><b>Upvotes:</b> 71</p><p><b>Summary:</b> Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. Existing synthesis methods often increase apparent difficulty by enriching graph structures, but structural complexity alone does not guarantee realized search difficulty: the intended search process can collapse through a cheaper identifying route. We formalize this gap with a shortcut-aware difficulty framework and identify four actionable shortcut risks: evidence co-coverage, single-clue selectivity, exposed constants, and prior-knowledge binding. To diagnose their realized effects, we use trajectory signatures including solving cost, answer hit time, and prior-shortcut rate. Guided by this framework, we introduce FORT, a Framework of Shortcut-Resistant Training-Data Synthesis. FORT constructs shortcut-resistant training data by controlling shortcut risks across entity selection, evidence graph construction, question formulation, and adversarial refinement. Experiments show that FORT induces longer pre-answer search and fewer shortcut patterns than existing open-source deep search datasets. Using the resulting trajectories, we train FORT-Searcher with supervised fine-tuning (SFT) only, and it achieves the best overall performance among comparable-size open-source search agents on challenging deep search benchmarks. Relevant resources will be made available at https://github.com/RUCAIBox/FORT-Searcher.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12087</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Redesign Mixture-of-Experts Routers with Manifold Power Iteration</title>
|
||
<link>https://arxiv.org/abs/2606.12397</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12397.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songhao Wu, Ang Lv, Ruobing Xie, Yankai Lin</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Router is the cornerstone component to the Mixture-of-Experts models. Serving as expert proxies, the rows of the router matrix compute their similarity to the MoE inputs to determine which subset of experts is activated. Ideally, each router row is designed to encode the expert matrix into this representative vector, such that its dot-product with token can better reflect token-expert affinity. However, there exists no design principles to enforce this condensation. In this paper, we propose to align each router row with the principal singular direction of the associated expert, as this direction provides the most expressive mathematical description of a matrix. Based on this principle, we propose a router redesign with Manifold Power Iteration (MPI). Specifically, it introduces a "Power-then-Retract" paradigm, where a power iteration step is performed on the router weights, followed by a retraction to impose a norm constraint to ensure both efficiency and stability. Theoretically, we show that MPI drives router rows to converge toward the principal singular directions of associated experts. Empirically, we pretrain MoE model across scales from 1B to 11B parameters to confirm that this alignment facilitates more effective MoE models.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12397</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Toward Generalist Autonomous Research via Hypothesis-Tree Refinement</title>
|
||
<link>https://arxiv.org/abs/2606.11926</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.11926.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiajie Jin, Yuyang Hu, Kai Qiu, Qi Dai, Chong Luo, Guanting Dong, Xiaoxi Li, Tong Zhao, Xiaolong Ma, Gongrui Zhang, Zhirong Wu, Bei Liu, Zhengyuan Yang, Linjie Li, Lijuan Wang, Hongjin Qian, Yutao Zhu, Zhicheng Dou</p><p><b>Upvotes:</b> 109</p><p><b>Summary:</b> Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the resulting lessons into later attempts. We study how an AI agent can run this loop autonomously over long horizons. We introduce Arbor, a general framework for autonomous research that combines a long-lived coordinator, short-lived executors, and Hypothesis Tree Refinement (HTR), a persistent tree that links hypotheses, artifacts, evidence, and distilled insights across time. The coordinator manages global research strategy over the tree, while executors implement and test individual hypotheses in isolated worktrees. As results return, Arbor updates the tree, propagates reusable lessons, refines the search frontier, and admits verified improvements. This design turns autonomous research from a sequence of local attempts into a cumulative process in which strategy, execution, and evidence are carried across time. We evaluate Arbor under Autonomous Optimization (AO), an operational setting where an agent improves an initial research artifact through iterative experimentation without step-level human supervision. Across six real research tasks in model training, harness engineering, and data synthesis, Arbor achieves the best held-out result on all six tasks, attaining more than 2.5x the average relative held-out gain of Codex and Claude Code under the same task interface and resource budget. On MLE-Bench Lite, Arbor reaches 86.36% Any Medal with GPT-5.5, the strongest result in our comparison.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.11926</guid>
|
||
<pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>On Subquadratic Architectures: From Applications to Principles</title>
|
||
<link>https://arxiv.org/abs/2606.12364</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12364.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anamaria-Roberta Hartl, Levente Zólyomi, David Stap, Pieter-Jan Hoedt, Niklas Schmidinger, Lukas Hauzenberger, Sebastian Böck, Günter Klambauer, Sepp Hochreiter</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Transformers dominate modern sequence modeling, but their quadratic attention incurs substantial computational cost. Subquadratic architectures offer a scalable alternative. However, it remains unclear which designs yield the most effective sequence models. We compare three leading approaches: xLSTM, Mamba-2, and Gated DeltaNet. We evaluate these models on tasks with complex dependencies: (1) code-model pre-training, (2) distillation of code models from large language models, and (3) pre-training of time-series foundation models. Across these settings, xLSTM delivers the strongest overall performance. To explain xLSTM's advantage, we present a unified formulation and analyze the underlying architectural mechanisms, focusing on state tracking and memory dynamics. Our results show that xLSTM enables more flexible and stable memory correction via its gating scheme. We corroborate these findings on controlled synthetic length-generalization tasks. Overall, our findings indicate that xLSTM's gains on complex tasks stem from robust state tracking and accumulation.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12364</guid>
|
||
<pubDate>Wed, 10 Jun 2026 17:33:55 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness</title>
|
||
<link>https://arxiv.org/abs/2606.12882</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.12882.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoxuan Wang, Haixin Wang, Alexander Taylor, Jason Cong, Yizhou Sun, Wei Wang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Large language models are increasingly deployed as agents for long-horizon tasks, yet their performance is shaped not only by model capability and environment design, but also by the harness that mediates agent--environment interaction. Existing harnesses are largely manually engineered, making them difficult to scale as trajectories grow longer and interactions become more complex. In this work, we ask whether harness can be generated by a learnable plug-in module that can be trained in an end-to-end fashion. We introduce HarnessBridge, a lightweight learnable harness controller that parameterizes the agent--environment interface as a bidirectional projection. HarnessBridge learns two bidirectional projections: observation projection, which distills raw trajectories into compact, decision-relevant states, and action projection, which converts proposed actions into executable transitions or trajectory-grounded rejections. We train HarnessBridge on a harness supervision dataset via unified instruction tuning. On Terminal-Bench~2.0 and SWE-bench Verified, HarnessBridge matches or surpasses strong specialized harnesses while substantially reducing token usage and trajectory length, and generalizes from smaller generators to larger commercial models.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.12882</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold</title>
|
||
<link>https://arxiv.org/abs/2606.13376</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13376.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Zhou, Ziheng Wang, Yuqin Lu, Haofeng Liu, Jun Liang, Shengfeng He, Jing Li</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We present MoVerse, a real-time video world model that creates an interactively navigable scene from a single narrow-field-of-view image. This setting is challenging because the input observes only a small fraction of the environment, while interactive roaming requires a complete surrounding world, persistent geometry, controllable camera motion, and temporally coherent high-fidelity observations. MoVerse addresses this problem by separating world construction from observation rendering. It first expands the input into a gravity-aligned 360^circ panorama with topology-aware diffusion, closing the missing field of view before 3D reasoning. It then lifts the panorama into a persistent 3D Gaussian scaffold using panoramic geometry-aware residual prediction, yielding a dense and directly renderable spatial memory. Finally, a Gaussian-conditioned video renderer translates scaffold renderings along user-specified camera trajectories into photorealistic video. To make this renderer practical for interaction, we train a bidirectional diffusion teacher for high-quality conditional rendering and distill it into a causal autoregressive student for bounded-latency streaming. This design combines the controllability and long-range consistency of explicit 3D representations with the perceptual quality of generative video models. MoVerse supports real-time scene roaming at 8~FPS on a single NVIDIA RTX~4090 GPU, demonstrating a practical path toward single-image world creation with interactive video output.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13376</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>VideoMDM: Towards 3D Human Motion Generation From 2D Supervision</title>
|
||
<link>https://arxiv.org/abs/2606.13364</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13364.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amir Mann, Gal Michael Harari, Merav Keidar, Or Litany</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> We introduce VideoMDM, a diffusion-based framework that trains 3D human motion priors directly from accurate 2D poses extracted from monocular videos, without any 3D ground truth. A pretrained 2D-to-3D lifter provides approximate 3D pose sequences that serve as a noisy teacher: these are diffused, denoised by the model in 3D, and supervised in 2D by reprojecting the prediction and comparing against accurate keypoints. We show that, under mild assumptions, a depth-weighted 2D reprojection loss is equivalent in expectation to direct 3D supervision, and we adapt standard 3D motion regularizers - velocity consistency and over-parameterized representation alignment - to this 2D setting. Unlike methods that lift 2D to 3D only at inference, VideoMDM learns a coherent 3D motion manifold during training. On HumanML3D it nearly closes the gap to fully 3D-supervised MDM (FID 0.88 vs 0.54); On real video datasets Fit3D and NBA the method learns to generate motions consistently preferred by humans, with strong quantitative results.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13364</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning</title>
|
||
<link>https://arxiv.org/abs/2606.13106</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayu Yang, Chao Chen, Shengen Wu, Yinhong Liu, Yuxuan Fan, Lujundong Li, Songning Lai, Chengwei Qin, Zhijiang Guo</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Latent chain-of-thought compresses reasoning by replacing visible reasoning traces with continuous hidden-state recurrence, but existing formulations are difficult to optimize with standard on-policy reinforcement learning (RL) and hard to interpret causally. Our key insight is that a single pair of explicit boundary tokens can address both issues at once: discrete entry and exit anchors make the latent block compatible with standard on-policy RL, and the same anchors offer a natural foothold for mechanistic analysis. Motivated by this, we propose SWITCH, a switchable latent reasoning framework. The model emits <swi> to enter latent mode and </swi> to exit. Because the boundaries are ordinary discrete tokens, the GRPO policy ratio is well-defined at every decision point. The same anchors also expose the latent steps to direct probing and causal intervention. We train the model with a visible-to-latent curriculum and a Switch-GRPO objective that propagates gradients through recurrent latent computation. SWITCH consistently outperforms prior hidden-state-recurrence latent reasoning approaches at similar scale. Mechanistic analysis through the boundary tokens further reveals three findings: (i) <swi> is a sharply localised, learned switching policy rather than a stylistic artefact; (ii) the latent step it opens performs problem-specific, causally important computation rather than acting as an inert placeholder; and (iii) that computation is concentrated at a single hidden-state transition on entry. Together, these results show that hidden-state-recurrence latent reasoning is both RL-trainable and open to direct mechanistic analysis, including of how on-policy RL itself improves the model from the inside.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13106</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers</title>
|
||
<link>https://arxiv.org/abs/2606.13289</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13289.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guozhen Zhang, Xuerui Qiu, Yutao Cui, Tianhui Song, Changlin Li, Junzhe Li, Tao Huang, Xiao Zhang, Yang Li, Jianbing Wu, Miles Yang, Zhao Zhong, Liefeng Bo, Limin Wang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space. In this paper, we present HYDRA-X, the first UMM that unifies image and video tokenization within a single Vision Transformer (ViT). Our design is driven by two core challenges: efficiently injecting spatiotemporal reconstruction capability into a native ViT, and embedding image- and video-level semantic awareness into the latent space. To address the first, comprehensive ablations reveal two key findings: (1) frame-level causal temporal attention suffices for visual reconstruction, whereas full spatiotemporal attention degrades it; and (2) hierarchical temporal compression substantially outperforms single-step alternatives. To tackle the second, we propose a lightweight decompressor that upsamples temporally compressed features under joint image-video teacher supervision, thereby enforcing complementary semantic structures within the compact latent space. Building on this holistic tokenizer, we further propose a principled improvement of the editing pipeline: source-target interaction should occur at the latent level inside the tokenizer rather than at the semantic level inside the LLM, substantially improving editing consistency and accelerating convergence. Instantiated at the 7B dense model, HYDRA-X achieves strong performance across image and video understanding and generation tasks, paving the way for future unified-tokenizer UMMs.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13289</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery</title>
|
||
<link>https://arxiv.org/abs/2606.13662</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13662.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amy Xin, Jiening Siow, Junjie Wang, Zijun Yao, Fanjin Zhang, Jian Song, Lei Hou, Juanzi Li</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> LLM-based agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and an execution environment, they can propose, validate, and iterate scientific solutions, and have produced results that outperform human-designed approaches. As model capabilities continue to improve, we argue that the bottleneck for autonomous scientific discovery is shifting from prescribing agent workflows to designing agent environments: the resources, constraints, and interfaces that shape agent behavior. We frame this as environment engineering: building environments that amplify productive behaviors, such as open-ended exploration, systematic artifact management, and inter-agent collaboration, while suppressing harmful behaviors, such as reward hacking and high-friction human oversight. We present EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery. EurekAgent engineers the environment along four dimensions: permissions engineering for bounded agent execution and isolated evaluation; artifact engineering for filesystem and Git-based collaboration; budget engineering for budget-aware exploration; and human-in-the-loop engineering for easy human supervision and intervention. EurekAgent sets new state-of-the-art results on multiple mathematics, kernel engineering, and machine learning tasks, including new state-of-the-art 26-circle packing results discovered with less than $11 in total API cost. We open-source our code and results, and call for environment engineering as a core research direction for developing reliable autonomous research agents.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13662</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories</title>
|
||
<link>https://arxiv.org/abs/2606.13578</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13578.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baochang Ren, Xinjie Liu, Xi Chen, Yanshuo Liu, Chenxi Li, Daqi Gao, Zeqin Su, Jintao Xing, Zirui Xue, Rui Li, Xiangyu Zhao, Shuofei Qiao, Minting Pan, Wangmeng Zuo, Lei Bai, Dongzhan Zhou, Ningyu Zhang, Huajun Chen</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read literature, generate hypotheses, and plan protocols, yet the execution of those protocols at the bench still requires a human operator. Vision-Language-Action (VLA) models provide one possible interface between written protocols and robot execution, but existing policies are trained mostly on household and tabletop demonstrations and rarely encounter the instruments, transparent liquids, or fixed protocol workflows found in scientific laboratories. Closing this gap requires both laboratory-specific supervision and a unified learning framework that can accommodate the diverse robot embodiments used to execute experimental protocols. We therefore identify data and embodiment as central bottlenecks alongside model design. To address the data side, we build RoboGenesis, a simulation-based workflow and data engine that composes configured laboratory workflows from atomic skills, validates and filters rollouts, and exports structured demonstrations across supported robot profiles. On the policy side, we present LabVLA, trained with a two-stage recipe: FAST action token pretraining first makes the Qwen3-VL-4B-Instruct backbone action aware before any continuous control is learned, and flow matching posttraining then attaches a DiT action expert under knowledge insulation. On the LabUtopia benchmark, LabVLA achieves the highest average success rate among all evaluated baselines under both in-distribution and out-of-distribution settings.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13578</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling</title>
|
||
<link>https://arxiv.org/abs/2606.13473</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13473.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiacheng Chen, Xinyu Zhang, Shunkai Zhang, Yanmohan Wang, Lin Li, Tiancheng Qin, Qin Wang, Zhengmao Zhu, Tianle Li, Jingyang Li, Zehan Li, Binyang Jiang, Jin Zhu, Han Ding, Fei Yu, Chenyu Du, Zijian Song, Jiayuan Song, Zhi Zhang, Yunan Huang, Weiyu Cheng, Pengyu Zhao, Yu Cheng</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities -- proof generation, proof verification, and critique-conditioned proof repair -- using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13473</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>InterleaveThinker: Reinforcing Agentic Interleaved Generation</title>
|
||
<link>https://arxiv.org/abs/2606.13679</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13679.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dian Zheng, Harry Lee, Manyuan Zhang, Kaituo Feng, Zoey Guo, Ray Zhang, Hongsheng Li</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their architectures, they cannot achieve interleaved generation (text-image sequence), which has crucial applications in visual narratives, guidance, and embodied manipulation. Even the latest open-source Unified Multimodal Models (UMMs) exhibit limited performance in this regard. In this paper, we introduce InterleaveThinker, the first multi-agent pipeline designed to endow any existing image generator with interleaved generation capabilities. Specifically, we employ a planner agent to organize the image-text input sequence, instructing the image generator on the required execution at each step. Subsequently, we introduce a critic agent to evaluate the generator's outputs, identify samples that deviate from the planned instructions, and refine the instructions for regeneration. To implement this pipeline, we construct the Interleave-Planner-SFT-80k and Interleave-Critic-SFT-112k to perform a format cold-start. Then we develop Interleave-Critic-RL-13k to reinforce the step-wise instruction correction capability within a generation trajectory using GRPO. Since a single interleaved generation trajectory may involve over 25 generator calls, optimizing the entire trajectory is computationally impractical. Therefore, we propose accuracy reward and step-wise reward, allowing single-step RL to effectively guide the entire generation trajectory. The results show that InterleaveThinker improves performance across various image generators. On interleaved generation benchmarks, it achieves performance comparable to Nano Banana and GPT-5. Surprisingly, it also significantly enhances the base model on reasoning-based benchmarks; for example, on 4-step FLUX.2-klein, we observe substantial gains on WISE and RISE.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13679</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning</title>
|
||
<link>https://arxiv.org/abs/2606.13673</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13673.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su, Byung-Kwan Lee, Chan Hee Song, Sifei Liu, Subhashree Radhakrishnan, Seungryong Kim, Yu-Chiang Frank Wang, Min-Hung Chen</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-augmented agents attempt to address this by augmenting VLMs with specialist perception modules, yet their effectiveness is bounded by the action interface through which those tools are invoked. In this work, we study how the design of this interface shapes the agent's capacity for open-ended spatial reasoning. Existing spatial agents either employ single-pass code execution, which commits to a full analysis strategy before any intermediate result is observed, or rely on a structured tool-call interface that often offers less flexibility for freely composing operations or tailoring the analysis to each task. Both designs offer limited flexibility for open-ended, complex 3D/4D spatial reasoning. We therefore propose SpatialClaw, a training-free framework for spatial reasoning that adopts code as the action interface. SpatialClaw maintains a stateful Python kernel pre-loaded with input frames and a suite of perception and geometry primitives, letting a VLM-backed agent write one executable cell per step conditioned on all prior outputs, enabling the agent to flexibly compose and manipulate perception results and adapt its analysis to both intermediate text and visual observations and the demands of each problem. Evaluated across 20 spatial reasoning benchmarks spanning a broad range of static and dynamic 3D/4D spatial reasoning tasks, SpatialClaw achieves 59.9% average accuracy, outperforming the recent spatial agent by +11.2 points, with consistent gains across six VLM backbones from two model families without any benchmark- or model-specific adaptation.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13673</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MiniMax Sparse Attention</title>
|
||
<link>https://arxiv.org/abs/2606.13392</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13392.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xunhao Lai, Weiqi Xu, Yufeng Yang, Qiaorui Chen, Yang Xu, Lunbin Zeng, Xiaolong Li, Haohai Sun, Haichao Zhu, Vito Zhang, Pengyu Zhao</p><p><b>Upvotes:</b> 119</p><p><b>Summary:</b> Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax attention makes this untenable at deployment scale. We introduce MiniMax Sparse Attention (MSA), a blockwise sparse attention built upon Grouped Query Attention (GQA). A lightweight Index Branch scores key-value blocks and independently selects a Top-k subset for each GQA group, enabling group-specific sparse retrieval while maintaining efficient block-level execution; the Main Branch then performs exact block-sparse attention over only the selected blocks. Designed around a principle of simplicity and scalability, MSA is deliberately streamlined, making it straightforward to deploy efficiently across a broad range of GPUs. To translate sparsity into practical speedups, we co-design MSA with a GPU execution path that uses exp-free Top-k selection and KV-outer sparse attention to improve tensor-core utilization under block-granular access. On a 109B-parameter model with native multimodal training, MSA performs on par with GQA while reducing per-token attention compute by 28.4x at 1M context. Paired with our co-designed kernel, MSA achieves 14.2x prefill and 7.6x decoding wall-clock speedups on H800. Our inference kernel is available at: https://github.com/MiniMax-AI/MSA. A production-grade natively multimodal model powered by MSA has been publicly released at: https://huggingface.co/MiniMaxAI/MiniMax-M3.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13392</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments</title>
|
||
<link>https://arxiv.org/abs/2606.13681</link>
|
||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2606.13681.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jundong Xu, Qingchuan Li, Jiaying Wu, Yihuai Lan, Shuyue Stella Li, Huichi Zhou, Bowen Jiang, Lei Wang, Jun Wang, Anh Tuan Luu, Caiming Xiong, Hae Won Park, Bryan Hooi, Zhiyuan Hu</p><p><b>Upvotes:</b> 127</p><p><b>Summary:</b> Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions. To address this gap, we introduce EvoArena, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains. We further propose EvoMem, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through changes in their memory. Experiments show that current agents struggle on EvoArena, achieving an average accuracy of 39.6% across evolving terminal, software, and social-preference domains. EvoMem consistently improves performance, yielding an average gain of 1.5% on EvoArena and also improving standard benchmarks such as GAIA and LoCoMo by 6.1% and 4.8%. Beyond individual tasks, EvoMem further improves chain-level accuracy by 3.7% on EvoArena, where success requires completing a consecutive sequence of related evolutionary subtasks. Mechanistic analysis shows that EvoMem improves evidence capture in the memory, indicating better preservation of complete evolving environment states. Our results highlight the importance of modeling evolution in both evaluation and memory for reliable agent deployment.</p></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2606.13681</guid>
|
||
<pubDate>Thu, 11 Jun 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
</channel>
|
||
</rss>
|