huggingface-daily-paper-feed/feed_weekly.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, 25 May 2026 00:34:57 +0000</lastBuildDate>
    <item>
      <title>OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments</title>
      <link>https://arxiv.org/abs/2605.18758</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18758.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Felix Henry, Xiaochen Lin, Jiangyou Zhu, Yangfan, Bingqian Zhang, Min Chen, Shiyu Huang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 15&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction routinely requires agents to process transient audio cues and temporal video dynamics that are tightly coupled with the moment of action. To bridge this gap, we introduce OmniGUI, the first step-level benchmark designed to evaluate GUI agents in omni-modal smartphone environments. OmniGUI provides continuous, interleaved multimodal inputs comprising static images, synchronous audio, and video clips at every action step. The dataset encompasses 709 expert-demonstrated episodes (2,579 action steps) across 29 applications, systematically annotated with objective multimodal dependency levels. Because dedicated omni-modal GUI agent frameworks are currently in their nascent stage, we select foundational omni-modal models capable of natively processing interleaved inputs to serve as agent proxies for our initial baselines. Our empirical evaluation reveals that while current models exhibit competency on visually static tasks, their action prediction performance degrades significantly in environments requiring synchronous temporal and auditory signals. Furthermore, ablation studies isolate specific operational bottlenecks, notably cross-modal interference when processing task-irrelevant environmental noise. The complete dataset, evaluation pipeline, and baseline prompts are provided in the supplementary material. Project page: https://omni-gui.github.io.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18758</guid>
      <pubDate>Fri, 03 Apr 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding</title>
      <link>https://arxiv.org/abs/2605.02290</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02290.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Taewon Yun, Jisu Shin, Jeonghwan Choi, Seunghwan Bang, Hwanjun Song&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 39&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Distilling large reasoning models is essential for making Long-CoT reasoning practical, as full-scale inference remains computationally prohibitive. Existing curation-based approaches select complete reasoning traces post-hoc, overlooking collaboration among heterogeneous teachers and lacking dynamic exploration, which leads to redundant sampling and missed complementary reasoning. We introduce CoRD, a collaborative multi-teacher decoding framework that performs step-wise reasoning synthesis guided by predictive perplexity-based scoring and beam search. This enables heterogeneous LRMs to jointly construct coherent reasoning trajectories while efficiently preserving diverse, high-potential hypotheses. Experiments show that CoRD produces higher-quality reasoning data and achieves near teacher-level student performance with fewer, structured supervision signals, without substantial efficiency overhead. CoRD further generalizes well to out-of-domain and open-ended settings. The dataset and model are available at https://github.com/DISL-Lab/CoRD{https://github.com/DISL-Lab/CoRD}.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.02290</guid>
      <pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware</title>
      <link>https://arxiv.org/abs/2605.05945</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05945.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Senthil Palanisamy, Abhishek Anand, Satpal Singh Rathor, Pratyush Patnaik, Shubhanshu Khatana&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 10&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; The recent advancement of Vision Language Action (VLA) models has driven a critical demand for large scale egocentric datasets. However, existing datasets are often limited by short episode durations, typically spanning only a few minutes, which fails to capture the long horizon temporal dependencies necessary for complex robotic task execution. To bridge this gap, we present MobileEgo Anywhere, a framework designed to facilitate the collection of robust, hour plus egocentric trajectories using commodity mobile hardware. We leverage the ubiquitous sensor suites of modern smartphones to provide high fidelity, long term camera pose tracking, effectively removing the high hardware barriers associated with traditional robotics data collection. Our contributions are three fold: (1) we release a novel dataset comprising 200 hours of diverse, long form egocentric data with persistent state tracking; (2) we open source a mobile application that enables any user to record egocentric data, and (3) we provide a comprehensive processing pipeline to convert raw mobile captures into standardized, training ready formats for Vision Language Action model and foundation model research. By democratizing the data collection process, this work enables the massive scale acquisition of long horizon data across varied global environments, accelerating the development of generalizable robotic policies.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.05945</guid>
      <pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Steered LLM Activations are Non-Surjective</title>
      <link>https://arxiv.org/abs/2604.09839</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.09839.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Aayush Mishra, Daniel Khashabi, Anqi Liu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 11&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating activations into human-readable explanations) and safety research (e.g., jailbreakability). However, it is unclear whether steered behavior is realizable by any textual prompt. In this work, we cast this question as a surjectivity problem: for a fixed model, does every steered activation admit a preimage under the model's natural forward pass? Under practical assumptions, we prove that activation steering pushes the residual stream off the manifold of states reachable from discrete prompts. Almost surely, no prompt can reproduce the same internal behavior induced by steering. We also illustrate this finding empirically across three widely used LLMs. Our results establish a formal separation between white-box steerability and black-box prompting. We therefore caution against interpreting the ease and success of activation steering as evidence of prompt-based interpretability or vulnerability, and argue for evaluation protocols that explicitly decouple white-box and black-box interventions.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2604.09839</guid>
      <pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Unsupervised Process Reward Models</title>
      <link>https://arxiv.org/abs/2605.10158</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10158.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Artyom Gadetsky, Maxim Kodryan, Siba Smarak Panigrahi, Hang Guo, Maria Brbic&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 23&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Process Reward Models (PRMs) are a powerful mechanism for steering large language model reasoning by providing fine-grained, step-level supervision. However, this effectiveness comes at a significant cost: PRMs require expert annotations for every reasoning step, making them costly and difficult to scale. Here, we propose a method for training unsupervised PRMs (uPRM) that requires no human supervision, neither at the level of step-by-step annotations nor through ground-truth verification of final answers. The key idea behind our approach is to define a scoring function, derived from LLM next-token probabilities, that jointly assesses candidate positions of first erroneous steps across a batch of reasoning trajectories. We demonstrate the effectiveness of uPRM across diverse scenarios: (i) uPRM achieves up to 15% absolute accuracy improvements over the LLM-as-a-Judge in identifying first erroneous steps on the ProcessBench dataset; (ii) as a verifier for test-time scaling, uPRM performs comparably to supervised PRMs and outperforms the majority voting baseline by up to 6.9%, and (iii) when used as a reward signal in reinforcement learning, uPRM enables more robust policy optimization throughout training compared to a supervised PRM trained using ground-truth labels. Overall, our results open a path toward scalable reward modeling for complex reasoning tasks.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.10158</guid>
      <pubDate>Mon, 11 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Targeted Neuron Modulation via Contrastive Pair Search</title>
      <link>https://arxiv.org/abs/2605.12290</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12290.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Sam Herring, Jake Naviasky, Karan Malhotra&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 14&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Language models are instruction-tuned to refuse harmful requests, but the mechanisms underlying this behavior remain poorly understood. Popular steering methods operate on the residual stream and degrade output coherence at high intervention strengths, limiting their practical use. We introduce contrastive neuron attribution (CNA), which identifies the 0.1% of MLP neurons whose activations most distinguish harmful from benign prompts, requiring only forward passes with no gradients or auxiliary training. In instruct models, ablating the discovered circuit reduces refusal rates by over 50% on a standard jailbreak benchmark while preserving fluency and non-degeneracy across all steering strengths. Applying CNA to matched base and instruct models across Llama and Qwen architectures (from 1B to 72B parameters), we find that base models contain similar late-layer discrimination structures but steering these neurons produces only content shifts, not behavioral change. These results demonstrate that neuron-level intervention enables reliable behavioral steering without the quality tradeoffs of residual-stream methods. More broadly, our findings suggest that alignment fine-tuning transforms pre-existing discrimination structure into a sparse, targetable refusal gate.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.12290</guid>
      <pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Training Large Language Models to Predict Clinical Events</title>
      <link>https://arxiv.org/abs/2605.12817</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12817.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Benjamin Turtel, Paul Wilczewski, Kris Skotheim&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 14&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Longitudinal clinical notes contain rich evidence of how patients evolve over time, but converting this signal into training supervision for clinical prediction remains challenging. We extend Foresight Learning to clinical prediction by converting time-ordered MIMIC-III notes into examples consisting of past patient context, a natural-language question about a possible future event, and a label resolved from later documentation. This process yields 6,900 prediction examples from 702 admissions across medications, procedures, organ support, microbiology, and mortality. A small LoRA adapter trained on these examples improves over the prompted base model, reducing expected calibration error from 0.1269 to 0.0398 and Brier score from 0.199 to 0.145, while slightly outperforming GPT-5 point estimates on held-out questions. The approach enables reusable clinical prediction supervision from longitudinal notes without hand-engineered structured features or endpoint-specific classifiers.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.12817</guid>
      <pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Hölder Policy Optimisation</title>
      <link>https://arxiv.org/abs/2605.12058</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12058.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yuxiang Chen, Dingli Liang, Yihang Chen, Ziqin Gong, Chenyang Le, Zhaokai Wang, Jiachen Zhu, Lingyu Yang, Jianghao Lin, Weinan Zhang, Jun Wang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 19&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Group Relative Policy Optimisation (GRPO) enhances large language models by estimating advantages across a group of sampled trajectories. However, mapping these trajectory-level advantages to policy updates requires aggregating token-level probabilities within each sequence. Relying on a fixed aggregation mechanism for this step fundamentally limits the algorithm's adaptability. Empirically, we observe a critical trade-off: certain fixed aggregations frequently suffer from training collapse, while others fail to yield satisfactory performance. To resolve this, we propose HölderPO, a generalised policy optimisation framework unifying token-level probability aggregation via the Hölder mean. By explicitly modulating the parameter p, our framework provides continuous control over the trade-off between gradient concentration and variance bounds. Theoretically, we prove that a larger p concentrates the gradient to amplify sparse learning signals, whereas a smaller p strictly bounds gradient variance. Because no static configuration can universally resolve this concentration-stability trade-off, we instantiate the framework with a dynamic annealing algorithm that progressively schedules p across the training lifecycle. Extensive evaluations demonstrate superior stability and convergence over existing baselines. Specifically, our approach achieves a state-of-the-art average accuracy of 54.9% across multiple mathematical benchmarks, yielding a substantial 7.2% relative gain over standard GRPO and secures an exceptional 93.8% success rate on ALFWorld.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.12058</guid>
      <pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information</title>
      <link>https://arxiv.org/abs/2605.11609</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.11609.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Guobin Shen, Xiang Cheng, Chenxiao Zhao, Lei Huang, Jindong Li, Dongcheng Zhao, Xing Yu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 190&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger external teacher. Yet in math reasoning the gains are inconsistent, even when the same approach succeeds elsewhere. A pointwise mutual information analysis traces the failure to the privileged context itself: it inflates the teacher's confidence on tokens already implied by the solution (structural connectives, verifiable claims) and deflates it on deliberation tokens ("Wait", "Let", "Maybe") that drive multi-step search. We propose Anti-Self-Distillation (AntiSD), which ascends a divergence between student and teacher rather than descending it: this reverses the per-token sign and yields a naturally bounded advantage in one step. An entropy-triggered gate disables the term once the teacher entropy collapses, completing a drop-in replacement for default self-distillation. Across five models from 4B to 30B parameters on math reasoning benchmarks, AntiSD reaches the GRPO baseline's accuracy in 2 to 10x fewer training steps and improves final accuracy by up to 11.5 points. AntiSD opens a path to scalable self-improvement, where a language model bootstraps its own reasoning through its training signal.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.11609</guid>
      <pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving</title>
      <link>https://arxiv.org/abs/2605.13734</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13734.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Zedong Liu, Xinyang Ma, Dejun Luo, Hairui Zhao, Bing Lu, Wenjing Huang, Yida Gu, Xingchen Liu, Zheng Wei, Jinyang Liu, Dingwen Tao, Guangming Tan&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 10&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggregation) improves scalability and cost efficiency, but it also turns KV into an explicit payload crossing network and storage boundaries, making KV a dominant end-to-end bottleneck. Existing KV compression are typically static runtime configurations, despite production service context varies over time in workload mix, bandwidth, and SLO/quality budgets. As a result, a fixed choice can be suboptimal or even increase latency. We present KVServe, the first service-aware and adaptive KV communication compression framework for disaggregated LLM serving: KVServe (1) unifies KV compression into a modular strategy space with new components and cross-method recomposition; (2) introduces Bayesian Profiling Engine that efficiently searches this space and distills a 3D Pareto candidate set, reducing 50times offline search overhead; and (3) deploys a Service-Aware Online Controller that combines an analytical latency model with a lightweight bandit to select profiles under constraints and correct offline-to-online mismatch. Integrated into vLLM and evaluated across datasets, models, GPUs and networks, KVServe achieves up to 9.13times JCT speedup in PD-separated serving and up to 32.8times TTFT reduction in KV-disaggregated serving.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.13734</guid>
      <pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation</title>
      <link>https://arxiv.org/abs/2605.11739</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.11739.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yuchen Cai, Ding Cao, Liang Lin, Chunxi Luo, Xin Xu, Kai Yang, Weijie Liu, Saiyong Yang, Tianxiang Zhao, Guangzhong Sun, Guiquan Liu, Junfeng Fang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 56&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and more stable supervision, while the parameter-level mechanisms underlying OPD's efficiency remain poorly understood. In this work, we argue that OPD's efficiency stems from a form of ``foresight'': it establishes a stable update trajectory toward the final model early in training. This foresight manifests in two aspects. First, at the Module-Allocation Level, OPD identifies regions with low marginal utility and concentrates updates on modules that are more critical to reasoning. Second, at the Update-Direction Level, OPD exhibits stronger low-rank concentration, with its dominant subspaces aligning closely with the final update subspace early in training. Building on these findings, we propose EffOPD, a plug-and-play acceleration method that speeds up OPD by adaptively selecting an extrapolation step size and moving along the current update direction. EffOPD requires no additional trainable modules or complex hyperparameter tuning, and achieves an average training acceleration of 3times while maintaining comparable final performance. Overall, our findings provide a parameter-dynamics perspective for understanding the efficiency of OPD and offer practical insights for designing more efficient post-training methods for large language models.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.11739</guid>
      <pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>When Vision Speaks for Sound</title>
      <link>https://arxiv.org/abs/2605.16403</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.16403.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Xiaofei Wen, Wenjie Jacky Mo, Xingyu Fu, Rui Cai, Tinghui Zhu, Wendi Li, Yanan Xie, Muhao Chen, Peng Qi&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 146&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual cues to infer or hallucinate acoustic information, rather than verifying the audio stream. This issue appears across both state-of-the-art open-source omni models and leading closed-source models from providers such as Google and OpenAI. We characterize this failure mode as an audio-visual Clever Hans effect, in which models appear (falsely) audio-grounded, but actually exploit visual-acoustic correlations without verifying whether the audio and visual streams are truly aligned. To systematically study this behavior, we introduce Thud, an intervention-driven probing framework based on three counterfactual audio edits: Shift, which tests temporal synchronization; Mute, which tests sound existence; and Swap, which tests audio-visual consistency. Beyond diagnosis, we further study a two-stage alignment recipe: intervention-derived preference pairs teach audio verification, while event-level general video preferences regularize the model against over-specialization. Our best 10K-sample recipe improves average performance across the three intervention dimensions by 28 percentage points, while slightly improving performance on general video and audio-visual QA benchmarks.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.16403</guid>
      <pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence</title>
      <link>https://arxiv.org/abs/2605.12882</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12882.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Dongsheng Ma, Jiayu Li, Zhengren Wang, Yijie Wang, Jiahao Kong, Weijun Zeng, Jutao Xiao, Jie Yang, Wentao Zhang, Bin Wang, Conghui He&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 264&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting evidence unchecked. This answer-only approach masks a critical failure mode: a model can land on the correct answer while grounding it in the wrong passage -- a critical risk in high-stakes domains like law, finance, and medicine, where every conclusion must be traceable to a specific source region. To address this, we introduce CiteVQA, a benchmark that requires models to return element-level bounding-box citations alongside each answer, evaluating both jointly. CiteVQA comprises 1,897 questions across 711 PDFs spanning seven domains and two languages, averaging 40.6 pages per document. To ensure fidelity and scalability, the ground-truth citations are generated by an automated pipeline-which identifies crucial evidence via masking ablation-and are subsequently validated through expert review. At the core of our evaluation is Strict Attributed Accuracy (SAA), which credits a prediction only when the answer and the cited region are both correct. Auditing 20 MLLMs reveals a pervasive Attribution Hallucination: models frequently produce the right answer while citing the wrong region. The strongest system (Gemini-3.1-Pro-Preview) achieves an SAA of only 76.0, and the strongest open-source MLLM reaches just 22.5. Ultimately, towards trustworthy document intelligence, CiteVQA exposes a reliability gap that answer-only evaluations overlook, providing the instrumentation needed to close it. Our repository is available at https://github.com/opendatalab/CiteVQA.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.12882</guid>
      <pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing</title>
      <link>https://arxiv.org/abs/2605.15181</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15181.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Anirudh Sundara Rajan, Krishna Kumar Singh, Yong Jae Lee&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 12&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted pipelines or teacher imitation, limiting flexibility and decoupling learning from actual editing outcomes. We propose an experiential framework for long-horizon image editing, where a planner generates structured atomic decompositions and an orchestrator selects tools and regions to execute each step. A vision language judge provides outcome-based rewards for instruction adherence and visual quality. The orchestrator is trained to maximize these rewards, and successful trajectories are used to refine the planner. By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15181</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>EndPrompt: Efficient Long-Context Extension via Terminal Anchoring</title>
      <link>https://arxiv.org/abs/2605.14589</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14589.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Han Tian, Luxuan Chen, Xinran Chen, Rui Kong, Fang Wang, Jiamin Chen, Jinman Zhao, Yuchen Li, Jiashu Zhao, Shuaiqiang Wang, Haoyi Xiong, Dawei Yin&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 15&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Extending the context window of large language models typically requires training on sequences at the target length, incurring quadratic memory and computational costs that make long-context adaptation expensive and difficult to reproduce. We propose EndPrompt, a method that achieves effective context extension using only short training sequences. The core insight is that exposing a model to long-range relative positional distances does not require constructing full-length inputs: we preserve the original short context as an intact first segment and append a brief terminal prompt as a second segment, assigning it positional indices near the target context length. This two-segment construction introduces both local and long-range relative distances within a short physical sequence while maintaining the semantic continuity of the training text--a property absent in chunk-based simulation approaches that split contiguous context. We provide a theoretical analysis grounded in Rotary Position Embedding and the Bernstein inequality, showing that position interpolation induces a rigorous smoothness constraint over the attention function, with shared Transformer parameters further suppressing unstable extrapolation to unobserved intermediate distances. Applied to LLaMA-family models extending the context window from 8K to 64K, EndPrompt achieves an average RULER score of 76.03 and the highest average on LongBench, surpassing LCEG (72.24), LongLoRA (72.95), and full-length fine-tuning (69.23) while requiring substantially less computation. These results demonstrate that long-context generalization can be induced from sparse positional supervision, challenging the prevailing assumption that dense long-sequence training is necessary for reliable context-window extension. The code is available at https://github.com/clx1415926/EndPrompt.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.14589</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning</title>
      <link>https://arxiv.org/abs/2605.14212</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14212.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yaolun Zhang, Yujie Zhao, Nan Wang, Yiran Wu, Jiayu Chang, Yizhao Chen, Qingyun Wu, Jishen Zhao, Huazheng Wang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 18&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Automatic multi-agent systems aim to instantiate agent workflows without relying on manually designed or fixed orchestration. However, existing automatic MAS approaches remain only partially adaptive: they either perform training-free test-time search or optimize the meta-level designer while keeping downstream execution agents frozen, which creating a frozen-executor ceiling and leaving the end-to-end training of self-designing and self-executing agentic models unexplored. To address this, we introduce MetaAgent-X, an end-to-end reinforcement learning framework that jointly optimizes automatic MAS design and execution. MetaAgent-X enables script-based MAS generation, execution rollout collection, and credit assignment for both designer and executor trajectories. To support stable and scalable optimization, we propose Executor Designer Hierarchical Rollout and Stagewise Co-evolution to improve training stability and expose the dynamics of designer-executor co-evolution. MetaAgent-X consistently outperforms existing automatic MAS baselines, achieving up to 21.7% gains. Comprehensive ablations show that both designer and executor improve throughout training, and that effective automatic MAS learning follows a stagewise co-evolution process. These results establish end-to-end trainable automatic MAS as a practical paradigm for building self-designing and self-executing agentic models.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.14212</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution</title>
      <link>https://arxiv.org/abs/2605.15301</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15301.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Han Li, Jinyu Tian, Rili Feng, Yuqiao Du, Chong Zheng, Chenyu Wang, Chenchen Liu, Shihao Li, Xinping Lei, Yifan Yao, Weihao Xie, Letian Zhu, Jiaheng Liu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 22&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Large language models (LLMs) still struggle with the rigorous reasoning demands of hard competitive programming. While recent multi-agent frameworks attempt to bridge this reliability gap, they remain fundamentally stateless: they rely on static retrieval and discard the valuable problem-solving and debugging experience gained from previous tasks. To address this, we present Solvita, an agentic evolution framework that enables continuous learning without requiring weight updates to the underlying LLM. Solvita reorganizes problem-solving into a closed-loop system of strategy selection, program synthesis, certified supervision, and targeted hacking, executed by four specialized agents: Planner, Solver, Oracle, and Hacker. Crucially, each agent is paired with a trainable, graph-structured knowledge network. As the system operates, outcome signals, such as pass/fail verdicts, test certification quality, and adversarial vulnerabilities discovered by the Hacker, are recast as reinforcement learning updates to these network weights. This allows the agents to dynamically route future queries based on past successes and failures, effectively accumulating transferable reasoning experience over time. Evaluated across CodeContests, APPS, AetherCode, and live Codeforces rounds, Solvita establishes a new state-of-the-art among code-generation agents, outperforming existing multi-agent pipelines and nearly doubling the accuracy of single-pass baselines.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15301</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>ReactiveGWM: Steering NPC in Reactive Game World Models</title>
      <link>https://arxiv.org/abs/2605.15256</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15256.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Zeqing Wang, Danze Chen, Zhaohu Xing, Zizhao Tong, Yinhan Zhang, Xingyi Yang, Yeying Jin&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 28&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Current game world models simulate environments from a subjective, player-centric perspective. However, by treating the Non-Player Character (NPC) merely as background pixels, these models cannot capture interactions between the player and NPC. In that sense, they act as passive video renderers rather than real simulation engines, lacking the physical understanding needed to model action-induced NPC reactivities. We introduce ReactiveGWM, a reactive game world model that synthesizes dynamic interactions between the player and NPC. Instead of entangling all interaction dynamics, ReactiveGWM explicitly decouples player controls from NPC behaviors. Player actions are injected into the diffusion backbone via a lightweight additive bias, while high-level NPC responses (e.g., Offense, Control, Defense) are grounded through cross-attention modules. Crucially, these modules learn a game-agnostic representation of interactive logic. This enables zero-shot strategy transfer: our learned modules can be plugged directly into off-the-shelf, unannotated world models of different games. This instantly unlocks steerable NPC interactions without any domain-specific retraining. Evaluated on two Street Fighter games, ReactiveGWM maintains fine-grain player controllability while achieving robust, prompt-aligned NPC strategy adherence, paving the way for scalable, strategy-rich interaction with the NPC.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15256</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation</title>
      <link>https://arxiv.org/abs/2605.14333</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14333.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yang Yue, Fangyun Wei, Tianyu He, Jinjing Zhao, Zanlin Ni, Zeyu Liu, Jiayi Guo, Lei Shi, Yue Dong, Li Chen, Ji Li, Gao Huang, Dong Chen&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 33&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer: aggressive downsampling and quantization often discard the fine-grained structures needed to preserve readable glyphs and distinctive facial features. We attribute this gap to standard discrete-tokenizer objectives being weakly aligned with text legibility and facial fidelity, as these objectives typically optimize generic reconstruction while compressing diverse content uniformly. To address this, we propose InsightTok, a simple yet effective discrete visual tokenization framework that enhances text and face fidelity through localized, content-aware perceptual losses. With a compact 16k codebook and a 16x downsampling rate, InsightTok significantly outperforms prior tokenizers in text and face reconstruction without compromising general reconstruction quality. These gains consistently transfer to autoregressive image generation in InsightAR, producing images with clearer text and more faithful facial details. Overall, our results highlight the potential of specialized supervision in tokenizer training for advancing discrete image generation.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.14333</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration</title>
      <link>https://arxiv.org/abs/2605.14278</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14278.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Ruicheng Zhang, Kaixi Cong, Jun Zhou, Zhizhou Zhong, Zunnan Xu, Shuiyang Mao, Wei Liu, Xiu Li&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 37&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Aligning streaming autoregressive (AR) video generators with human preferences is challenging. Existing reinforcement learning methods predominantly rely on noise-based exploration and SDE-based surrogate policies that are mismatched to the deterministic ODE dynamics of distilled AR models, and tend to perturb low-level appearance rather than the high-level semantic storyline progression critical for long-horizon coherence. To address these limitations, we present KVPO, an ODE-native online Group Relative Policy Optimization (GRPO) framework for aligning streaming video generators. For diversity exploration, KVPO introduces a causal-semantic exploration paradigm that relocates the source of variation from stochastic noise to the historical KV cache. By stochastically routing historical KV entries, it constructs semantically diverse generation branches that remain strictly on the data manifold. For policy modeling, KVPO introduces a velocity-field surrogate policy based on Trajectory Velocity Energy (TVE), which quantifies branch likelihood in flow-matching velocity space and yields a reward-weighted contrastive objective fully consistent with the native ODE formulation. Experiments on multiple distilled AR video generators demonstrate consistent gains in visual quality, motion quality, and text-video alignment across both single-prompt short-video and multi-prompt long-video settings.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.14278</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Auditing Agent Harness Safety</title>
      <link>https://arxiv.org/abs/2605.14271</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14271.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Chengzhi Liu, Yichen Guo, Yepeng Liu, Yuzhe Yang, Qianqi Yan, Xuandong Zhao, Wenyue Hua, Sheng Liu, Sharon Li, Yuheng Bu, Xin Eric Wang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 54&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a correct, benign answer over a trajectory that accesses unauthorized resources or leaks context to the wrong agent. Output-level evaluation cannot see these failures, yet most safety benchmarks score only final outputs or terminal states, even though many violations occur mid-trajectory rather than at termination. The central question is whether the harness respects user intent, permission boundaries, and information-flow constraints throughout execution. To address this gap, we propose HarnessAudit, a framework that audits full execution trajectories across boundary compliance, execution fidelity, and system stability, with a focus on multi-agent harnesses where these risks are most pronounced. We further introduce HarnessAudit-Bench, a benchmark of 210 tasks across eight real-world domains, instantiated in both single-agent and multi-agent configurations with embedded safety constraints. Evaluating ten harness configurations across frontier models and three multi-agent frameworks, we find that: (i) task completion is misaligned with safe execution, and violations accumulate with trajectory length; (ii) safety risks vary across domains, task types, and agent roles; (iii) most violations concentrate in resource access and inter-agent information transfer; and (iv) multi-agent collaboration expands the safety risk surface, while harness design sets the upper bound of safe deployment.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.14271</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>MMSkills: Towards Multimodal Skills for General Visual Agents</title>
      <link>https://arxiv.org/abs/2605.13527</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13527.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Kangning Zhang, Shuai Shao, Qingyao Li, Jianghao Lin, Lingyue Fu, Shijian Wang, Wenxiang Jiao, Yuan Lu, Weiwen Liu, Weinan Zhang, Yong Yu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 117&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as textual prompts, executable code, or learned routines. For visual agents, however, procedural knowledge is inherently multimodal: reuse depends not only on what operation to perform, but also on recognizing the relevant state, interpreting visual evidence of progress or failure, and deciding what to do next. We formalize this requirement as multimodal procedural knowledge and address three practical challenges: (I) what a multimodal skill package should contain; (II) where such packages can be derived from public interaction experience; and (III) how agents can consult multimodal evidence at inference time without excessive image context or over-anchoring to reference screenshots. We introduce MMSkills, a framework for representing, generating, and using reusable multimodal procedures for runtime visual decision making. Each MMSkill is a compact, state-conditioned package that couples a textual procedure with runtime state cards and multi-view keyframes. To construct these packages, we develop an agentic trajectory-to-skill Generator that transforms public non-evaluation trajectories into reusable multimodal skills through workflow grouping, procedure induction, visual grounding, and meta-skill-guided auditing. To use them, we introduce a branch-loaded multimodal skill agent: selected state cards and keyframes are inspected in a temporary branch, aligned with the live environment, and distilled into structured guidance for the main agent. Experiments across GUI and game-based visual-agent benchmarks show that MMSkills consistently improve both frontier and smaller multimodal agents, suggesting that external multimodal procedural knowledge complements model-internal priors.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.13527</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>PhysBrain 1.0 Technical Report</title>
      <link>https://arxiv.org/abs/2605.15298</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15298.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Shijie Lian, Bin Yu, Xiaopeng Lin, Changti Wu, Hang Yuan, Xiaolin Hu, Zhaolong Shen, Yuzhuo Miao, Haishan Liu, Yuxuan Tian, Yukun Shi, Cong Huang, Kai Chen&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 140&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Vision-language-action models have advanced rapidly, but robot trajectories alone provide limited coverage for learning broad physical understanding. PhysBrain 1.0 studies a complementary route: converting large-scale human egocentric video into structured physical commonsense supervision before robot adaptation. Our data engine extracts scene elements, spatial dynamics, action execution, and depth-aware relations, then turns them into question-answer supervision for training PhysBrain VLMs. The resulting physical priors are further transferred to VLA policies through a capability-preserving and language-sensitive adaptation design. Across multimodal QA benchmarks and embodied control benchmarks, including ERQA, PhysBench, SimplerEnv-WidowX, LIBERO, and RoboCasa, PhysBrain 1.0 achieves SOTA results and shows especially strong out-of-domain performance on SimplerEnv. These results suggest that scaling physical commonsense from human interaction video can provide an effective bridge from multimodal understanding to robot action.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15298</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining</title>
      <link>https://arxiv.org/abs/2605.14747</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14747.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Weimin Xiong, Shuhao Gu, Bowen Ye, Zihao Yue, Lei Li, Feifan Song, Sujian Li, Hao Tian&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 142&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Recent advances in multimodal large language models have driven growing interest in graphical user interface (GUI) agents, yet their generalization remains constrained by the scarcity of large-scale training data spanning diverse real-world applications. Existing datasets rely heavily on costly manual annotations and are typically confined to narrow domains. To address this challenge, we propose Video2GUI, a fully automated framework that extracts grounded GUI interaction trajectories directly from unlabeled Internet videos. Video2GUI employs a coarse-to-fine filtering strategy to identify high-quality GUI tutorial videos and convert them into structured agent trajectories. Applying this pipeline to 500 million video metadata entries, we construct WildGUI, a large-scale dataset containing 12 million interaction trajectories spanning over 1,500 applications and websites. Pre-training Qwen2.5-VL and Mimo-VL on WildGUI yields consistent improvements of 5-20% across multiple GUI grounding and action benchmarks, matching or surpassing state-of-the-art performance. We will release both the WildGUI dataset and the Video2GUI pipeline to support future research of GUI agents.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.14747</guid>
      <pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage</title>
      <link>https://arxiv.org/abs/2605.15597</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15597.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jiale Liu, Jungang Li, Jieming Yu, Xinglin Yu, Zihao Dongfang, Zongjian Ding, Kaifeng Ding, Yi Yang, Lidong Chen, Yang Zou, Shunwen Bai, Jiahuan Zhang, Haoran Huang, Shan Huang, Yudong Gao, Mingjun Cheng&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 11&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Modern 3D visual learning relies on observations sampled from metric 3D assets, yet existing scans, meshes, point clouds, simulations, and reconstructions do not directly provide a sparse, comparable, and geometry-consistent panoramic training interface. Dense trajectories duplicate nearby views, source-specific rendering policies yield heterogeneous annotations, and sparse heuristics may miss important regions or introduce depth-inconsistent observations. We study how to convert 3D assets into sparse panoramic RGB-D-pose data that preserves complete scene coverage with low redundancy and auditable provenance. We propose COVER (Coverage-Oriented Viewpoint curation with ERP Range-depth warping), a training-free ERP viewpoint curator that projects geometry observed from selected views into candidate ERP probes, scores incremental coverage, and penalizes depth conflicts. Under bounded proxy error, its greedy coverage proxy preserves the standard coverage-style approximation behavior up to an additive error term. Using COVER, we build CM-EVS (Coverage-curated Metric ERP View Set), a panoramic RGB-D-pose dataset with 36,373 curated ERP frames from 1,275 indoor scenes across Blender indoor, HM3D, and ScanNet++, complemented by outdoor panoramas from TartanGround and OB3D re-encoded into the same schema. Each frame provides full-sphere RGB, metric range depth, calibrated pose; COVER-produced indoor frames include per-step provenance logs. With a median of only 25 frames per indoor scene, CM-EVS covers all 13 unified room types while maintaining compact scene-level coverage. Experiments show that COVER improves the coverage-conflict trade-off, making CM-EVS a sparse, compact, and auditable RGB-D-pose resource for geometry-consistent panoramic 3D learning.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15597</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Unlocking Dense Metric Depth Estimation in VLMs</title>
      <link>https://arxiv.org/abs/2605.15876</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15876.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Hanxun Yu, Xuan Qu, Yuxin Wang, Jianke Zhu, Lei ke&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 12&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and prevents the recovery of dense geometry. Prior methods either distill geometry from external vision models, introducing error accumulation, or enable direct prediction with inefficient per-pixel query or coarse token-level outputs. In this paper, we propose DepthVLM, a simple yet effective framework that transforms a single VLM into a native dense geometry predictor while preserving its multimodal capability. By attaching a lightweight depth head to the LLM backbone and training under a unified vision-text supervision paradigm with a two-stage schedule, DepthVLM generates full-resolution depth maps alongside language outputs in a single forward pass. We further introduce a unified indoor-outdoor metric depth benchmark in a VLM-compatible format. Experiments show that DepthVLM significantly outperforms existing VLMs with higher inference efficiency, surpasses leading pure vision models, and improves complex 3D spatial reasoning, moving toward a truly unified foundation model. All code and checkpoints will be publicly released.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15876</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control</title>
      <link>https://arxiv.org/abs/2605.15963</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15963.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jingxuan Wei, Xi Bai, Shan Liu, Caijun Jia, Zheng Sun, Xinglong Xu, Siyuan Li, Linzhuang Sun, Bihui Yu, Conghui He, Cheng Tan&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 13&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Large vision-language models have significantly advanced GUI agents, enabling executable interaction across web, mobile, and desktop interfaces. Yet these gains largely rely on a forgiving region-tolerant paradigm, where many nearby pixels inside the same component remain valid. Precise geometric construction breaks this assumption: actions must land on points in continuous canvas space rather than tolerant regions. Because geometric primitives carry ontological dependencies, a local coordinate error can induce cascading topological failures that distort downstream objects and invalidate the final construction. We identify this regime as precision-sensitive GUI tasks, requiring point-level accuracy, geometry-aware verification, and robustness to dependency-driven error propagation. To benchmark it, we introduce PAGE Bench, with 4,906 problems and over 224K process-supervised, pixel-level GUI actions. We further propose PAGER, a topology-aware agent that decomposes construction into dependency-structured planning and pixel-level execution. Pixel-grounded supervised tuning establishes executable action grammar, while precision-aligned reinforcement learning mitigates rollout-induced exposure bias through state-conditioned geometric feedback. Experiments reveal a pronounced Semantic-Execution Gap: general multimodal models can exceed 88% action type accuracy yet remain below 6% task success. PAGER closes this gap, delivering 4.1x higher task success than the strongest evaluated general baseline and raising step success rate from below 9% for GUI-specialized agents to over 62%, establishing a new state of the art for point-precise GUI control.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15963</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design</title>
      <link>https://arxiv.org/abs/2605.15871</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15871.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Alberto Pepe, Chien-Yu Lin, Despoina Magka, Bilge Acun, Yannan Nellie Wu, Anton Protopopov, Carole-Jean Wu, Yoram Bachrach&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 16&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers. We introduce a dual-framework approach: AIRA-Compose for high-level architecture search, and AIRA-Design for low-level mechanistic implementation. AIRA-Compose uses 11 agents to explore fundamental computational primitives under a 24-hour budget. Agents evaluate million-parameter candidates, extrapolating top designs to 350M, 1B, and 3B scales. This yields 14 architectures across two families: AIRAformers (Transformer-based) and AIRAhybrids (Transformer-Mamba). Pre-trained at 1B scale, these consistently outperform Llama 3.2 and Composer-found baselines. On downstream tasks, AIRAformer-D and AIRAhybrid-D improve accuracy by 2.4% and 3.8% over Llama 3.2. Furthermore, AIRA-Compose finds models with highly efficient scaling frontiers: AIRAformer-C scales 54% and 71% faster than Llama 3.2 and Composer's best Transformer, while AIRAhybrid-C outscales Nemotron-2 by 23% and Composer's best hybrid by 37%. AIRA-Design tasks 20 agents with writing novel attention mechanisms for long-range dependencies and high-performing training scripts. On the Long Range Arena benchmark, agent-designed architectures reach within 2.3% and 2.6% of human state-of-the-art on document matching and text classification. On the Autoresearch benchmark, Greedy Opus 4.5 achieves 0.968 validation bits-per-byte under a fixed time budget, surpassing the published minimum. Together, these frameworks show AI agents can autonomously discover architectures and algorithmic optimizations matching or surpassing hand-designed baselines. This establishes a powerful paradigm for discovering next-generation foundation models, marking a clear step toward recursive self-improvement.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15871</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs</title>
      <link>https://arxiv.org/abs/2605.15565</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15565.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Haizhong Zheng, Yizhuo Di, Jiahui Wang, Shuowei Jin, Xueshen Liu, Yongji Wu, Z. Morley Mao, Ion Stoica, Jiawei Zhao, Beidi Chen&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 16&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL remains prohibitively expensive. Scaling RL to agentic LLMs requires supporting complex workloads, including multi-policy collaborative training, while efficiently using elastic, heterogeneous, and cross-region compute resources. Existing LLM RL systems support some of these capabilities, but each new extension often requires dedicated system engineering. This burden arises from trainer-centered control architectures and the lack of principled abstractions for RL system components. To address these limitations, we propose AstraFlow, a dataflow-oriented RL system that replaces conventional trainer-centered control with principled component abstractions. In AstraFlow, rollout services, dataflow management, and training are decoupled into autonomous components, enabling the system to natively support complex multi-policy agentic RL workloads and efficiently exploit diverse compute resources. We evaluate AstraFlow across math, code, search, and AgentBench workloads, showing that the same system supports multi-policy training, elastic scaling, heterogeneous cross-region execution, and composable data algorithms without system-level code changes. In multi-policy collaborative training, AstraFlow achieves comparable or better accuracy than existing RL systems while speeding up training time by 2.7x.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15565</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Measuring Maximum Activations in Open Large Language Models</title>
      <link>https://arxiv.org/abs/2605.15572</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15572.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Luxuan Chen, Han Tian, Xinran Chen, Rui Kong, Fang Wang, Jiamin Chen, Yuchen Li, Jiashu Zhao, Shuaiqiang Wang, Haoyi Xiong, Dawei Yin&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 18&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characterized outlier features and massive activations on pre-2024 LLaMA-style models, and the downstream activation-quantization stack inherits that picture without revisiting it for the post-LLaMA open-model boom. We ask the deployment-oriented question: how large can activations get in modern open LLMs, and how does this magnitude vary across families, generations, and training stages? Under a unified pipeline (5,000-sample multi-domain corpus, family-specific tokenization, identical hooks across embeddings, hidden states, attention, MLP/MoE, SwiGLU gates, and final norm), we measure global and layerwise maxima on 27 checkpoints from 8 open families spanning dense, MoE, vision-language, intermediate-training, and instruction-tuned variants. We find that (i) global maxima span over nearly four orders of magnitude at comparable parameter counts, with Qwen3.5 and MoE checkpoints in the 10^2 to 10^3 range and Gemma3-27B-it reaching ~7 x 10^5; (ii) cross-family and cross-generation comparisons break simple monotonic scaling; and (iii) MoE checkpoints exhibit 14.0-23.4x lower peaks than matched-scale dense counterparts, while the residual stream carries the global maximum in 22/24 checkpoints. A lightweight INT-8 sanity check shows that measured maxima co-vary with low-bit reconstruction error via activation-scale selection. We conclude that maximum activation magnitude is a model property tied to family, architecture, and training stage - not a simple byproduct of size - and should be measured and reported alongside any open-weight release before low-bit deployment. The code is publicly available at https://github.com/clx1415926/Max_act_llm.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15572</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation</title>
      <link>https://arxiv.org/abs/2605.16079</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.16079.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yiming Zhao, Yu Zeng, Wenxuan Huang, Zhen Fang, Qing Miao, Qisheng Su, Jiawei Zhao, Jiayin Cai, Lin Chen, Zehui Chen, Yukun Qi, Yao Hu, Xiaolong Jiang, Feng Zhao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 27&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring precise spatiotemporal localization at the instance level. Existing methods primarily rely on text prompts for human-model interaction, but these prompts struggle to provide precise spatial and temporal references, resulting in poor user experience. Furthermore, current approaches typically decouple visual perception from language reasoning, centering reasoning around language rather than visual content, which limits the model's ability to proactively perceive fine-grained visual evidence. To address these challenges, we propose VideoSeeker, a novel paradigm for instance-level video understanding through visual prompts. VideoSeeker seamlessly integrates agentic reasoning with instance-level video understanding tasks, enabling the model to proactively perceive and retrieve relevant video segments on demand. We construct a four-stage fully automated data synthesis pipeline to efficiently generate large-scale, high-quality instance-level video data. We internalize tool-calling and proactive perception capabilities into the model via cold-start supervision and RL training, building a powerful video understanding model. Experiments demonstrate that our model achieves an average improvement of +13.7% over baselines on instance-level video understanding tasks, surpassing powerful closed-source models such as GPT-4o and Gemini-2.5-Pro, while also showing effective transferability on general video understanding benchmarks. The relevant datasets and code will be released publicly.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.16079</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR</title>
      <link>https://arxiv.org/abs/2605.15726</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15726.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Chanuk Lee, Sangwoo Park, Minki Kang, Sung Ju Hwang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 33&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Reinforcement learning with verifiable rewards (RLVR) has emerged as a scalable paradigm for improving the reasoning capabilities of large language models. However, its effectiveness is fundamentally limited by exploration: the policy can only improve on trajectories it has already sampled. While increasing the number of rollouts alleviates this issue, such brute-force scaling is computationally expensive, and existing approaches that modify the optimization objective provide limited control over what is explored. In this work, we propose NudgeRL, a framework for structured and diversity-driven exploration in RLVR. Our approach introduces Strategy Nudging, which conditions each rollout on lightweight, strategy-level contexts to induce diverse reasoning trajectories without relying on expensive oracle supervision. To effectively learn from such structured exploration, we further propose a unified objective, which decomposes the reward signal into inter- and intra-context components and incorporates a distillation objective to transfer discovered behaviors back to the base policy. Empirically, NudgeRL outperforms standard GRPO with up to 8 times larger rollout budgets, while outperforming oracle-guided RL baseline on average across five challenging math benchmarks. These results demonstrate that structured, context-driven exploration can serve as an efficient and scalable alternative to both brute-force rollout scaling and feasibility-oriented methods based on privileged information. Our code is available at https://github.com/tally0818/NudgeRL.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15726</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization</title>
      <link>https://arxiv.org/abs/2605.15980</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15980.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Xiaoxuan He, Siming Fu, Zeyue Xue, Weijie Wang, Ruizhe He, Yuming Li, Dacheng Yin, Shuai Dong, Haoyang Huang, Hongfa Wang, Nan Duan, Bohan Zhuang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 36&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days per experiment. Existing efficiency methods reduce costs through sliding window subsampling training timesteps, but fundamentally compromise optimization, exhibiting severe instability and failing to reach full trajectory performance. We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets while substantially improving training efficiency. Flash-GRPO addresses two critical challenges: iso-temporal grouping eliminates timestep-confounded variance by enforcing prompt-wise temporal consistency, decoupling policy performance from timestep difficulty; temporal gradient rectification neutralizes the time-dependent scaling factor that causes vastly inconsistent gradient magnitudes across timesteps. Experiments on 1.3B to 14B parameter models validate Flash-GRPO's effectiveness, demonstrating substantial training acceleration with consistent stability and state-of-the-art alignment quality.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15980</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo</title>
      <link>https://arxiv.org/abs/2605.16257</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.16257.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Hanwen Wang, Weizhi Zhao, Xiangyu Wang, Siyuan Huang, He Lin, Boyuan Zheng, Rongtao Xu, Gang Wang, Yao Mu, He Wang, Lue Fan, Hongsheng Li, Zhaoxiang Zhang, Tieniu Tan&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 50&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Achieving human-level manipulation requires dexterous robotic hands capable of complex object interactions. Advancing such capabilities further demands standardized benchmarks for systematic evaluation. However, existing dexterous benchmarks lack tasks that reflect the unique manipulation capabilities of dexterous hands over parallel grippers, as well as comprehensive evaluation pipelines. In this paper, we present DexJoCo, a benchmark and toolkit for task-oriented dexterous manipulation, comprising 11 functionally grounded tasks that evaluate tool-use, bimanual coordination, long-horizon execution, and reasoning. We develop a low-cost data collection system and collect 1.1K trajectories across these tasks, with support for domain randomization to assess robustness. We benchmark modern models under diverse settings, including visual and dynamics randomization, multi-task training, and action-head adaptation. Through extensive empirical analysis, we identify several important insights and common limitations of current policies in dexterous manipulation, highlighting key challenges for future research in dexterous hand robot learning. Project page available at: https://dexjoco.github.io&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.16257</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?</title>
      <link>https://arxiv.org/abs/2605.16679</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.16679.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Haolin Chen, Deon Metelski, Leon Qi, Tao Xia, Joonyul Lee, Steve Brown, Kevin Riley, Frank Wang, T. Y. Alvin Liu, Hank Capps MD, Zeyu Tang, Xiangchen Song, Lingjing Kong, Fan Feng, Tianyi Zeng, Zhiwei Liu, Zixian Ma, Hang Jiang, Fangli Geng, Yuan Yuan, Chenyu You, Qingsong Wen, Hua Wei, Yanjie Fu, Yue Zhao, Carl Yang, Biwei Huang, Kun Zhang, Caiming Xiong, Sanmi Koyejo, Eric P. Xing, Philip S. Yu, Weiran Yao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 51&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density, decisions must be grounded in a large library of medical, insurance, and operational rules; Multi-role composition: a single task requires the agent to play multiple roles with handoffs; and multilateral interaction: intermediate workflow steps are multi-turn dialogs, such as peer-to-peer review and patient outreach. We introduce χ-Bench, a benchmark of long-horizon healthcare workflows across three domains: provider prior authorization, payer utilization management, and care management. Each task hands the agent a clinical case in a high-fidelity simulator of 20 healthcare apps exposed via 87 MCP tools, which it must drive to a terminal status through tool calls and writing the role's artifacts, guided by a 1,290+ document managed-care operations handbook skill. Across 30 agent harness/models configurations, the best agent resolves only 28.0% of tasks, no agent clears 20% on strict pass^3, and executing all tasks in a single session slumps the performance to 3.8%. These results raise the hypothesis that similar gaps are likely to surface in other policy-dense, role-composed, irreversible enterprise domains.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.16679</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Process Rewards with Learned Reliability</title>
      <link>https://arxiv.org/abs/2605.15529</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15529.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jinyuan Li, Langlin Huang, Chengsong Huang, Shaoyang Xu, Donghong Cai, Yuyi Yang, Wenxuan Zhang, Jiaxin Huang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 51&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Process Reward Models (PRMs) provide step-level feedback for reasoning, but current PRMs usually output only a single reward score for each step. Downstream methods must therefore treat imperfect step-level reward predictions as reliable decision signals, with no indication of when these predictions should be trusted. We propose BetaPRM, a distributional PRM that predicts both a step-level success probability and the reliability of that prediction. Given step-success supervision from Monte Carlo continuations, BetaPRM learns a Beta belief that explains the observed number of successful continuations through a Beta-Binomial likelihood, rather than regressing to the finite-sample success ratio as a point target. This learned reliability signal indicates when a step reward should be trusted, enabling downstream applications to distinguish reliable rewards from uncertain ones. As one application, we introduce Adaptive Computation Allocation (ACA) for PRM-guided Best-of-N reasoning. ACA uses the learned reliability signal to stop when a high-reward solution is reliable and to spend additional computation on uncertain candidate prefixes. Experiments across four backbones and four reasoning benchmarks show that BetaPRM improves PRM-guided Best-of-N selection while preserving standard step-level error detection. Built on this signal, ACA improves the accuracy--token tradeoff over fixed-budget Best-of-16, reducing token usage by up to 33.57% while improving final-answer accuracy.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15529</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization</title>
      <link>https://arxiv.org/abs/2605.15824</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15824.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Quanjian Song, Yefeng Shen, Mengting Chen, Hao Sun, Jinsong Lan, Xiaoyong Zhu, Bo Zheng, Liujuan Cao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 60&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Human-centric video customization, particularly at the garment level, has shown significant commercial value. However, existing approaches cannot support low-latency and interactive garment control, which is crucial for applications such as e-commerce and content creation. This paper studies how to achieve interactive multi-garment video customization while preserving motion coherence using only single-garment video data. We present FashionChameleon, a real-time and interactive framework for human-garment customization in autoregressive video generation, where users can interactively switch garment during generation. FashionChameleon consists of three key techniques: (i) Instead of training on multi-garment video data, we train a Teacher Model with In-Context Learning on a single reference-garment pair. By retaining the image-to-video training paradigm while enforcing a mismatch between the reference and garment image, the model is encouraged to implicitly preserve coherence during single-garment switching. (ii) To achieve consistency and efficiency during generation, we introduce Streaming Distillation with In-Context Learning, which fine-tunes the model with in-context teacher forcing and improves extrapolation consistency via gradient-reweighted distribution matching distillation. (iii) To extend the model for interactive multi-garment video customization, we propose Training-Free KV Cache Rescheduling, which includes garment KV refresh, historical KV withdraw, and reference KV disentangle to achieve garment switching while preserving motion coherence. Our FashionChameleon uniquely supports interactive customization and consistent long-video extrapolation, while achieving real-time generation at 23.8 FPS on a single GPU, 30-180times faster than existing baselines.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.15824</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Active Learners as Efficient PRP Rerankers</title>
      <link>https://arxiv.org/abs/2605.14236</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14236.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jeremías Figueiredo Paschmann, Juan Kaplan, Francisco Nattero, Santiago Barron, Juan Wisznia, Luciano del Corro&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 95&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Pairwise Ranking Prompting (PRP) elicits pairwise preference judgments from an LLM, which are then aggregated into a ranking, usually via classical sorting algorithms. However, judgments are noisy, order-sensitive, and sometimes intransitive, so sorting assumptions do not match the setting. Because sorting aims to recover a full permutation, truncating it to meet a call budget does not produce a dependable top-K. We thus reframe PRP reranking as active learning from noisy pairwise comparisons and show that active rankers are drop-in replacements that improve NDCG@10 per call in the call-constrained regime. Our noise-robust framework also introduces a randomized-direction oracle that uses a single LLM call per pair. This approach converts systematic position bias into zero-mean noise, enabling unbiased aggregate ranking without the cost of bidirectional calls.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.14236</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection</title>
      <link>https://arxiv.org/abs/2605.16839</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.16839.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jiwon Song, Dongwon Jo, Beomseok Kang, Jae-Joon Kim&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 12&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Chunked prefill has become a widely adopted serving strategy for long-context large language models, but efficient attention computation in this regime remains challenging. Existing sparse attention methods are primarily designed for one-shot prefill and do not translate efficiently to chunked prefill: block-sparse kernels lose efficiency when the query length is limited by the chunk size, while fine-grained pattern search becomes costly when repeated over the accumulated KV cache at every chunk. QUOKA, a recent method that directly targets chunked prefill, avoids sparse-kernel overhead but relies on query-subsampled, token-level KV selection, which can miss query-specific KV entries and introduce explicit KV-copy overhead. To address these limitations, we propose CompactAttention, a chunked-prefill attention mechanism based on Block-Union KV Selection. CompactAttention treats 2D block-sparse masks as KV-selection signals rather than direct sparse-kernel execution plans, and converts them into GQA-aware per-group KV block tables through Q-block union and intra-group union. This construction produces the minimal block tables that preserve all KV blocks selected by the input masks under paged execution constraints, enabling selected KV blocks to be accessed in place without explicit KV compaction. On LLaMA-3.1-8B-Instruct, CompactAttention maintains accuracy close to dense attention on the RULER benchmark while delivering up to 2.72times attention speedup at 128K context length under chunked prefill.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.16839</guid>
      <pubDate>Sat, 16 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps</title>
      <link>https://arxiv.org/abs/2605.16928</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.16928.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yanke Zhou, Yiduo Li, Hanlin Tang, Maohua Li, Kan Liu, Lan Tao, Lin Qu, Yuan Yao, Xiaoxing Ma&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 85&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely either on native sparse training or on heuristic token eviction, creating an undesirable trade-off among efficiency, training cost, and accuracy. In this work, we show that full-attention LLMs are already intrinsically sparse and can be transformed into highly sparse models with only minimal adaptation. Our approach is built on three observations: (1) only a small subset of attention heads truly requires full long-context processing; (2) long-range retrieval is governed primarily by a low-dimensional subspace, allowing relevant tokens to be retrieved efficiently with a 16-dimensional indexer; and (3) the useful token budget is strongly query-dependent, making dynamic top-p selection more suitable than fixed top-k sparsification. Based on these insights, we propose RTPurbo, which retains the full KV cache only for retrieval heads and introduces a lightweight token indexer for sparse attention. By exploiting the model's intrinsic sparsity, RTPurbo achieves sparsification with only a few hundred training steps. Experiments on long-context benchmarks and reasoning tasks show that RTPurbo preserves near-lossless accuracy while delivering substantial efficiency gains, including up to a 9.36times prefill speedup at 1M context and about a 2.01times decode speedup. These results suggest that strong sparse inference can be obtained from standard full-attention training without expensive native sparse pretraining.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.16928</guid>
      <pubDate>Sat, 16 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements</title>
      <link>https://arxiv.org/abs/2605.17242</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.17242.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yuxuan Wan, Tingshuo Liang, Jiakai Xu, Jingyu Xiao, Yintong Huo, Michael R Lyu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 12&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Coding agents can generate web applications from natural-language descriptions, yet a recent benchmark study shows that generated applications fail to meet functional requirements in over 70% of cases. The core difficulty is that web correctness cannot be assessed from source files or terminal output: the application must be deployed, exercised through simulated browser interactions, and failures must be translated into actionable repair signals -- steps that current agents cannot perform without human mediation.   We present TDDev, a framework that automates this closed loop through three stages: (1) converting high-level requirements into structured acceptance tests before any code is written, (2) deploying the application and validating it through browser-based interaction simulation, and (3) translating browser-observed failures into structured repair reports for the coding agent. Enabled by TDDev, we conduct the first controlled empirical study of Test-driven development (TDD) strategies for web application generation, comparing four development protocols across two coding agents, two backbone models, and two benchmarks. TDD infrastructure consistently improves generation quality by 34--48 percentage points over a no-TDD baseline. The central finding is that the optimal protocol depends on the model's generation style: models that build applications holistically benefit most from agentic enforcement, while models that extend code conservatively benefit from incremental enforcement. Mismatching protocol to generation style eliminates the TDD benefit entirely while multiplying token cost up to 25-fold. A user study confirms that TDDev reduces manual developer intervention to zero, shifting the workload from continuous prompt engineering to autonomous, feedback-driven refinement.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.17242</guid>
      <pubDate>Sun, 17 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models</title>
      <link>https://arxiv.org/abs/2605.17672</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.17672.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Dehai Min, Giovanni Vaccarino, Huiyi Chen, Yongliang Wu, Gal Yona, Lu Cheng&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 22&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Large Reasoning Models (LRMs) achieve strong performance by generating long chains of thought (CoT), but often overthink, continuing to reason after a solution has already stabilized and thereby wasting tokens and increasing latency. Existing inference-time early-exit methods rely primarily on answer-level signals, such as confidence or trial-answer consistency, to decide when to stop. However, these signals mainly reflect answer readiness rather than reasoning convergence: they may trigger before the model has finished exploring or self-correcting, causing premature exits that can degrade final-answer accuracy and leave the retained reasoning chain semantically incomplete. We identify reasoning-level semantic redundancy as a complementary signal for semantic-preserving early exit: when successive steps no longer add novel progress and instead revisit established conclusions, the reasoning trajectory has likely converged. Building on this insight, we propose PUMA, a plug-and-play framework that combines a lightweight Redundancy Detector with answer-level verification. The detector flags semantically redundant candidate exits, while verification confirms whether stopping is safe, allowing PUMA to remove redundant continuation while preserving both answer accuracy and a coherent reasoning prefix. Across five LRMs and five challenging reasoning benchmarks, PUMA achieves 26.2% average token reduction while preserving accuracy and retained CoT quality. Additional experiments on code generation, zero-shot vision-language reasoning, and learned stopping-policy internalization further demonstrate that reasoning-level redundancy is a robust, transferable, and learnable signal for efficient reasoning. Our code is available at https://github.com/giovanni-vaccarino/PUMA.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.17672</guid>
      <pubDate>Sun, 17 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs</title>
      <link>https://arxiv.org/abs/2605.17260</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.17260.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jihwan Kim, Nikhil Parthasarathy, Danfeng Qin, Junhwa Hur, Deqing Sun, Bohyung Han, Ming-Hsuan Yang, Boqing Gong&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 24&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; The fundamental challenge in scaling Video Large Language Models (Video LLMs) to long-form video lies in managing the explosion of visual-token context length. Existing strategies predominantly focus on "post-hoc" token reduction -- reducing visual tokens after feature extraction to alleviate the LLM's computational overhead. While these methods effectively reduce the number of visual tokens, we observe that the primary latency bottleneck then shifts from the LLM to the expensive per-frame processing of the vision encoder. To address this, we introduce LiteFrame, a strong, yet highly efficient video encoder backbone for Video LLMs. To train LiteFrame, we propose Compressed Token Distillation (CTD), a novel training framework that teaches a compact student vision encoder to directly predict information-dense, spatio-temporally compressed representations produced by a large teacher vision model, effectively bypassing redundant computation. When coupled with further Language Model Adaptation (LMA), this approach results in a new latency-accuracy Pareto frontier -- compared with InternVL3-8B, LiteFrame provides a 35% reduction in end-to-end latency while processing 8times more frames and improves average video understanding accuracy across multiple benchmarks. Our results demonstrate a new potential path to unlocking longer-form video understanding under fixed compute budgets.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.17260</guid>
      <pubDate>Sun, 17 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>OProver: A Unified Framework for Agentic Formal Theorem Proving</title>
      <link>https://arxiv.org/abs/2605.17283</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.17283.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; David Ma, Kaijing Ma, Shawn Guo, Yunfeng Shi, Enduo Zhao, Jiajun Shi, Zhaoxiang Zhang, Gavin Cheung, Jiaheng Liu, Zili Wang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 30&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Recent progress in formal theorem proving has benefited from large-scale proof generation and verifier-aware training, but agentic proving is rarely integrated into prover training, appearing only at inference time. We present OProver, a unified framework for agentic formal theorem proving in Lean 4, in which failed proof attempts are iteratively revised using retrieved compiler verified proofs and Lean compiler feedback. OProver is trained through continued pretraining followed by iterative post-training: each iteration runs agentic proving, indexes newly verified proofs into OProofs and the retrieval memory, uses repair trajectories as SFT data, and uses unresolved hard cases for RL. OProofs is built from public Lean resources, large-scale proof synthesis, and agentic proving traces, containing 1.77M Lean statements, 6.86M compiler-verified proofs, and serialized trajectories with retrieved context, failed attempts, feedback, and repairs. Across five benchmarks, OProver-32B attains the best Pass@32 on MiniF2F (93.3%), ProverBench (58.2%), and PutnamBench (11.3%), and ranks second on MathOlympiad (22.8%) and ProofNet (33.2%) more top placements than any prior open-weight whole-proof prover.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.17283</guid>
      <pubDate>Sun, 17 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Semantic Generative Tuning for Unified Multimodal Models</title>
      <link>https://arxiv.org/abs/2605.18714</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18714.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Songsong Yu, Yuxin Chen, Ying Shan, Yanwei Li&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 10&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture. However, prevailing training paradigms independently optimize understanding via sparse text signals and generation through dense pixel objectives. Such a decoupled strategy yields misaligned representation spaces, isolating visual understanding from generation and hindering their mutual reinforcement. This work presents the first systematic investigation into generative post-training, where we formulate hierarchical visual tasks as generative proxies to bridge the isolation in UMMs. Our empirical investigation reveals that high-level semantic tasks, particularly image segmentation, serve as optimal proxies. Unlike low-level tasks that distract models with texture details, segmentation provides structural semantics that significantly enhance both vision-centric perception and generative layout fidelity. Building upon these insights, we introduce Semantic Generative Tuning (SGT), a novel paradigm that leverages segmentation as a generative proxy to align and synergize multimodal capabilities. Mechanistic analyses further demonstrate that SGT fundamentally improves feature linear separability and optimizes visual-textual attention allocation pattern. Extensive evaluations show that SGT consistently improves both multimodal comprehension and generative fidelity across mainstream benchmarks. Our code is available on the https://song2yu.github.io/SGT/.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18714</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Forecasting Downstream Performance of LLMs With Proxy Metrics</title>
      <link>https://arxiv.org/abs/2605.18607</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18607.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Arkil Patel, Siva Reddy, Marius Mosbach, Dzmitry Bahdanau&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 10&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Progress in language model development is often driven by comparative decisions: which architecture to adopt, which pretraining corpus to use, or which training recipe to apply. Making these decisions well requires reliable performance forecasts, yet the two commonly used signals are fundamentally limited. Cross-entropy loss is poorly aligned with downstream capabilities, and direct downstream evaluation is expensive, sparse, and often uninformative at early training stages. Instead, we propose to construct proxy metrics by aggregating token-level statistics, such as entropy, top-k accuracy, and expert token rank, from a candidate model's next token distribution over expert-written solutions. Across three settings, our proxies consistently outperform loss- and compute-based baselines: 1) For cross-family model selection, they rank a heterogeneous population of reasoning models with mean Spearman Rho = 0.81 (vs. Rho = 0.36 for cross-entropy loss); 2) For pretraining data selection, they reliably rank 25 candidate corpora for a target model at roughly 10{,}000times less compute than direct evaluation, pushing the Pareto frontier beyond existing methods; and 3) for training-time forecasting, they extrapolate downstream accuracy across an 18times compute horizon with roughly half the error of existing alternatives. Together, these results suggest that expert trajectories are a broadly useful source of signal for assessing model capabilities, enabling reliable performance forecasting throughout the model development life cycle.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18607</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>SENSE: Satellite-based ENergy Synthesis for Sustainable Environment</title>
      <link>https://arxiv.org/abs/2605.18101</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18101.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Kailai Sun, Mingyi He, Heye Huang, Can Rong, Alok Prakash, Baoshen Guo, Shenhao Wang, Jinhua Zhao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 11&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Urban Building Energy Modeling plays a critical role in achieving the United Nations' Sustainable Development Goals 7 and 11. Although existing studies based on satellite imagery and deep learning have achieved remarkable progress, many challenges exist: most existing studies are inherently predictive, failing to reflect the generative nature of urban planning; although generative AI and diffusion models have seen explosive growth in satellite imagery, they lack the urban functional generation (e.g., energy layer); third, aligned high-quality high-resolution building energy data with satellite imagery is limited and scarce. Here we propose SENSE (Satellite-based ENergy Synthesis for Sustainable Environment), a unified generative UBEM framework that jointly synthesizes realistic urban satellite imagery and aligned high-quality building energy consumption and height maps. By conditioning on road networks and urban density metrics, SENSE, based on a controllable diffusion model, leverages the knowledge learned by large vision models to generate urban building energy consumption and height information (annotations) in the latent space. Experiments across four cities (New York City, Boston, Lyon, Busan) demonstrate that SENSE achieves high visual fidelity and strong physical consistency, satisfying the ASHRAE standard metric. Experiments demonstrate that SENSE can generate enough annotated synthetic data using less than 20% labeled energy data, boosting downstream prediction performance by 10% IoU. Compared to SOTA urban energy prediction methods, SENSE significantly reduced prediction error (reduced 3%-11% NMBE and 1%-9% CVRMSE). This study offers an energy-efficiency urban planning and physical generation solution for urban science, energy science and building science. The dataset and code: https://huggingface.co/datasets/skl24/MUSE and https://github.com/kailaisun/GenAI4Urban-Energy/.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18101</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Interactive Evaluation Requires a Design Science</title>
      <link>https://arxiv.org/abs/2605.17829</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.17829.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Keyang Xuan, Peiyang Song, Pan Lu, Pengrui Han, Wenkai Li, Zhenyu Zhang, Zexue He, Wenyue Hua, Manling Li, Jiaxuan You, Adrian Weller, Yizhong Wang, Jiaxin Pei&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 14&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; AI evaluation is undergoing a structural change. Large language models (LLMs) are increasingly deployed as systems that act over time through tools, environments, users, and other agents, while many evaluation practices still inherit assumptions from response-centered benchmarks (e.g., fixed inputs, isolated outputs, and outcome judgments that can be made from a single response). The field has begun to build interactive benchmarks, but the resulting landscape is fragmented: benchmarks differ in what interaction artifacts they admit, how trajectories are scored, and what claims their results support. This position paper argues that interactive evaluation should be treated as a principled evaluation paradigm, not merely a new family of agent benchmarks. Simply adopting previous evaluation paradigms does not suffice. We define evaluation as an autonomous mapping from evidence to judgments, and show that interactive evaluation changes both sides of this mapping: the evidence becomes interaction-generated trajectories, while the evaluation procedure must assess process, recoverability, coordination, robustness, and system-level performance. Building on this definition, we propose a two-axis taxonomy, derive design principles and reporting standards, examine representative scenarios, and analyze how longstanding evaluation challenges reappear at the trajectory level.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.17829</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>StableVLA: Towards Robust Vision-Language-Action Models without Extra Data</title>
      <link>https://arxiv.org/abs/2605.18287</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18287.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yiyang Fu, Chubin Zhang, Shukai Gong, Yufan Deng, Kaiwei Sun, Qiyang Min, Qibin Hou, Yansong Tang, Jianan Wang, Daquan Zhou&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 15&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; It is infeasible to encompass all possible disturbances within the training dataset. This raises a critical question regarding the robustness of Vision-Language-Action (VLA) models when encountering unseen real-world visual disturbances, particularly under imperfect visual conditions. In this work, we conduct a systematic study based on recent state-of-the-art VLA models and reveal a significant performance drop when visual disturbances absent from the training data are introduced. To mitigate this issue, we propose a lightweight adapter module grounded in information theory, termed the Information Bottleneck Adapter (IB-Adapter), which selectively filters potential noise from visual inputs. Without requiring any extra data or augmentation strategies, IB-Adapter consistently improves over the baseline by an average of 30%, while adding fewer than 10M parameters, demonstrating notable efficiency and effectiveness. Furthermore, even with a 14x smaller backbone (0.5B parameters) and no pre-training on the Open X-Embodiment dataset, our model StableVLA achieves robustness competitive with 7B-scale state-of-the-art VLAs. With negligible parameter overhead (&lt;10M), our approach maintains accuracy on long-horizon tasks and surpasses OpenPi under both synthetic and physical visual corruptions.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18287</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos</title>
      <link>https://arxiv.org/abs/2605.18984</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18984.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yuqi Tang, Yang Shi, Zhuoran Zhang, Qixun Wang, Xuehai Bai, Yue Ding, Ruizhe Chen, Bohan Zeng, Xinlong Chen, Xuanyu Zhu, Bozhou Li, Yuran Wang, Yifan Dai, Chengzhuo Tong, Xinyu Liu, Yiyan Ji, Yujie Wei, Yuhao Dong, Shilin Yan, Fengxiang Wang, Yi-Fan Zhang, Haotian Wang, Yuanxing Zhang, Pengfei Wan&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 22&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Recent video generative models have greatly improved the realism of AI-generated videos, yet their outputs still exhibit artifacts such as temporal inconsistencies, structural distortions, and semantic incoherence. While Multimodal Large Language Models (MLLMs) show strong visual understanding capabilities, their ability to perceive and reason about such artifacts remains unclear. Existing benchmarks often lack systematic evaluation of artifact-aware perception and fine-grained diagnostic reasoning, especially across diverse AI-generated video domains beyond photorealistic content. To address this gap, we introduce Artifact-Bench, a comprehensive benchmark for evaluating MLLMs on AI-generated video artifact detection and analysis. We first establish a three-level hierarchical taxonomy of realism artifacts, covering photorealistic, animated, and CG-style videos. Based on this taxonomy, Artifact-Bench defines three complementary tasks: real vs. AI-generated video classification, pairwise realism comparison, and fine-grained artifact identification. Experiments on 19 leading MLLMs reveal substantial limitations in artifact perception and reasoning, with many models approaching random or even below-random performance in challenging settings. We further observe significant misalignment between MLLM judgments and human perceptual preferences, highlighting their limited reliability as general evaluators for AI-generated video realism.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18984</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Aurora: Unified Video Editing with a Tool-Using Agent</title>
      <link>https://arxiv.org/abs/2605.18748</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18748.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yongsheng Yu, Ziyun Zeng, Zhiyuan Xiao, Zhenghong Zhou, Hang Hua, Wei Xiong, Jiebo Luo&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 29&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and reference images, and one set of weights covers replacement, removal, style transfer, and reference-driven insertion. The design is flexible, but it assumes that the user already provides model-ready text, reference images, and spatial grounding for local edits, which real requests often omit. We present Aurora, an agentic video editing framework that pairs a tool-augmented vision-language model (VLM) agent with a unified video diffusion transformer. The VLM agent maps a raw user request to a structured edit plan aligned with the transformer's conditioning channels, thereby resolving textual and visual underspecification before generation. We train the VLM agent with supervised data for complete edit planning and reference-image selection, together with preference pairs for robust tool use and instruction refinement. We introduce AgentEdit-Bench to evaluate agent-enhanced video editing under textual and visual underspecification. Experiments on AgentEdit-Bench and two existing video editing benchmarks show that Aurora improves over instruction-only baselines and that the VLM agent transfers to compatible frozen video editing models. Project page: https://yeates.github.io/Aurora-Page&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18748</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs</title>
      <link>https://arxiv.org/abs/2605.20258</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20258.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Sangwoo Park, Woongyeong Yeo, Seanie Lee, Yumin Choi, Hyomin Lee, Kangsan Kim, Jinheon Baek, Seong Joon Oh, Sung Ju Hwang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 29&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language models are increasingly deployed as personal agents handling sensitive workflows, adhering to CI becomes critical. However, even frontier models remain unreliable in making disclosure decisions, and existing mitigation strategies often degrade underlying task performance. To overcome this privacy-utility trade-off, we propose SELFCI, a complementary self-distillation framework that decouples information suppression from task resolution. SELFCI jointly optimizes two independent reverse KL divergences over distinct teacher distributions derived from feedback: one encourages preserving task-relevant information for utility, while the other enforces minimal and appropriate disclosure. This complementary formulation induces a Product-of-Experts (PoE) target, aligning the policy with the intersection of capability and privacy requirements. Empirical evaluations demonstrate that SELFCI, without relying on costly external supervision, consistently outperforms competitive baselines such as online reinforcement learning algorithms (e.g., GRPO). These trends further extend to out-of-domain settings involving agentic workflows and accumulated private context, suggesting that SELFCI provides a practical path toward CI alignment.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20258</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Post-Trained MoE Can Skip Half Experts via Self-Distillation</title>
      <link>https://arxiv.org/abs/2605.18643</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18643.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Xingtai Lv, Li Sheng, Kaiyan Zhang, Yichen You, Siyan Gao, Xueheng Luo, Yuxin Zuo, Yuchen Fan, Junlin Yang, Ganqu Cui, Bingning Wang, Fan Yang, Youbang Sun, Ning Ding, Bowen Zhou&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 30&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by adjusting the activated experts in an input-dependent manner. Existing dynamic MoE methods usually rely on pre-training from scratch or task-specific adaptation, leaving the practical conversion of fully trained MoE underexplored. Enabling such adaptation would directly alleviate the inference costs by allowing easy tokens to bypass unnecessary expert during serving. This paper introduces Zero-Expert Self-Distillation Adaptation (ZEDA), a low-cost framework that transforms post-trained static MoE models into efficient dynamic ones. To stabilize this architectural conversion, ZEDA injects parameter-free zero-output experts into each MoE layer and adapts the augmented model through two-stage self-distillation, utilizing the original MoE as a frozen teacher and applying a group-level balancing loss. On Qwen3-30B-A3B and GLM-4.7-Flash across 11 benchmarks spanning math, code, and instruction following, ZEDA eliminates over 50% of expert FLOPs at marginal accuracy loss. It outperforms the strongest dynamic MoE baseline by 6.1 and 4.0 points on the two models, and delivers ~1.20times end-to-end inference speedup.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18643</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Harnessing LLM Agents with Skill Programs</title>
      <link>https://arxiv.org/abs/2605.17734</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.17734.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Hongjun Liu, Yifei Ming, Shafiq Joty, Chen Zhao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 34&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lessons are often encoded as textual guidance that remains largely advisory, lacking explicit mechanisms for when and how to intervene in the agent loop. To bridge the gap, we introduce HASP(Harnessing LLM Agents with Skill Programs), a new framework that upgrades skills into executable Program Functions (PFs). Rather than offering passive advice, PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context. HASP is highly modular: it can be applied at inference time for direct agent-loop intervention, during post-training to provide structured supervision, or for self-improvement by evolving validated, teacher-reviewed PFs. Empirically, HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks. For example, on web-search reasoning, inference-time PFs alone improve the average performance by 25% compared to (multi-loop) ReAct Agent, while post-training and controlled evolution achieve a 30.4% gain over Search-R1. To provide deeper insights into HASP, our mechanism analysis reveals how PFs trigger and intervene, how skills are internalized, and the requirement for stable skill library evolution.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.17734</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis</title>
      <link>https://arxiv.org/abs/2605.18451</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18451.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yixuan Yang, Zhen Luo, Wanshui Gan, Jinkun Hao, Junru Lu, Jinghao Yan, Zhaoyang Lyu, Xudong Xu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 40&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Designing realistic and functional 3D indoor rooms is essential for a wide range of applications, including interior design, virtual reality, gaming, and embodied AI. While recent MLLM-based approaches have shown great potential for 3D room synthesis from textual descriptions or reference images, text-based methods struggle to capture precise spatial information, and existing image-conditioned agents suffer from instability and infinite looping when tasked with holistic room generation from top-down views. To address these limitations, we propose Code-as-Room, an MLLM-based agentic framework equipped with a structured execution harness, which represents 3D rooms with Blender codes. Given a top-down room image, the framework parses the reference image to extract scene elements and their spatial relationships, and synthesizes executable Blender code for geometry, materials, and lighting in a principled, multi-stage pipeline. A cross-stage memory module is maintained throughout to mitigate context forgetting inherent to existing agent-based frameworks. We further introduce a dedicated benchmark for code-based 3D room synthesis, encompassing various evaluation protocols. Based on our benchmark, comprehensive comparisons against existing agent-based methods are conducted to validate the effectiveness of our proposed execution harness.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18451</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL</title>
      <link>https://arxiv.org/abs/2605.18703</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18703.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Minrui Xu, Zilin Wang, Mengyi DENG, Zhiwei Li, Zhicheng Yang, Xiao Zhu, Yinhong Liu, Boyu Zhu, Baiyu Huang, Chao Chen, Heyuan Deng, Fei Mi, Lifeng Shang, Xingshan Zeng, Zhijiang Guo&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 48&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and the scarcity of realistic training data that captures implicit human reasoning. Existing approaches depend on costly real-world APIs, hallucination-prone LLM simulators, or synthetic environments that are often single-turn or depend on pre-collected documents. Moreover, synthetic trajectories are frequently over-specified, resembling instruction sequences rather than natural human intents, reducing their effectiveness for RL training. We introduce EnvFactory, a fully automated framework that addresses both challenges. EnvFactory autonomously explores and verifies stateful, executable tool environments from authentic resources, and synthesizes natural multi-turn trajectories through topology-aware sampling and calibrated refinement, producing grounded queries with implicit intents. Using only 85 verified environments across 7 domains, EnvFactory generates 2,575 SFT and RL trajectories. Despite using significantly fewer environments than prior work, which are often 5 times more, EnvFactory achieves superior training efficiency and downstream performance, improving Qwen3-series models by up to +15% on BFCLv3, +8.6% on MCP-Atlas, and +6% on conversational benchmarks including τ^2-Bench and VitaBench. By fully automating both environment construction and trajectory synthesis, EnvFactory provides a scalable, extensible, and robust foundation for Agentic RL.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18703</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook</title>
      <link>https://arxiv.org/abs/2605.20266</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20266.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Kaiwen Luo, Zhenhong Zhou, Leo Wang, Liang Lin, Yang Xiao, Tianyu Shao, Yuanhe Zhang, Yuxuan Li, Miao Yu, Kailin Lyu, Jiaming Zhang, Dongrui Liu, Li Sun, Yueming Wu, Kai Li, Ting Dang, Xiaojun Jia, Rohan Kumar Das, Xinfeng Li, Siyuan Liang, Qiufeng Wang, Xingjun Ma, Jing Chen, Kun Wang, Junhao Dong, Deqing Zou, Yu Cheng, Xia Hu, Zhigang Zeng, Sen Su, Yang Liu, Yu-Gang Jiang, Philip S. Yu, Yew-Soon Ong&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 56&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; The foundational capabilities established by Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs), within which Large Audio Language Models (LALMs) are essential for realizing universal auditory intelligence. Despite their remarkable performance, the escalation of LALMs' capabilities has significantly outpaced the development of systemic frameworks to ensure their trustworthiness. This survey provides a comprehensive investigation into the endogenous mechanisms of LALMs, detailing the architectural innovations and alignment algorithms that facilitate emergent reasoning. Specifically, we analyze how the transition to unified end-to-end frameworks and the integration of continuous acoustic signals inherently expand the attack surface. To rigorously evaluate the risks within these paradigms, we establish a comprehensive taxonomy of trustworthiness, categorizing critical vulnerabilities such as cross-modal jailbreaking, latent acoustic backdoors, and biometric privacy leakage. We review the state-of-the-art through six analytical pillars: hallucination, robustness, safety, privacy, fairness, and authentication. The profound imbalance between a mature offensive landscape and underdeveloped defenses further validates the critical trustworthiness gaps and multidimensional risks facing audio-centric intelligence. Finally, we propose a strategic roadmap advocating for "Defense-in-Depth" architectures, causal auditory world modeling, and intrinsic representation engineering to bridge the gap between empirical performance and intrinsically trustworthy audio intelligence. Our project has been uploaded to GitHub https://github.com/Kwwwww74/Awesome-Trustworthy-AudioLLMs.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20266</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization</title>
      <link>https://arxiv.org/abs/2605.17757</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.17757.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Zhongzhu Zhou, Donglin Zhuang, Jisen Li, Ziyan Chen, Shuaiwen Leon Song, Ben Athiwaratkun, Xiaoxia Wu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 61&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; INT2 KV-cache quantization is attractive for long-context LLM serving, but it remains difficult to make both accurate and deployable. Simple rotations such as Hadamard transforms reduce outliers, but still degrade at INT2 because they are not aligned with downstream attention. We propose OSCAR, an Ultra-low-bit KV Cache quantization method that estimates attention-aware covariance structures offline and uses them to derive fixed rotations and clipping thresholds for quantization. In this way, it aligns KV quantization with the covariance structures that attention actually consumes. More importantly, we not only provide theoretical justification but also develop a fully deployable OSCAR system with a custom INT2 attention kernel that remains compatible with paged KV-cache serving and fused kernel pipelines, enabling seamless integration into modern LLM serving frameworks such as SGLang and vLLM.   We evaluate our methods on recent reasoning models with reasoning traces of up to 32k tokens across 5 tasks. On Qwen3-4B-Thinking-2507 and Qwen3-8B, OSCAR reduces the BF16 accuracy gap to 3.78 and 1.42 points, respectively, while naive rotation INT2 collapses to nearly zero. We further scale OSCAR to Qwen3-32B and GLM-4.7 (358B params), where it remains effectively on par with BF16. On long context - RULER-NIAH up to 128K, OSCAR remains robust on both Qwen3 models, while naive rotation INT2 collapses. System-wise, OSCAR reduces KV-cache memory by approximately 8x, improves throughput by up to 7x at large batch sizes under the same memory budget, and accelerates batch-size-1 decoding by up to 3x over BF16 due to reduced memory bandwidth overhead.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.17757</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>AI for Auto-Research: Roadmap &amp; User Guide</title>
      <link>https://arxiv.org/abs/2605.18661</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18661.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Lingdong Kong, Xian Sun, Wei Chow, Linfeng Li, Kevin Qinghong Lin, Xuan Billy Zhang, Song Wang, Rong Li, Qing Wu, Wei Gao, Yingshuo Wang, Shaoyuan Xie, Jiachen Liu, Leigang Qu, Shijie Li, Lai Xing Ng, Benoit R. Cottereau, Ziwei Liu, Tat-Seng Chua, Wei Tsang Ooi&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 63&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents can execute experiments, draft manuscripts, and simulate critique with minimal human input. Yet this productivity frontier exposes a deeper integrity problem: under scientific pressure, even frontier LLMs still fabricate results, miss hidden errors, and fail to judge novelty reliably. Studying developments through April 2026, we present an end-to-end analysis of AI across the complete research lifecycle, organized into four epistemological phases: Creation (idea generation, literature review, coding &amp; experiments, tables &amp; figures), Writing (paper writing), Validation (peer review, rebuttal &amp; revision), and Dissemination (posters, slides, videos, social media, project pages, and interactive agents). We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy: AI excels at structured, retrieval-grounded, and tool-mediated tasks, but remains fragile for genuinely novel ideas, research-level experiments, and scientific judgment. Generated ideas often degrade after implementation, research code lags far behind pattern-matching benchmarks, and end-to-end autonomous systems have not yet consistently reached major-venue acceptance standards. We further show that greater automation can obscure rather than eliminate failure modes, making human-governed collaboration the most credible deployment paradigm. Finally, we provide a structured taxonomy, benchmark suite, and tool inventory, cross-stage design principles, and a practitioner-oriented playbook, with resources maintained at our project page.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18661</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Lance: Unified Multimodal Modeling by Multi-Task Synergy</title>
      <link>https://arxiv.org/abs/2605.18678</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18678.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Fengyi Fu, Mengqi Huang, Shaojin Wu, Yunsheng Jiang, Yufei Huo, Hao Li, Yinghang Song, Fei Ding, Jianzhu Guo, Qian He, Zheren Fu, Zhendong Mao, Yongdong Zhang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 72&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; We present Lance, a lightweight native unified model supporting multimodal understanding, generation, and editing for both images and videos. Rather than relying on model capacity scaling or text-image-dominant designs, Lance explores a practical paradigm for unified multimodal modeling via collaborative multi-task training. It is grounded in two core principles: unified context modeling and decoupled capability pathways. Specifically, Lance is trained from scratch and employs a dual-stream mixture-of-experts architecture on shared interleaved multimodal sequences, enabling joint context learning while decoupling the pathways for understanding and generation. We further introduce modality-aware rotary positional encoding to mitigate interference among heterogeneous visual tokens and boost cross-task alignment. During training, Lance adopts a staged multi-task training paradigm with capability-oriented objectives and adaptive data scheduling to strengthen both semantic comprehension and visual generation performance. Experimental results demonstrate that Lance substantially outperforms existing open-source unified models in image and video generation, while retaining strong multimodal understanding capabilities. The homepage is available at https://lance-project.github.io.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18678</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos</title>
      <link>https://arxiv.org/abs/2605.18233</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18233.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; X. Feng, J. Zhu, M. Wu, C. Chen, F. Mao, H. Guo, J. Wu, X. Chu, K. Huang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 88&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce longer videos. Frame-level autoregressive frameworks, e.g., FIFO-diffusion, offer the advantage of generating infinitely long videos with constant memory consumption. However, the mismatch between training and inference, coupled with the challenge of maintaining long-term consistency, limits the effective utilization of foundation models. To mitigate these concerns, we propose MIGA, a novel infinite-frame long video generation method. Firstly, we propose an effective two-stage alignment mechanism that mitigates the training-inference gap by reducing the excessive noise span fed to the model. We then introduce an innovative dual consistency enhancement mechanism, where the self-reflection approach corrects early high-noise frames and the long-range frame guidance approach leverages later low-noise frames with broad coverage to steer generation, jointly improving temporal consistency. Extensive experiments on VBench and NarrLV demonstrate the state-of-the-art performance of MIGA. Our project page is available at https://xiaokunfeng.github.io/miga_homepage/.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18233</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation</title>
      <link>https://arxiv.org/abs/2605.18739</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18739.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yukang Chen, Luozhou Wang, Wei Huang, Shuai Yang, Bohan Zhang, Yicheng Xiao, Ruihang Chu, Weian Mao, Qixin Hu, Shaoteng Liu, Yuyang Zhao, Huizi Mao, Ying-Cong Chen, Enze Xie, Xiaojuan Qi, Song Han&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 108&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; We present LongLive-2.0, an NVFP4-based parallel infrastructure throughout the full training and inference workflow of long video generation, addressing speed and memory bottlenecks. For training, we introduce sequence-parallel autoregressive (AR) training, instantiated as Balanced SP, which co-designs the efficient teacher-forcing layout with SP execution by pairing clean-history and noisy-target temporal chunks on each rank, enabling a natural teacher-forcing mask with SP-aware chunked VAE encoding. Combined with NVFP4 precision, it reduces GPU memory cost and accelerates GEMM computation during training, the proportion of which increases as video length grows. Moreover, we show that a high-quality infrastructure and dataset enable a remarkably clean training pipeline. Unlike existing Self-Forcing series methods that rely on ODE initialization and subsequent distribution matching distillation (DMD), LongLive-2.0 directly tunes a diffusion model into a long, multi-shot, interactive auto-regressive (AR) diffusion model. It can be further converted to real-time generation (4 to 2 denoising steps) with standalone LoRA weights. For inference on Blackwell GPUs, we enable W4A4 NVFP4 inference, quantize KV cache into NVFP4 for memory savings, and boost end-to-end throughput with asynchronous streaming VAE decoding. On non-Blackwell GPU architectures, we deploy SP inference to match the speed on Blackwell GPUs, while the quantized KV cache can lower inter-GPU communication of SP. Experiments show up to 2.15x speedup in training, and 1.84x in inference. LongLive-2.0-5B achieves 45.7 FPS inference while attaining strong performance on benchmarks. To our knowledge, LongLive-2.0 is the first NVFP4 training and inference system for long video generation.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18739</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution</title>
      <link>https://arxiv.org/abs/2605.18401</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18401.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Hongyi Liu, Haoyan Yang, Tao Jiang, Bo Tang, Feiyu Xiong, Zhiyu Li&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 124&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills as an experience schema that couples executable scripts, with non-executable guidance on procedures. Yet open skill ecosystems contain redundant, uneven, environment-sensitive artifacts, and indiscriminate updates can pollute future context. We present SkillsVote, a lifecycle-governance framework for Agent Skills from collection and recommendation to evolution. SkillsVote profiles a million-scale open-source corpus for environment requirements, quality, and verifiability, then synthesizes tasks for verifiable skills. Before execution, SkillsVote performs agentic library search over structured skill library to expose instructional skill context. After execution, it decomposes trajectories into skill-linked subtasks, attributes outcomes to skill use, agent exploration, environment, and result signals, and admits only successful reusable discoveries to evidence-gated updates. In our evaluation, offline evolution improves GPT-5.2 on Terminal-Bench 2.0 by up to 7.9 pp, while online evolution improves SWE-Bench Pro by up to 2.6 pp. Overall, governed external skill libraries can improve frozen agents without model updates when systems control exposure, credit, and preservation.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18401</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Code as Agent Harness</title>
      <link>https://arxiv.org/abs/2605.18747</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18747.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Xuying Ning, Katherine Tieu, Dongqi Fu, Tianxin Wei, Zihao Li, Yuanchen Bei, Jiaru Zou, Mengting Ai, Zhining Liu, Ting-Wei Li, Lingjie Chen, Yanjun Zhao, Ke Yang, Bingxuan Li, Cheng Qian, Gaotang Li, Xiao Lin, Zhichen Zeng, Ruizhong Qiu, Sirui Chen, Yifan Sun, Xiyuan Yang, Ruida Wang, Rui Pan, Chenyuan Yang, Dylan Zhang, Liri Fang, Zikun Cui, Yang Cao, Pan Chen, Dorothy Sun, Ren Chen, Mahesh Srinivasan, Nipun Mathur, Yinglong Xia, Hong Li, Hong Yan, Pan Lu, Lingming Zhang, Tong Zhang, Hanghang Tong, Jingrui He&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 199&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code connects agents to reasoning, action, and environment modeling. Second, we examine harness mechanisms: planning, memory, and tool use for long-horizon execution, together with feedback-driven control and optimization that make harness reliable and adaptive. Third, we discuss scaling the harness from single-agent systems to multi-agent settings, where shared code artifacts support multi-agent coordination, review, and verification. Across these layers, we summarize representative methods and practical applications of code as agent harness, spanning coding assistants, GUI/OS automation, embodied agents, scientific discovery, personalization and recommendation, DevOps, and enterprise workflows. We further outline open challenges for harness engineering, including evaluation beyond final task success, verification under incomplete feedback, regression-free harness improvement, consistent shared state across multiple agents, human oversight for safety-critical actions, and extensions to multimodal environments. By centering code as the harness of agentic AI, this survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.18747</guid>
      <pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Fast 4D Mesh Generation by Spatio-Temporal Attention Chains</title>
      <link>https://arxiv.org/abs/2605.19786</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Dvir Samuel, Yuval Atzmon, Gal Chechik, Yoni Kasten&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 10&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; 4D mesh generation has recently emerged as a powerful paradigm for recovering dynamic 3D structure from videos, but existing methods remain slow, computationally expensive, and difficult to scale to longer sequences. We introduce a training-free approach that accelerates 4D mesh generation while improving temporal correspondence quality. Our key observation is that temporal correspondences emerge inside a 4D backbone long before its generated meshes become visually accurate. We exploit this with a general framework we call Spatio-Temporal Attention Chain which propagates information across space and time. Starting from vertices on an anchor mesh, the chain maps vertices to latent tokens. It then follows temporal correspondences in latent space, and recovers frame-specific vertices through latent-to-vertex attention. This design avoids expensive explicit matching while preserving anchor mesh details and thereby improving dynamic mesh geometry and temporal consistency.   Compared to state-of-the-art, our method generates a 4D mesh in 9 seconds, achieving a 13times speedup while producing higher-quality results. Moreover, our approach scales to videos up to 16times longer without degrading mesh quality. Beyond generation, the improved correspondences enable competitive zero-shot performance on two downstream tasks: 2D object tracking and 4D tracking. We further show that our framework enables reliable camera estimation, a capability not supported by prior 4D mesh generation methods.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19786</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Stitched Value Model for Diffusion Alignment</title>
      <link>https://arxiv.org/abs/2605.19804</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19804.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Hyojun Go, Hyungjin Chung, Prune Truong, Goutam Bhat, Li Mi, Zhaochong An, Zixiang Zhao, Dominik Narnhofer, Serge Belongie, Federico Tombari, Konrad Schindler&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 11&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic preference. That alignment is challenging because the reward is defined for clean output images, but the alignment procedure requires value function estimates at noisy intermediate latents. Existing methods resort to Tweedie-style or Monte Carlo approximations, trading off estimator bias against computational cost: Tweedie estimates are efficient but biased, while Monte Carlo estimates are more accurate but require expensive rollouts. A natural alternative would be a learned value function, but it remains an open question how to effectively train a strong and general value model specifically for noisy latents. Here, we propose StitchVM, a model stitching framework that efficiently transfers reward models pretrained for clean images to the noisy latent regime. StitchVM starts from an existing, truncated pixel-space reward model and attaches a frozen diffusion backbone to it as its head. From the pixel-space model, the resulting hybrid retains a carefully pretrained, robust reward capability; from the diffusion backbone, it inherits its native ability to handle noisy latents. The stitching procedure is exceptionally lightweight, e.g., stitching and finetuning CLIP ViT-L and SD 3.5 Medium takes only 10 GPU-hours. By lifting powerful pixel-space reward models to latent space, StitchVM opens up a new style of diffusion alignment: instead of rough, yet costly per-sample approximation of the value function, the correct function for the actual, noisy latents is constructed once and then amortized over many samples and iterations. We show that this approach yields improvements across a broad range of downstream steering and post-training methods: DPS becomes 3.2times faster while halving peak GPU memory, and DiffusionNFT becomes 2.3times faster.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19804</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization</title>
      <link>https://arxiv.org/abs/2605.19436</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19436.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Ahmed Heakl, Abdelrahman M. Shaker, Youssef Mohamed, Rania Elbadry, Omar Fetouh, Fahad Shahbaz Khan, Salman Khan&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 14&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; When a model produces a correct solution under reinforcement learning with verifiable rewards (RLVR), every token receives the same reward signal regardless of whether it was a decisive reasoning step or a grammatical filler. A natural fix is to condition the model on the correct answer as a teacher, identifying tokens it would have generated differently had it known the answer. Prior work shows this either corrupts training by leaking the answer into the gradient, or produces a weak signal that cannot distinguish decisive steps from filler, since both look equally surprising relative to the model's baseline. We propose Contrastive Evidence Policy Optimization (CEPO), which asks a sharper question at every token: not just "does the correct answer favor this token?" but "does the correct answer favor it while the wrong answer disfavors it?" A token satisfying both is a genuine reasoning step; one satisfying neither is filler. The wrong-answer teacher is constructed from rejected rollouts already in the training batch, incurring no additional sampling cost. We prove CEPO inherits all structural safety guarantees of the prior state of the art while strictly sharpening credit at decisive tokens, with the improvement vanishing exactly at filler positions. Empirically, CEPO achieves 43.43% and 60.56% average accuracy across five multimodal mathematical reasoning benchmarks at 2B and 4B scale, respectively, versus 41.17% and 57.43% for GRPO under identical training budgets. Distribution-matching self-distillation methods (OPSD, SDPO) fall below the untrained baseline, empirically confirming the information leakage our theory predicts. Our code is available at https://github.com/ahmedheakl/CEPO.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19436</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation</title>
      <link>https://arxiv.org/abs/2605.20183</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20183.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yujie Wei, Yujin Han, Zhekai Chen, Yongming Li, Kaixun Jiang, Zhihang Liu, Quanhao Li, Zhiwu Qing, Xiang Wang, Zhen Xing, Ruihang Chu, Lingyi Hong, Yefei He, Junjie Zhou, Junqiu Yu, Yang Shi, Difan Zou, Kai Zhu, Shiwei Zhang, Yingya Zhang, Yu Liu, Xihui Liu, Hongming Shan&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 14&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Video generation is rapidly evolving from single-shot synthesis to complex multi-shot audio-video (MSAV) narratives to meet real-world demands. However, evaluating such frontier models remains a fundamental challenge. Existing benchmarks are limited in scope and data diversity, and rely on rigid evaluation pipelines, preventing systematic and reliable assessment of modern MSAV models. To bridge these gaps, we introduce MSAVBench, the first comprehensive benchmark and adaptive hybrid evaluation framework for multi-shot audio-video generation. Our benchmark spans four key dimensions, video, audio, shot, and reference, covering diverse task settings, varying shot counts of up to 15, and challenging non-realistic scenarios. Our evaluation framework improves robustness through an adaptive self-correction mechanism for shot segmentation, instance-wise rubrics for subjective metrics, and tool-grounded evidence extraction for complex judgments. Furthermore, MSAVBench achieves high alignment with human judgments, reaching a Spearman rank correlation of 91.5%. Our systematic evaluation of 19 state-of-the-art closed- and open-source models shows that current systems still struggle with director-level control and fine-grained audio-visual synchronization, while modular or agentic generation pipelines offer a promising path toward narrowing the gap between open- and closed-source models. We will release the benchmark data and evaluation code to facilitate future research.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20183</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions</title>
      <link>https://arxiv.org/abs/2605.20087</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20087.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Chuanyang Jin, Binze Li, Haopeng Xie, Cathy Mengying Fang, Tianjian Li, Shayne Longpre, Hongxiang Gu, Maximillian Chen, Tianmin Shu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 16&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Conversational AI has now reached billions of users, yet existing datasets capture only what people say, not what they think. We introduce ThoughtTrace, the first large-scale dataset that pairs real-world multi-turn human--AI conversations with users' self-reported thoughts: their reasons for sending prompts and reactions to assistant responses. ThoughtTrace comprises 1,058 users, 2,155 conversations, 17,058 turns, and 10,174 thought annotations collected across 20 language models. Our analysis shows that ThoughtTrace captures long-horizon, topically diverse interactions, and that thoughts are semantically distinct from messages, difficult for frontier LLMs to infer from context, diverse in content, and tied to conversation stages. We further demonstrate the utility of thoughts for downstream modeling. First, thoughts improve user-behavior prediction as inference-time context. Second, thought-guided rewrites provide fine-grained alignment signals for training personalized assistants. Together, ThoughtTrace establishes user thoughts as a new data modality for studying the cognitive dynamics behind human--AI interaction and provides a foundation for building assistants that better understand and adapt to users' latent goals, preferences, and needs.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20087</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing</title>
      <link>https://arxiv.org/abs/2605.19484</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19484.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Haobo Hu, Xiangwu Guo, Zhiheng Chen, Difei Gao, Haotian Liu, Libiao Jin, Qi Mao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 20&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; While GUI agents have made significant progress in web navigation and basic operating system tasks, their capabilities in professional creative workflows remain largely underexplored. To bridge this gap, we introduce Cutverse, a benchmark designed to systematically evaluate autonomous GUI agents in realistic media post-production environments. We curate expert demonstrations across 7 professional applications (e.g., Premiere Pro, Photoshop), covering 186 complex, long-horizon tasks grounded in authentic editing workflows, involving dense multimodal interfaces and tightly coupled interaction sequences. To support scalable evaluation, we develop a lightweight parser that transforms raw screen recordings and low-level interaction logs into structured, compositional GUI action trajectories with precise grounding. Extensive evaluations reveal that existing agents achieve only 36.0\% task success on realistic media editing tasks, underscoring the challenges posed by complex, long-horizon media post-production workflows in our benchmark.While current models demonstrate promising spatial grounding, multimodal alignment, and coordinated action execution, they remain limited in long-horizon reliability and domain-specific planning.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19484</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening</title>
      <link>https://arxiv.org/abs/2605.19597</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19597.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Ming Zhang, Qiyuan Peng, Yinxi Wei, Yujiong Shen, Kexin Tan, Yuhui Wang, Zhenghao Xiang, Junjie Ye, Zhangyue Yin, Zhiheng Xi, Shihan Dou, Tao Gui, Maxm Pan, Ruizhi Yang, Qi Zhang, Xuanjing Huang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 20&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Evaluating large language models (LLMs) on natural-language logical reasoning is essential because rule-governed tasks require conclusions to follow strictly from stated premises. Many existing logical-reasoning benchmarks are generated by templating natural-language items from sampled formulas, provide only coarse or unaudited formal annotations, and are now quickly saturated by frontier reasoning models. We present LLMEval-Logic, a Chinese logical reasoning benchmark built from realistic situational scenarios. Its pipeline forward-authors and expert-audits natural-language items together with their reference formalizations, verifies annotated answers with Z3, constructs expert rubrics for natural-to-formal grading, and hardens selected items through a closed-loop adversarial workflow. The benchmark is released in two paired subsets: a 246-item Base subset shipped with 1,400 expert-developed rubric atoms, and a 190-item Hard subset with 938 multi-step sub-questions over closed model spaces. Evaluating 14 frontier LLMs on LLMEval-Logic reveals substantial gaps in current models: the best model reaches only 37.5% Hard Item Accuracy, and even with reference symbols the highest joint Z3+Rubric formalization score among evaluated models reaches only 60.16%. Our benchmark is publicly available at https://github.com/llmeval/LLMEval-Logic.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19597</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs</title>
      <link>https://arxiv.org/abs/2605.20315</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20315.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Haiquan Lu, Zigeng Chen, Gongfan Fang, Xinyin Ma, Xinchao Wang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 28&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; LLM agents have recently emerged as a powerful paradigm for solving complex tasks through planning, tool use, memory retrieval, and multi-step interaction. However, these agentic workflows often introduce substantial input-side overhead, making the compute-intensive prefilling stage a key bottleneck in long-context, multi-turn inference. In this work, we propose Mix-Quant, a simple and effective phase-aware quantization framework for fast agentic inference. We first investigate FP4 quantization in agentic LLM workflows and observe that quantizing the entire inference process can incur significant performance degradation. In contrast, the prefilling stage exhibits substantial quantization redundancy and can therefore be quantized with minimal accuracy loss, despite being the dominant source of computation. Based on this insight, we apply high-throughput NVFP4 quantization to the prefilling phase while preserving BF16 precision for decoding. By decoupling prefilling acceleration from decoding quality, Mix-Quant combines phase-aware algorithmic quantization with hardware-efficient NVFP4 execution to alleviate the inference bottleneck in LLM agents. Extensive experiments across long-context and agentic benchmarks demonstrate that Mix-Quant largely preserves task performance while delivering significant efficiency improvements, achieving up to a 3x speedup during prefilling.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20315</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition</title>
      <link>https://arxiv.org/abs/2605.19995</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19995.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Hongji Yang, Songlian Li, Yucheng Zhou, Xiaotong Zhao, Alan Zhao, Chengzhong Xu, Jianbing Shen&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 34&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Recent diffusion models achieve strong photorealism and fluency in video generation, yet remain fragile under abstract, sparse or complex conditions, leading to poor performance in professional production workflows such as storyboard sketches and clay render conditions. Existing video generation models, either inject conditions through adapters or couple a generic vision-language model (VLM) within a diffusion backbone, leaving a capability gap and failing to produce the videos that align with the user's creative intent. We present CogOmniControl, a reasoning-driven framework that factorizes controllable video generation into creative intent cognition and generation. Specifically, we train a specialized CogVLM using authentic anime production data. Compared to generic VLMs, it generates more professional and clear outputs, accurately cognizing user creative intent from sparse and abstract conditions and tuning these cues into dense reasoning output. Besides, CogOmniDiT unifies the controls from various conditions through in-context generation and is aligned to the CogVLM reasoning outputs via reinforcement learning. Furthermore, leveraging CogVLM's robust capability in guiding video generation, we release its potential in planning specific evaluators and enable a Best-of-N selection for the generated videos. This integration transforms the entire framework into a closed-loop "harness-like" architecture. We further introduce CogReasonBench and CogControlBench, built from professional workflows data that carry genuine creative intent rather than simulated ones. Experiments on two benchmarks show that CogOmniControl surpassed the existing open-source models. The project website: https://um-lab.github.io/CogOmniControl/&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19995</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Toto 2.0: Time Series Forecasting Enters the Scaling Era</title>
      <link>https://arxiv.org/abs/2605.20119</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20119.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Emaad Khwaja, Chris Lettieri, Gerald Woo, Eden Belouadah, Marc Cenac, Guillaume Jarry, Enguerrand Paquin, Xunyi Zhao, Viktoriya Zhukov, Othmane Abou-Amal, Chenghao Liu, Ameet Talwalkar, David Asker&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 36&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; We show that time series foundation models scale: a single training recipe produces reliable forecast-quality improvements from 4M to 2.5B parameters. We release Toto 2.0, a family of five open-weights forecasting models trained under this recipe. The Toto 2.0 family sets a new state of the art on three forecasting benchmarks: BOOM, our observability benchmark; GIFT-Eval, the standard general-purpose benchmark; and the recent contamination-resistant TIME benchmark. This report describes our experimental results and details the design decisions behind Toto 2.0: its architecture and training recipe, training data, and the u-muP hyperparameter transfer pipeline. All five base checkpoints are released under Apache 2.0.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20119</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond</title>
      <link>https://arxiv.org/abs/2605.19660</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19660.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Zunhai Su, Rui Yang, Chao Zhang, Yaxiu Liu, Yifan Zhang, Wei Wu, Jing Xiong, Dayou Du, Xialie Zhuang, Yulei Qian, Yuchen Xie, Yik-Chung Wu, Hongxia Yang, Ngai Wong&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 39&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; The rapid advancement toward long-context reasoning and multi-modal intelligence has made the memory footprint of the Key-Value (KV) cache a dominant memory bottleneck for efficient deployment. While the established per-channel quantization effectively accommodates intrinsic channel-wise outliers in Key tensors, its efficacy diminishes under extreme compression. In this work, we revisit the inherent limitations of the per-channel quantization paradigm from both empirical and theoretical perspectives. Our analysis identifies Token Norm Imbalance (TNI) as the primary bottleneck to quantization fidelity. We demonstrate that TNI systematically amplifies errors when shared quantization parameters are required to span token groups exhibiting substantial norm disparities. Instead of relying on intricate quantization pipelines (e.g., TurboQuant), we propose OScaR (Omni-Scaled Canalized Rotation), an accurate and lightweight KV cache compression framework for X-LLMs (i.e., text-only, multi-modal, and omni-modal LLMs). Advancing the per-channel paradigm, OScaR employs Canalized Rotation followed by Omni-Token Scaling to mitigate TNI-induced sequence-dimensional variance both effectively and efficiently, further supported by our optimized system design and CUDA kernels. Extensive evaluations across X-LLMs show that OScaR consistently outperforms existing methods and achieves near-lossless performance under INT2 quantization, establishing it as a robust, low-complexity, and universal framework that defines a new Pareto front. Compared with the BF16 FlashDecoding-v2 baseline, our OScaR implementation achieves a notable up to 3.0x speedup in decoding, reduces memory footprint by 5.3x, and increases throughput by 4.1x. The code for OScaR is publicly available at https://github.com/ZunhaiSu/OScaR-KV-Quant.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19660</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>OpenComputer: Verifiable Software Worlds for Computer-Use Agents</title>
      <link>https://arxiv.org/abs/2605.19769</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19769.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jinbiao Wei, Qianran Ma, Yilun Zhao, Xiao Zhou, Kangqi Ni, Guo Gan, Arman Cohan&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 56&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured inspection endpoints over real applications, (2) a self-evolving verification layer that improves verifier reliability using execution-grounded feedback, (3) a task-generation pipeline that synthesizes realistic and machine-checkable desktop tasks, and (4) an evaluation harness that records full trajectories and computes auditable partial-credit rewards. In its current form, OpenComputer covers 33 desktop applications and 1,000 finalized tasks spanning browsers, office tools, creative software, development environments, file managers, and communication applications. Experiments show that OpenComputer's hard-coded verifiers align more closely with human adjudication than LLM-as-judge evaluation, especially when success depends on fine-grained application state. Frontier agents struggle with end-to-end completion despite partial progress, and open-source models exhibit sharp drops from their OSWorld-Verified scores, exposing a persistent gap in robust computer automation.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19769</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment</title>
      <link>https://arxiv.org/abs/2605.19577</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19577.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Minxuan Lv, Tiehua Mei, Tanlong Du, Junmin Chen, Zhenpeng Su, Ziyang Chen, Ziqi Wang, Zhennan Wu, Ruotong Pan, jian Liang, Ruiming Tang, Han Li&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 56&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL methods often treat data construction as a matter of designing increasingly complex retrieval paths, leading to homogeneous task coverage and reward formulations that inadequately reflect practical long-context requirements. Our work offers two contributions. (1) Capability-oriented data construction with full open release. We openly release a dataset of 23K RLVR samples, the complete construction pipeline, and all training code. Guided by a taxonomy of long-context capabilities, the dataset spans 9 task types, each paired with its natural evaluation metric. It comprises curated open-source samples from established corpora and synthetic samples whose QA pairs are generated from real source documents such as books, academic papers, and multi-turn dialogues. Under the same vanilla GRPO setup, our dataset alone outperforms the closed-source QwenLong-L1.5 dataset. Moreover, our Qwen3-30B-A3B model trained on this data delivers long-context performance comparable to DeepSeek-R1-0528 and Qwen3-235B-A22B-Thinking-2507, suggesting that broader coverage and greater reward diversity substantially benefit long-context capability improvement. (2) TMN-Reweight for heterogeneous multitask optimization. To address optimization challenges from heterogeneous rewards, we propose TMN-Reweight, which combines task-level mean normalization for cross-task reward scale alignment with difficulty-adaptive weighting for more reliable advantage estimation. TMN-Reweight further improves average performance over vanilla GRPO, with general capabilities preserved or improved across reported evaluations.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19577</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows</title>
      <link>https://arxiv.org/abs/2605.14678</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14678.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Haoran Zhang, Luxin Xu, Zhilin Wang, Runquan Gui, Shunkai Zhang, Haodi Lei, Zihao He, Bingsu He, Chicheng Qin, Tong Zhu, Xiaoye Qu, Yang Yang, Yu Cheng, Yafu Li&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 91&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; The rise of personal assistant agents, e.g., OpenClaw, highlights the growing potential of large language models to support users across everyday life and work. A core challenge in these settings is proactive assistance, since users often begin with underspecified requests and leave important needs, constraints, or preferences unstated. However, existing benchmarks rarely evaluate whether agents can identify and act on such hidden intents before they are explicitly stated, especially in sustained multi-turn interactions where user needs emerge gradually. To address this gap, we introduce π-Bench, a benchmark for proactive assistance comprising 100 multi-turn tasks across 5 domain-specific user personas. By incorporating hidden user intents, inter-task dependencies, and cross-session continuity, π-Bench evaluates agents' ability to anticipate and address user needs over extended interactions, jointly measuring proactivity and task completion in long-horizon trajectories that better reflect real-world use. Experiments show (1) proactive assistance remains challenging, (2) a clear distinction between task completion and proactivity, and (3) the value of prior interaction for proactive intent resolution in later tasks.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.14678</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation</title>
      <link>https://arxiv.org/abs/2605.19833</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19833.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Zhifei Xie, Kaiyu Pang, Haobin Zhang, Deheng Ye, Xiaobin Hu, Shuicheng Yan, Chunyan Miao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 127&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Despite rapid advances in automatic speech recognition (ASR) and large audio-language models, robust recognition in real-world environments remains limited by an "acoustic robustness bottleneck": models often lose acoustic grounding and produce omissions or hallucinations under severe, compositional distortions. We propose Mega-ASR, a unified ASR-in-the-wild framework that combines scalable compound-data construction with progressive acoustic-to-semantic optimization. We introduce Voices-in-the-Wild-2M, covering 7 classic acoustic phenomena and 54 physically plausible compound scenarios, and train Mega-ASR with Acoustic-to-Semantic Progressive Supervised Fine-Tuning and Dual-Granularity WER-Gated Policy Optimization. Extensive experiments demonstrate that Mega-ASR achieves significant advantages over prior state-of-the-art systems on adverse-condition ASR benchmarks (45.69% vs. 54.01% on VOiCES R4-B-F, and 21.49% vs. 29.34% on NOIZEUS Sta-0). On complex compositional acoustic scenarios, Mega-ASR further delivers over 30% relative WER reduction against strong open- and closed-source baselines, establishing a scalable paradigm for robust ASR in-the-wild.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19833</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration</title>
      <link>https://arxiv.org/abs/2605.20025</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20025.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jiaqi Liu, Shi Qiu, Mairui Li, Bingzhou Li, Haonian Ji, Siwei Han, Xinyu Ye, Peng Xia, Zihan Dong, Congyu Zhang, Letian Zhang, Guiming Chen, Haoqin Tu, Xinyu Yang, Lu Feng, Xujiang Zhao, Haifeng Chen, Jiawei Zhou, Xiao Wang, Weitong Zhang, Hongtu Zhu, Yun Li, Jieru Mei, Hongliang Fei, Jiaheng Zhang, Linjie Li, Linjun Zhang, Yuyin Zhou, Sheng Wang, Caiming Xiong, James Zou, Zeyu Zheng, Cihang Xie, Mingyu Ding, Huaxiu Yao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 166&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail and inform the next attempt, and lessons accumulate across cycles. Existing autonomous research systems often model this process as a linear pipeline: they rely on single-agent reasoning, stop when execution fails, and do not carry experience across runs. We present AutoResearchClaw, a multi-agent autonomous research pipeline built on five mechanisms: structured multi-agent debate for hypothesis generation and result analysis, a self-healing executor with a Pivot/Refine decision loop that transforms failures into information, verifiable result reporting that prevents fabricated numbers and hallucinated citations, human-in-the-loop collaboration with seven intervention modes spanning full autonomy to step-by-step oversight, and cross-run evolution that converts past mistakes into future safeguards. On ARC-Bench, a 25-topic experiment-stage benchmark, AutoResearchClaw outperforms AI Scientist v2 by 54.7%. A human-in-the-loop ablation across seven intervention modes reveals that precise, targeted collaboration at high-leverage decision points consistently outperforms both full autonomy and exhaustive step-by-step oversight. We position AutoResearchClaw as a research amplifier that augments rather than replaces human scientific judgment. Code is available at https://github.com/aiming-lab/AutoResearchClaw.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20025</guid>
      <pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation</title>
      <link>https://arxiv.org/abs/2605.21605</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.21605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Sixiang Chen, Zhaohu Xing, Tian Ye, Xinyu Geng, Yunlong Lin, Jianyu Lai, Xuanhua He, Fuxiang Zhai, Jialin Gao, Lei Zhu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 10&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal generative ability with external resources. As requests become more diverse and demanding, we aim to develop a general image-generation agent that can self-evolve through trajectories and use tools more effectively across varied generation challenges. To this end, we propose GenEvolve, a self-evolving framework based on Tool-Orchestrated Visual Experience Distillation. In GenEvolve, each generation attempt is modeled as a tool-orchestrated trajectory, where the agent gathers evidence, selects references, invokes generation skills, and composes them into a prompt-reference program. Unlike existing agentic generation methods that mainly rely on image-level scalar rewards, GenEvolve compares multiple trajectories for the same request and abstracts best-worst differences into structured visual experience, provided only to a privileged teacher branch. Inspired by on-policy self-distillation, Visual Experience Distillation provides dense token-level supervision, helping the student internalize better search, knowledge activation, reference selection, and prompt construction. We further construct GenEvolve-Data and GenEvolve-Bench. Experiments on public benchmarks and GenEvolve-Bench show substantial gains over strong baselines, achieving state-of-the-art performance among current image-generation frameworks. Our website is as follows: https://ephemeral182.github.io/GenEvolve/&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.21605</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists</title>
      <link>https://arxiv.org/abs/2605.20668</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20668.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Seungone Kim, Dongkeun Yoon, Kiril Gashteovski, Juyoung Suk, Jinheon Baek, Pranjal Aggarwal, Ian Wu, Viktor Zaverkin, Spase Petkoski, Daniel R. Schrider, Ilija Dukovski, Francesco Santini, Biljana Mitreska, Yong Jeong, Kyeongha Kwon, Young Min Sim, Dragana Manasova, Arthur Porto, Biljana Mojsoska, Makoto Takamoto, Marko Shuntov, Ruoqi Liu, Hyunjoo Jenny Lee, Niyazi Ulas Dinç, Yehhyun Jo, Sunkyu Han, Chungwoo Lee, Huishan Li, Esther H. R. Tsai, Ergun Simsek, Khushboo Shafi, Yeonseung Chung, Jihye Park, Aleksandar Shulevski, Henrik Christiansen, Yoosang Son, Elly Knight, Amanda Montoya, Jeongyoun Ahn, Christian Langkammer, Heera Moon, Changwon Yoon, Nikola Stikov, Mooseok Jang, Edward Choi, Junhan Kim, Yeon Sik Jung, Woo Youn Kim, Jae Kyoung Kim, Ishraq Md Anjum, Hyun Uk Kim, Drew Bridges, Carolin Lawrence, Xiang Yue, Alice Oh, Akari Asai, Sean Welleck, Graham Neubig&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 11&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; With the advancement of AI capabilities, AI reviewers are beginning to be deployed in scientific peer review, yet their capability and credibility remain in question: many scientists simply view them as probabilistic systems without the expertise to evaluate research, while other researchers are more optimistic about their readiness without concrete evidence. Understanding what AI reviewers do well, where they fall short, and what challenges remain is essential. However, existing evaluations of AI reviewers have focused on whether their verdicts match human verdicts (e.g., score alignment, acceptance prediction), which is insufficient to characterize their capabilities and limits. In this paper, we close this gap through a large-scale expert annotation study, in which 45 domain scientists in Physical, Biological, and Health Sciences spent 469 hours rating 2,960 individual criticisms (each targeting one specific aspect of a paper) from human-written and AI-generated reviews of 82 Nature-family papers on correctness, significance, and sufficiency of evidence. On a composite of all three dimensions, a reviewing agent powered by GPT-5.2 scores above each paper's top-rated human reviewer (60.0% vs. 48.2%, p = 0.009), while all three AI reviewers (including Gemini 3.0 Pro and Claude Opus 4.5) exceed the lowest-rated human across every dimension. AI reviewers' accurate criticisms are also more often rated significant and well-evidenced, and surface a distinct 26% of issues no human raises. However, AI reviewers overlap far more than humans do (21% vs. 3% for cross-reviewer pairs), and exhibit 16 recurring weaknesses humans do not share, such as limited subfield knowledge, lack of long context management over multiple files, and overly critical stance on minor issues. Overall, our results position current AI reviewers as complements to, not substitutes for, human reviewers.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20668</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines</title>
      <link>https://arxiv.org/abs/2605.20630</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20630.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Alimurtaza Mustafa Merchant, Krish Veera, Sajal Kumar Goyla, Shambhawi Bhure, Dhaval Patel, Kaoutar El Maghraoui&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 12&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Industrial asset operations workflows are latency-sensitive because a single user query may require coordination over sensor data, work orders, failure modes, forecasting tools, and domain-specific agents. We evaluate this problem on AssetOpsBench (AOB), an industrial agent benchmark whose plan-execute pipeline exposes repeated overhead from tool discovery, LLM planning, MCP tool execution, and final summarization. Existing LLM caching techniques such as KV-cache reuse and embedding-based semantic caching were designed for chatbot serving and break down when output validity depends on time, asset, or sensor parameters. We propose two complementary optimization layers for AOB plan-execute pipelines: a temporal semantic cache and a set of MCP workflow optimizations combining disk-backed tool-discovery caching and dependency-aware parallel step execution. MCP workflow optimizations corresponded to a 1.67x speedup and reduced median end-to-end latency by about 40.0% while the temporal-cache benchmark achieved a median of 30.6x speedup on cache hits. Beyond the speedup, our results expose a concrete failure mode of pure semantic caching for parameter-rich industrial queries, providing a critical analysis of how caching choices interact with evaluation correctness in MCP-backed agent benchmarks.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20630</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment</title>
      <link>https://arxiv.org/abs/2605.17602</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.17602.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Kuei-Chun Kao, Daixuan Huo, Yuanhao Ban, Cho-Jui Hsieh&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 16&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Aligning Text-to-Image (T2I) generation models with human preferences increasingly relies on image reward models that score or rank generated images according to prompt alignment and perceptual quality. Existing reward models are commonly trained as Bradley-Terry (BT) preference models on large-scale human preference corpora, making them costly to train, difficult to adapt, and opaque in their evaluation criteria. Meanwhile, Vision-Language Model (VLM) judges can provide more fine-grained assessments through textual rubrics, but their manually designed or heuristically generated scoring rules may fail to reliably reflect human preferences. In this paper, we propose AutoRubric-T2I, the first rubric learning framework in T2I that automatically synthesizes and selects explicit rubrics for guiding VLM judges. AutoRubric-T2I first synthesizes reasoning traces from preference pairs into candidate rubrics, then uses a VLM judge to score paired images under each rubric, producing pairwise rubric-score differences for preference learning. To remove noisy and redundant rules, we further employ a ell_1-Regularized Logistic Regression Refiner, which selects the Top-N most discriminative rubrics. Extensive evaluations show that AutoRubric-T2I produces high-quality, interpretable reward signals using less than 0.01% of the annotated preference data, substantially reducing the need for large-scale reward-model training. On image reward benchmarks such as MMRB2, AutoRubric-T2I outperforms strong reward model baselines. We further validate AutoRubric-T2I as an RL reward on downstream T2I tasks, including TIIF and UniGenBench++, where it improves generation quality over scalar reward models using the Flow-GRPO pipeline on diffusion models.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.17602</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Q-ARVD: Quantizing Autoregressive Video Diffusion Models</title>
      <link>https://arxiv.org/abs/2605.21072</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.21072.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Siao Tang, Xinyin Ma, Gongfan Fang, Xingyi Yang, Xinchao Wang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 19&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Autoregressive video diffusion models (ARVDs) have emerged as a promising architecture for streaming video generation, paving the way for real-time interactive video generation and world modeling. Despite their potential, the substantial inference cost of ARVDs remains a major obstacle to practical deployment, making model quantization a natural direction for improving efficiency. However, quantization for ARVDs remains largely unexplored. Our empirical analysis shows that directly applying existing quantization schemes developed for standard diffusion transformers to ARVDs leads to suboptimal performance, revealing quantization behaviors that differ from those observed in bidirectional diffusion models. In this paper, we identify two critical challenges in quantizing ARVDs: (C1) Highly unbalanced frame-wise quantization sensitivity. Error accumulation during autoregressive generation can induce severely skewed quantization sensitivity across frames, following an exponential-like decay pattern. (C2) Prominent and heterogeneous outlier patterns in weights. Weight distributions exhibit pronounced outlier channels, whose patterns vary substantially across layer types and block depths. To address these issues, we propose Q-ARVD, a novel framework for accurate ARVD quantization. (S1) To tackle the highly unbalanced frame-wise sensitivity, Q-ARVD incorporates a final-quality aware frame-weighting mechanism into the quantization objective. (S2) To prevent heterogeneous outliers from degrading performance, Q-ARVD introduces an outlier-aware adaptive dual-scale quantization, which automatically detects the presence and quantity of outlier channels for an arbitrary layer, and isolates them to protect normal channels. Extensive experiments demonstrate the superiority of Q-ARVD.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.21072</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning</title>
      <link>https://arxiv.org/abs/2605.21487</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.21487.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Dian Zheng, Manyuan Zhang, Hongyu Li, Hongbo Liu, Kai Zou, Kaituo Feng, Hongsheng Li&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 21&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training. Due to inherent task conflicts, such strategy requires complex multi-stage pipelines, massive data mixing, and balancing tricks, merely resulting in a performance trade-off rather than true mutual reinforcement. To break this paradigm, we propose Uni-Edit, an intelligent image editing task that serves as the first general task for UMM tuning. Unlike complex mixed pipelines, Uni-Edit improves performance across all three abilities at once using only one task, one training stage, and one dataset. Specifically, we first identify image editing as an inherently ideal general task, as it naturally demands both visual understanding and generation. However, existing editing data relies on simplistic instructions that severely underutilize a model's understanding capacity. To address this, we introduce the first automated and scalable data synthesis pipeline for intelligent editing, transforming diverse VQA data into complex and effective editing instructions with embedded questions and nested logic. This yields Uni-Edit-148k, pairing diverse reasoning-intensive instructions with high-quality edited images. Extensive experiments on BAGEL and Janus-Pro demonstrate that tuning solely on Uni-Edit achieves comprehensive enhancements across all three capabilities without any auxiliary operations.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.21487</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>HRM-Text: Efficient Pretraining Beyond Scaling</title>
      <link>https://arxiv.org/abs/2605.20613</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20613.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Guan Wang, Changling Liu, Chenyu Wang, Cai Zhou, Yuhao Sun, Yifei Wu, Shuai Zhen, Luca Scimeca, Yasin Abbasi Yadkori&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 21&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foundational research. In contrast, biological systems demonstrate highly sample-efficient learning through multi-timescale processing, such as the functional organization of the frontoparietal loop. Taking this as inspiration, we introduce HRM-Text, which replaces standard Transformers with a Hierarchical Recurrent Model (HRM) that decouples computation into slow-evolving strategic and fast-evolving execution layers. To stabilize this deep recurrence for language modeling, we introduce MagicNorm and warmup deep credit assignment. Furthermore, instead of standard raw-text pretraining, we train exclusively on instruction-response pairs using a task-completion objective and PrefixLM masking. Serving as an empirical existence proof of efficient pretraining, a 1B-parameter HRM-Text model trained from scratch on only 40 billion unique tokens and $1,500 budget achieves 60.7% on MMLU, 81.9% on ARC-C, 82.2% on DROP, 84.5% on GSM8K, and 56.2% on MATH. Despite utilizing roughly 100-900x fewer training tokens and 96-432x less estimated compute than standard baselines, HRM-Text performs competitively with 2-7B parameter open models. These results demonstrate that co-designing architectures and objectives can radically reduce the compute-to-performance ratio, making pretraining from scratch accessible to the broader research community.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20613</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching</title>
      <link>https://arxiv.org/abs/2605.20910</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20910.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jangho Park, Geon Yeong Park, Gihyun Kwon, Jong Chul Ye&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 24&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Extending the generation horizon of video diffusion models to long sequences remains a long-standing and important challenge. Existing training-free approaches fall into two categories: extensions of bidirectional models, which are tightly coupled to specific architectures and suffer from quality degradation over long horizons, and autoregressive models, which accumulate drift errors due to exposure bias and tend to produce repetitive motion patterns. To address these issues, we propose a novel but simple inference-time approach for long video generation that is architecture-agnostic and requires no additional training. Our method generates long videos via overlapping sliding windows, where predicted clean samples from adjacent windows are blended via Tweedie matching to enforce both manifold constraint and temporal consistency across overlap regions. Stochastic early-phase sampling then synchronizes per-window trajectories by injecting fresh noise after each Tweedie matching correction in the high-noise phase, before transitioning to deterministic ODE sampling to preserve fine-grained visual fidelity. Applied to various video generation models, our method generates videos several times longer than the native window length while outperforming both training-free and autoregressive baselines in temporal consistency and visual quality, and further extends to audio-video joint generation and text-to-3DGS without any fine-tuning.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20910</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Generative Recursive Reasoning</title>
      <link>https://arxiv.org/abs/2605.19376</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.19376.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Junyeob Baek, Mingyu Jo, Minsu Kim, Mengye Ren, Yoshua Bengio, Sungjin Ahn&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 27&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by performing iterative latent-state refinement with shared transition functions. Yet existing RRMs are largely deterministic, following a single latent trajectory and converging to a single prediction. We introduce Generative Recursive reAsoning Models (GRAM), a framework that turns recursive latent reasoning into probabilistic multi-trajectory computation. GRAM models reasoning as a stochastic latent trajectory, enabling multiple hypotheses, alternative solution strategies, and inference-time scaling through both recursive depth and parallel trajectory sampling. This yields a latent-variable generative model supporting conditional reasoning via p_θ(y mid x) and, with fixed or absent inputs, unconditional generation via p_θ(x). Trained with amortized variational inference, GRAM improves over deterministic recurrent and recursive baselines on structured reasoning and multi-solution constraint satisfaction tasks, while demonstrating an unconditional generation capability. https://ahn-ml.github.io/gram-website&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.19376</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories</title>
      <link>https://arxiv.org/abs/2605.21468</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.21468.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Zhepei Wei, Xinyu Zhu, Wei-Lin Chen, Chengsong Huang, Jiaxin Huang, Yu Meng&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 44&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving reasoning in large language models (LLMs), yet the underlying geometry of the resulting parameter trajectories remains underexplored. In this work, we demonstrate that RLVR weight trajectories are extremely low-rank and highly predictable. Specifically, we find that the majority of downstream performance gains are captured by a rank-1 approximation of the parameter deltas, where the magnitude of this projection evolves near-linearly with training steps. Motivated by this, we propose a simple and compute-efficient method RELEX (REinforcement Learning EXtrapolation), which estimates the rank-1 subspace from a short observation window and extrapolates future checkpoints via linear regression, with no learned model required. Across three models (i.e., Qwen2.5-Math-1.5B, Qwen3-4B-Base, and Qwen3-8B-Base), RELEX produces checkpoints that match or exceed RLVR performance on both in-domain and out-of-domain benchmarks, requiring as few as 15% steps of full RLVR training. Remarkably, RELEX is able to extrapolate far beyond the observation window at no training cost, predicting checkpoints up to 10-20times beyond the observed prefix with continued improvement (e.g., observe only the first 50 steps and extrapolate to 1000 steps). Our ablation analysis confirms the minimalist sufficiency of RELEX: neither increasing the subspace rank nor employing non-linear modeling yields further gains in extrapolation. Finally, we show that RELEX's success stems from a "denoising" effect: by projecting updates onto the rank-1 subspace, the model discards stochastic optimization noise that would otherwise degrade performance during extrapolation. Our code is available at https://github.com/weizhepei/RELEX.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.21468</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects</title>
      <link>https://arxiv.org/abs/2605.21572</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.21572.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Ziang Cao, Yinghao Liu, Haitian Li, Runmao Yao, Fangzhou Hong, Zhaoxi Chen, Liang Pan, Ziwei Liu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 46&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Simulation-ready physical 3D assets have emerged as a promising direction owing to their broad applicability in downstream tasks. However, most existing 3D generation methods either neglect physical properties or are limited to a single asset category, e.g., rigid, deformable, or articulated objects. To address these limitations, we introduce PhysX-Omni, a unified framework for simulation-ready physical 3D generation across diverse asset types. Specifically, we develop a novel and efficient geometry representation tailored for Vision-Language Models, which directly encodes high-resolution 3D structures without compression, significantly improving generation performance. In addition, we construct the first general simulation-ready 3D dataset, PhysXVerse, covering diverse indoor and outdoor categories. Furthermore, to comprehensively and flexibly evaluate both generative and understanding capabilities in the wild, we propose PhysX-Bench, which encompasses six key attributes: geometry, absolute scale, material, affordance, kinematics, and function description. Extensive experiments with conventional metrics and PhysX-Bench show that PhysX-Omni performs strongly in both generation and understanding. Moreover, additional studies further validate the potential of PhysX-Omni for applications in simulation-ready scene generation and robotic policy learning. We believe PhysX-Omni can significantly advance a wide range of downstream applications, particularly in embodied AI and physics-based simulation.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.21572</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools</title>
      <link>https://arxiv.org/abs/2605.20682</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20682.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Rongbin Tan, Fangfang Lin, Zhenlong Yuan, Min Qiu, Kejin Cui, Mengmeng Wang, Yi Wang, Zijian Song, Zhiyuan Wang, Jiyuan Wang, Yue Wang, Shuhan Song§, Huawei Cao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 80&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Multimodal large language models (MLLMs) have shown remarkable capability in bridging visual perception and textual reasoning, enabling zero-shot understanding across diverse industrial scenarios. However, their performance in open-vocabulary industrial anomaly detection (IAD) is often limited by domain-misaligned reasoning and hallucinated structural inferences. To address these challenges, we propose IndusAgent, a tool-augmented agentic framework for open-vocabulary IAD. Specifically, we first construct Indus-CoT, a structured dataset that integrates global visual observations, high-resolution local patches, and expert normalcy priors, providing supervision for fine-tuning the model on rigorous industrial inspection trajectories. Building on this, IndusAgent dynamically orchestrates a set of external tools, including dynamic region cropping, high-frequency feature enhancement, and prior retrieval, thus enabling the agent to actively resolve visual ambiguities and disentangle subtle anomalies. Furthermore, we introduce a gated reinforcement learning objective that jointly optimizes anomaly classification, localization accuracy, anomaly type reasoning, and efficient tool usage, ensuring that tool invocation occurs only when beneficial. Extensive evaluations on five industrial anomaly benchmarks, including MVTec-AD, VisA, MPDD, DTD, and SDD, demonstrate that IndusAgent achieves state-of-the-art zero-shot performance among all existing methods, validating our robustness and generalization capacity.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.20682</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards</title>
      <link>https://arxiv.org/abs/2605.21467</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.21467.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Kaiyi Zhang, Wei Wu, Yankai Lin&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 192&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Reinforcement learning from verifiable rewards (RLVR) has emerged as a central technique for improving the reasoning capabilities of large language models. Despite its effectiveness, how response-level rewards translate into token-level probability changes remains poorly understood. We introduce a discriminator view of RLVR updates, showing that the policy-gradient update direction implicitly acts as a linear discriminator over token-gradient vectors and thereby determines which token probabilities are increased or decreased during learning. Under standard sequence-level RLVR, this discriminator is constructed from positive- and negative-side centroids formed by advantage-weighted averaging of token-gradient vectors. However, such centroid construction can be dominated by shared high-frequency patterns, such as formatting tokens, diluting sparse yet discriminative directions that better distinguish high-reward responses from low-reward ones. To address this limitation, we propose DelTA, a discriminative token credit assignment method that estimates token coefficients to amplify side-specific token-gradient directions and downweight shared or weakly discriminative ones. These coefficients reweight a self-normalized RLVR surrogate, making the effective side-wise centroids more contrastive and thereby reshaping the RLVR update direction. On seven mathematical benchmarks, DelTA outperforms the strongest same-scale baselines by 3.26 and 2.62 average points on Qwen3-8B-Base and Qwen3-14B-Base, respectively. Additional results on code generation, a different backbone, and out-of-domain evaluations further demonstrate the generalization ability of DelTA.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.21467</guid>
      <pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles</title>
      <link>https://arxiv.org/abs/2605.22177</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22177.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jinyang Wu, Guocheng Zhai, Ruihan Jin, Yuhao Shen, Zhengxi Lu, Fan Zhang, Haoran Luo, Zheng Lian, Zhengqi Wen, Jianhua Tao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 18&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; The proliferation of large language models (LLMs) and modular skills has endowed autonomous agents with increasingly powerful capabilities. Existing frameworks typically rely on monolithic LLMs and fixed logic to interface with these skills. This gives rise to a critical bottleneck: different LLMs offer distinct advantages across diverse domains, yet current frameworks fail to exploit the complementary strengths of models and skills, thereby limiting their performance on downstream tasks. In this paper, we present Maestro (Multimodal Agent for Expert-Skill Targeted Reinforced Orchestration), a Reinforcement Learning (RL)-driven orchestration framework that reframes heterogeneous multimodal tasks as a sequential decision-making process over a hierarchical model-skill registry. Rather than consolidating all knowledge into a single model, Maestro trains a lightweight policy to dynamically compose ensembles of frozen expert models and a two-tier skill library, deciding at each step whether to invoke an external expert, which model-skill pair to select, and when to terminate. The policy is optimized via outcome-based RL, requiring no step-level supervision. We evaluate Maestro across ten representative multimodal benchmarks spanning mathematical reasoning, chart understanding, high-resolution perception, and domain-specific analysis. With only a 4B orchestrator, Maestro achieves an average accuracy of 70.1%, surpassing both GPT-5 (69.3%) and Gemini-2.5-Pro (68.7%). Crucially, the learned coordination policy generalizes to unseen models and skills without retraining: augmenting the registry with out-of-domain experts yields a 59.5% average on four challenging benchmarks, outperforming all closed-source baselines. Maestro further maintains high computational efficiency with low latency. The source code is available at https://github.com/jinyangwu/Maestro.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22177</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention</title>
      <link>https://arxiv.org/abs/2605.22791</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22791.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Ali Hatamizadeh, Yejin Choi, Jan Kautz&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 22&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Linear attention replaces the unbounded cache of softmax attention with a fixed-size recurrent state, reducing sequence mixing to linear time and decoding to constant memory. The hard part is not just what to forget, but how to edit this compressed memory without scrambling existing associations. Delta-rule models subtract the current read before writing a new value, and Kimi Delta Attention (KDA) sharpens forgetting with channel-wise decay. But the active edit still uses a single scalar gate to control two different things: how much old content to erase on the key side and how much new content to commit on the value side. We introduce Gated DeltaNet-2, which generalizes both Gated DeltaNet and KDA by inheriting adaptive forgetting and channel-wise decay while addressing their shared limitation, the scalar tie between erasing and writing. Gated Delta Rule-2 separates these roles with a channel-wise erase gate b_t and a channel-wise write gate w_t, reducing to KDA when both gates collapse to the same scalar and to Gated DeltaNet when the decay also collapses. We derive a fast-weight update view, a chunkwise WY algorithm with channel-wise decay absorbed into asymmetric erase factors, and a gate-aware backward pass that preserves efficient parallel training. At 1.3B parameters trained on 100B FineWeb-Edu tokens, Gated DeltaNet-2 achieves the strongest overall results among Mamba-2, Gated DeltaNet, KDA, and Mamba-3 variants across language modeling, commonsense reasoning, and retrieval. Its advantage is most pronounced on long-context RULER needle-in-a-haystack benchmarks, where it improves the evaluated multi-key retrieval setting and remains strong in both recurrent and hybrid settings. Code is available at https://github.com/NVlabs/GatedDeltaNet-2.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22791</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving</title>
      <link>https://arxiv.org/abs/2605.22809</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22809.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jiahao Wang, Bo Sun, Yijing Bai, Vincent Casser, Songyou Peng, Zehao Zhu, Meng-Li Shih, Xander Masotto, Shih-Yang Su, Kanaad V Parvate, Tiancheng Ge, Linn Bieske, Dragomir Anguelov, Mingxing Tan, Chiyu Max Jiang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 24&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Robust training and validation of Autonomous Driving Systems (ADS) require massive, diverse datasets. Proprietary data collected by Autonomous Vehicle (AV) fleets, while high-fidelity, are limited in scale, diversity of sensor configurations, as well as geographic and long-tail-behavioral coverage. In contrast, in-the-wild data from sources like dashcams offers immense scale and diversity, capturing critical long-tail scenarios and novel environments. However, this unstructured, in-the-wild video data is incompatible with ADS expecting structured, multi-modal sensor inputs for validation and training. To bridge this data gap, we propose Sensor2Sensor, a novel generative modeling paradigm that translates in-the-wild monocular dashcam videos into a high-fidelity, multi-modal sensor suite (AV logs) comprising multi-view camera images and LiDAR point clouds. A core challenge is the lack of paired training data. We address this by converting real AV logs into dashcam-style videos via 4D Gaussian Splatting (4DGS) reconstruction and novel-view rendering. Sensor2Sensor then utilizes a diffusion architecture to perform the generative conversion. We perform comprehensive quantitative evaluations on the fidelity and realism of the generated sensor data. We demonstrate Sensor2Sensor's practical utility by converting challenging in-the-wild internet and dashcam footage into realistic, multi-modal data formats, further unlocking vast external data sources for AV development.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22809</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation</title>
      <link>https://arxiv.org/abs/2605.22536</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22536.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Xiaolong Zhou, Yifei Liu, Ziyang Gong, Jiarui Li, Qiyue Zhao, Muyao Niu, Yuanyuan Gao, Le Ma, Xue Yang, Hongjie Zhang, Zhihang Zhong&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 24&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pristine visual inputs and overlook the degradations that commonly occur in real-world deployment, such as motion blur, low light, adverse weather, lens distortion, and compression artifacts. This raises a fundamental question: how robust is the spatial intelligence of current MLLMs when visual observations are imperfect? To answer this question, we introduce SpaceDG, the first large-scale dataset for degradation-aware spatial understanding. It is constructed with a physically grounded degradation synthesis engine that embeds degradation formation process into 3D Gaussian Splatting (3DGS) rendering, enabling realistic simulation of nine degradation types. The resulting dataset contains approximately 1M QA pairs from nearly 1,000 indoor scenes. We further introduce SpaceDG-Bench, an human-verified benchmark with 1,102 questions spanning 11 reasoning categories and 9 visual degradation types, yielding over 10K VQA instances. Evaluating 25 open- and closed-source MLLMs reveals that visual degradations consistently and substantially impair spatial reasoning, exposing a critical robustness gap. Finally, we show that finetuning on SpaceDG markedly improves degradation robustness and can even surpass human performance under degraded conditions without any performance drop on clean images, highlighting the promise of degradation-aware training for robust spatial intelligence.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22536</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning</title>
      <link>https://arxiv.org/abs/2605.22642</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22642.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Banghao Chi, Yining Xie, Mingyuan Wu, Jingcheng Yang, Jize Jiang, Zhaoheng Li, Shengyi Qian, Minjia Zhang, Klara Nahrstedt, Rui Hou, Xiangjun Fan, Hanchao Yu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 33&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks, such as controlling computers and generating presentations, building an AI-driven spreadsheet agent has emerged as a promising research direction. Most existing spreadsheet agents rely on specialized prompting over general-purpose LLMs; while this design has potentials on simple spreadsheet operations, it struggles to manage the complex, multi-step workflows typical of real-world applications.   We introduce Spreadsheet-RL, a reinforcement learning (RL) fine-tuning framework designed to train specialized spreadsheet agents within a realistic Microsoft Excel environment. Spreadsheet-RL features an automated pipeline for scalable collection of paired start-goal spreadsheets from online forums, as well as domain-specific evaluation tasks in areas such as finance and supply chain management, which we compile into the new Domain-Spreadsheet benchmark dataset. It also includes a Spreadsheet Gym environment designed for multi-turn RL: Spreadsheet Gym exposes extensive Excel functionality through a Python sandbox, along with a refined harness that incorporates a comprehensive tool set and carefully designed tool-routing rules for spreadsheet tasks. Through comprehensive experiments, we show that Spreadsheet-RL substantially enhances AI agent's performance on both general and domain-specific spreadsheet tasks: it improves Qwen3-4B-Thinking-2507's Pass@1 on SpreadsheetBench from 12.0% to 23.4%, and raises Pass@1 from 8.4% to 17.2% on our curated Domain-Spreadsheet dataset. These results highlight Spreadsheet-RL's strong potential for generalization and real-world adoption in spreadsheet automation, and broadly, its promise for advancing LLM-based interactions with data interfaces in everyday work.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22642</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>WorldKV: Efficient World Memory with World Retrieval and Compression</title>
      <link>https://arxiv.org/abs/2605.22718</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22718.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Jung Yi, Minjae Kim, Paul Hyunbin Cho, Wooseok Jang, Sangdoo Yun, Seungryong Kim&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 33&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a previously seen viewpoint yields consistent content, remains an open problem. Full KV-cache attention preserves this consistency but breaks real-time constraints: memory footprint and attention cost grow linearly with rollout length. Sliding window inference restores throughput but discards long-term consistency. We propose WorldKV, a training-free framework with two components: World Retrieval and World Compression. World Retrieval stores evicted KV-cache chunks in GPU/CPU memory and selectively retrieves scene-relevant chunks via camera/ action correspondence, inserting them back into the native attention window without re-encoding. World Compression prunes redundant tokens within each chunk via key-key similarity to an anchor frame, halving per-chunk storage to fit 2x more history under a fixed budget. On Matrix-Game-2.0 and LingBot- World-Fast, WorldKV matches or exceeds full-KV memory fidelity at roughly 2x the throughput, and is competitive with memory-trained baselines without any fine-tuning. Project Page: https://cvlab-kaist.github.io/WorldKV/&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22718</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Forecasting Scientific Progress with Artificial Intelligence</title>
      <link>https://arxiv.org/abs/2605.22681</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22681.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Sean Wu, Pan Lu, Yupeng Chen, Jonathan Bragg, Yutaro Yamada, Peter Clark, David Clifton, Philip Torr, James Zou, Junchi Yu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 34&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Artificial intelligence (AI) is increasingly embedded in scientific discovery, yet whether it can anticipate scientific progress remains unclear. To study this question, we introduce a temporally grounded evaluation framework for forecasting scientific progress under controlled knowledge constraints. We present CUSP (Cutoff-conditioned Unseen Scientific Progress), a multi-disciplinary and event-level benchmark that evaluates scientific forecasting in AI systems through feasibility assessment, mechanistic reasoning, generative solution design, and temporal prediction. Across 4,760 scientific events, we observe systematic and domain-dependent limitations in current frontier models. While models can identify plausible research directions from competing candidates, they fail to reliably predict whether scientific advances will be realized and systematically misestimate when they will occur. Performance is highly heterogeneous across domains, with the timing of AI progress more predictable than advances in biology, chemistry, and physics. Performance is largely insensitive to whether events occur before or after the training cutoff, suggesting these limitations cannot be explained solely by knowledge exposure in training data. Under controlled information access, additional pre-cutoff knowledge improves performance but does not close the gap to full-information settings, which becomes more pronounced for high-citation advances. Models also exhibit systematic overconfidence and strong response biases, indicating unreliable uncertainty estimation. Taken together, current AI systems fall short as predictive tools for scientific progress. Access to prior knowledge does not translate into reliable forecasting, and performance benefits more from post-event information than from forward-looking prediction.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22681</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers</title>
      <link>https://arxiv.org/abs/2605.22668</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22668.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Javad Rajabi, Kimia Shaban, Koorosh Roohi, David B. Lindell, Babak Taati&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 36&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by modifying inference-time attention behavior, often through Rotary Position Embeddings (RoPE) extrapolation combined with attention scaling. However, these strategies apply a uniform and content-agnostic scaling across RoPE components with distinct frequency characteristics, inducing a trade-off between preserving global structure and recovering fine detail. We introduce SEGA, a training-free method that dynamically scales attention across RoPE components according to the latent's spatial-frequency structure at each denoising step. This adaptive scaling improves both structural coherence and fine-detail fidelity. Experiments show that SEGA consistently improves high-resolution synthesis across multiple target resolutions, outperforming state-of-the-art training-free baselines.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22668</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning</title>
      <link>https://arxiv.org/abs/2605.22012</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22012.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Yifan Dai, Zhenhua Wu, Bohan Zeng, Daili Hua, Jialing Liu, Bozhou Li, Yuran Wang, Chengzhuo Tong, Hao Liang, Xiaochen Ma, Junbo Niu, Tianyu Guo, Yang Shi, Yue Ding, Yiyan Ji, Bingyin Mei, Yushuo Guan, Yuanxing Zhang, Pengfei Wan, Fangcheng Fu, Wentao Zhang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 40&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Joint audio-visual reasoning is essential for omnimodal understanding, yet current multimodal large language models (MLLMs) still struggle when reasoning requires fine-grained evidence from both modalities. A central limitation is that explicit text-based chain-of-thought (CoT) compresses continuous audio-visual signals into discrete tokens, weakening temporal grounding and shifting intermediate reasoning toward language priors. We argue that a unified latent space is a better medium for such reasoning because it preserves dense sensory information while remaining compatible with autoregressive generation. Based on this insight, we propose LatentOmni, a cross-modal reasoning framework that interleaves textual reasoning with audio-visual latent states. LatentOmni introduces feature-level supervision to align latent reasoning states with task-relevant sensory features and uses Omni-Sync Position Embedding (OSPE) to maintain temporal consistency between latent audio and visual states. We further construct LatentOmni-Instruct-35K, a dataset of audio-visual interleaved reasoning trajectories for supervising latent-space reasoning. Comprehensive evaluation across multiple audio-visual reasoning benchmarks demonstrates that LatentOmni achieves the best performance among the evaluated open-source models and consistently outperforms the Explicit Text CoT baseline, supporting latent-space joint reasoning as a promising path toward stronger omnimodal understanding.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22012</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>ACC: Compiling Agent Trajectories for Long-Context Training</title>
      <link>https://arxiv.org/abs/2605.21850</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.21850.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Qisheng Su, Zhen Fang, Shiting Huang, Yu Zeng, Yiming Zhao, Kou Shi, Ziao Zhang, Lin Chen, Zehui Chen, Lijun Wu, Feng Zhao&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 56&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce massive trajectories when solving problems, invoking tools and receiving environment observations across many turns. The evidence needed to answer the original question is thus scattered throughout these turns, requiring integration of distant context segments. Nevertheless, standard agent SFT masks tool responses and only trains turn-level tool selection, creating a supervision blind spot where these scattered signals go unused. We propose Agent Context Compilation (ACC), which converts trajectories from search, software engineering, and database querying agents into long-context QA pairs that combine the original question with tool responses and environment observations gathered across multiple turns, training the model to answer directly without tool use. This makes the dependencies between the question and the evidence explicit, enabling direct supervision of long-context reasoning over distant segments without additional annotation. ACC is a simple but effective approach that can be combined with any existing long-context extension or training method, providing scalable supervised fine-tuning data. We validate ACC on long-range dependency modeling tasks through MRCR and GraphWalks, challenging benchmarks requiring cross-turn coreference resolution and graph traversal over extended contexts. Training Qwen3-30B-A3B with ACC achieves 68.3 on MRCR (+18.1) and 77.5 on GraphWalks (+7.6), results comparable to Qwen3-235B-A22B, while preserving general capabilities on GPQA, MMLU-Pro, AIME, and IFEval. Further mechanism analysis reveals that the ACC-trained model exhibits task-adaptive attention restructuring and expert specialization.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.21850</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?</title>
      <link>https://arxiv.org/abs/2605.22109</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22109.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Caixin Kang, Tianyu Yan, Sitong Gong, Mingfang Zhang, Liangyang Ouyang, Ruicong Liu, Bo Zheng, Huchuan Lu, Kaipeng Zhang, Yoichi Sato, Yifei Huang&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 162&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Multimodal Large Language Models (MLLMs) are increasingly deployed in human-facing roles where personality perception is critical, yet existing benchmarks evaluate this capability solely on numerical Big Five score prediction, leaving open whether models truly perceive personality through behavioral understanding or merely prejudge through superficial pattern matching. We address this gap with three contributions. (i) A new task: we formalize Grounded Personality Reasoning (GPR), which requires MLLMs to anchor each Big Five rating in observable evidence through a chain of rating, reasoning, and grounding. (ii) A new dataset: we release MM-OCEAN (1,104 videos, 5,320 MCQs), produced by a multi-agent pipeline with human verification, with timestamped behavioral observations, evidence-grounded trait analyses, and seven categories of cue-grounding MCQs. (iii) Benchmark and analysis: we design a three-tier evaluation (rating, reasoning, grounding) plus four sample-level failure-mode metrics: Prejudice Rate (PR), Confabulation Rate (CR), Integration-failure Rate (IR), and Holistic-grounding Rate (HR), and benchmark 27 MLLMs (13 closed, 14 open). The analysis uncovers a striking Prejudice Gap: across the field, 51% of correct ratings are not grounded in retrieved cues, and the Holistic-Grounding Rate spans only 0-33.5%. These findings expose a disconnect between getting the right score and reasoning for the right reason, charting a roadmap for grounded social cognition in MLLMs.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22109</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation</title>
      <link>https://arxiv.org/abs/2605.22355</link>
      <description>&lt;p&gt;&lt;img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22355.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Authors:&lt;/b&gt; Hanyu Guo, Jiedong Yang, Chao Chen, Longfei Xu, Kaikui Liu, Xiangxiang Chu&lt;/p&gt;&lt;p&gt;&lt;b&gt;Upvotes:&lt;/b&gt; 167&lt;/p&gt;&lt;p&gt;&lt;b&gt;Summary:&lt;/b&gt; Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports training models to bypass this dependency. We present TransitLM, a large-scale dataset of over 13 million transit route planning records from four Chinese cities covering 120,845 stations and 13,666 lines, released as a continual pre-training corpus and benchmark data for three evaluation tasks with complementary metrics. Experiments show that an LLM trained on TransitLM produces structurally valid routes at high accuracy and implicitly grounds arbitrary GPS coordinates to appropriate stations without any explicit mapping. These results demonstrate that transit route planning can be learned entirely from data, enabling end-to-end, map-free route generation directly from origin-destination information. The dataset and benchmark are available at https://huggingface.co/datasets/GD-ML/TransitLM, with evaluation code at https://github.com/HotTricker/TransitLM.&lt;/p&gt;</description>
      <guid isPermaLink="false">https://arxiv.org/abs/2605.22355</guid>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
    </item>
  </channel>
</rss>