diff --git a/feed_weekly.xml b/feed_weekly.xml index 8fa1e8d..291f4c3 100644 --- a/feed_weekly.xml +++ b/feed_weekly.xml @@ -7,741 +7,741 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 11 May 2026 00:30:42 +0000 + Mon, 18 May 2026 00:33:04 +0000 - StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing - https://arxiv.org/abs/2605.02904 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02904.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roberto Tacconelli</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We present StateSMix, a fully self-contained lossless compressor that couples an online-trained Mamba-style State Space Model (SSM) with sparse n-gram context mixing and arithmetic coding. The model is initialised from scratch and trained token-by-token on the file being compressed, requiring no pre-trained weights, no GPU, and no external dependencies. The SSM (DM=32, NL=2, approximately 120K active parameters per file) provides a continuously-updated probability estimate over BPE tokens, while nine sparse n-gram hash tables (bigram through 32-gram, 16M slots each) add exact local and long-range pattern memorisation via a softmax-invariant logit-bias mechanism that updates only non-zero-count tokens. An entropy-adaptive scaling mechanism modulates the n-gram contribution based on the SSM's predictive confidence, preventing over-correction when the neural model is already well-calibrated. On the standard enwik8 benchmark, StateSMix achieves 2.123 bpb on 1 MB, 2.149 bpb on 3 MB, and 2.162 bpb on 10 MB, beating xz -9e (LZMA2) by 8.7%, 5.4%, and 0.7% respectively. Ablation experiments establish the SSM as the dominant compression engine: it alone accounts for a 46.6% size reduction over a frequency-count baseline and beats xz without any n-gram component, while n-gram tables provide a complementary 4.1% gain through exact context memorisation. OpenMP parallelisation of the training loop yields 1.9x speedup on 4 cores. The system is implemented in pure C with AVX2 SIMD and processes approximately 2,000 tokens per second on commodity x86-64 hardware.</p> - https://arxiv.org/abs/2605.02904 - Sun, 05 Apr 2026 00:00:00 +0000 + Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning + https://arxiv.org/abs/2605.13852 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13852.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ido Sobol, Kihyuk Sohn, Yoav Blum, Egor Zakharov, Max Bluvstein, Andrea Vedaldi, Or Litany</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> We often aim to generate images that are both photorealistic and 3D-consistent, adhering to precise geometry, material, and viewpoint controls. Typically, this is achieved by fine-tuning an image generator, pre-trained on billions of real images, using renders of synthetic 3D assets, where annotations for control signals are available. While this approach can learn the desired controls, it often compromises the realism of the images due to domain gap between photographs and renders. We observe that this issue largely arises from the model learning an unintended association between the presence of control signals and the synthetic appearance of the images. To address this, we introduce Realiz3D, a lightweight framework for training diffusion models, that decouples controls and visual domain. The key idea is to explicitly learn visual domain, real or synthetic, separately from other control signals by introducing a co-variate that, fed into small residual adapters, shifts the domain. Then, the generator can be trained to gain controllability, without fitting to specific visual domain. In this way, the model can be guided to produce realistic images even when controls are applied. We enhance control transferability to the real domain by leveraging insights about roles of different layers and denoising steps in diffusion-based generators, informing new training and inference strategies that further mitigate the gap. We demonstrate the advantages of Realiz3D in tasks as text-to-multiview generation and texturing from 3D inputs, producing outputs that are 3D-consistent and photorealistic.</p> + https://arxiv.org/abs/2605.13852 + Wed, 25 Mar 2026 00:00:00 +0000 - Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning - https://arxiv.org/abs/2605.02913 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rohan Surana, Gagan Mundada, Xunyi Jiang, Chuhan Wang, Zhenwei Tang, Difan Jiao, Zihan Huang, Yuxin Xiong, Junda Wu, Sheldon Yu, Xintong Li, Raghav Jain, Nikki Kuang, Sizhe Zhou, Bowen Jin, Zhendong Chu, Tong Yu, Ryan Rossi, Kuan-Hao Huang, Jingbo Shang, Jiawei Han, Julian McAuley</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these systems, the rollout, the trajectory sampled from a prompt to termination, including intermediate reasoning steps and optional tool or environment interactions, determines the data the optimizer learns from, yet rollout design is often underreported. This survey provides an optimizer-agnostic view of rollout strategies for RL-based post-training of reasoning LLMs. We formalize rollout pipelines with unified notation and introduce Generate-Filter-Control-Replay (GFCR), a lifecycle taxonomy that decomposes rollout pipelines into four modular stages: Generate proposes candidate trajectories and topologies; Filter constructs intermediate signals via verifiers, judges, critics; Control allocates compute and makes continuation/branching/stopping decisions under budgets; and Replay retains and reuses artifacts across rollouts without weight updates, including self-evolving curricula that autonomously generate new training tasks. We complement GFCR with a criterion taxonomy of reliability, coverage, and cost sensitivity that characterizes rollout trade-offs. Using this framework, we synthesize methods spanning RL with verifiable rewards, process supervision, judge-based gating, guided and tree/segment rollouts, adaptive compute allocation, early-exit and partial rollouts, throughput optimization, and replay/recomposition for self-improvement. We ground the framework with case studies in math, code/SQL, multimodal reasoning, tool-using agents, and agentic skill benchmarks that evaluate skill induction, reuse, and cross-task transfer. Finally, we provide a diagnostic index that maps common rollout pathologies to GFCR modules and mitigation levers, alongside open challenges for building reproducible, compute-efficient, and trustworthy rollout pipelines.</p> - https://arxiv.org/abs/2605.02913 - Wed, 08 Apr 2026 00:00:00 +0000 - - - Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO - https://arxiv.org/abs/2605.04077 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04077.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Zeng, Jiameng Huang, Zhangyue Yin, Jiashuo Liu, Ziniu Li, Bingrui Li, Yuhao Wu, Yining Zheng, Ge Zhang, Wenhao Huang, Xipeng Qiu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is widely adopted for its simplicity and effectiveness. However, an important design choice remains underexplored: how token-level policy gradient terms are aggregated within each sampled group. Standard GRPO uses sequence aggregation, while recent work has advocated token aggregation as a better alternative. We show that these two rules induce different optimization biases: token aggregation introduces sign-length coupling, while sequence aggregation implicitly downweights longer responses through sequence-level equal weighting. To address this tension, we propose Balanced Aggregation (BA), a simple drop-in replacement that computes token-level means separately within the positive and negative subsets and then combines them with sequence-count-based weights. Experiments with Qwen2.5-Math-7B and Qwen3-1.7B on DAPO-17k and Polaris, evaluated on six reasoning and coding benchmarks, show that BA consistently improves training stability and final performance over standard token and sequence aggregation. Our analysis further shows that the relative effectiveness of token and sequence aggregation is largely governed by response-length variation and the positive-negative length gap, highlighting aggregation as a critical design dimension in GRPO-style RLVR.</p> - https://arxiv.org/abs/2605.04077 - Tue, 14 Apr 2026 00:00:00 +0000 - - - MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills - https://arxiv.org/abs/2604.20441 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.20441.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yingyong Hou, Xinyuan Lao, Huimei Wang, Qianyu Yao, Wei Chen, Bocheng Huang, Fei Sun, Yuxian Lv, Weiqi Lei, Xueqian Wen, Pengfei Xia, Zhujun Tan, Shengyang Xie</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Background: Agent skills are increasingly deployed as modular, reusable capability units in AI agent systems. Medical research agent skills require safeguards beyond general-purpose evaluation, including scientific integrity, methodological validity, reproducibility, and boundary safety. This study developed and preliminarily evaluated a domain-specific audit framework for medical research agent skills, with a focus on reliability against expert review. Methods: We developed MedSkillAudit (skill-auditor@1.0), a layered framework assessing skill release readiness before deployment. We evaluated 75 skills across five medical research categories (15 per category). Two experts independently assigned a quality score (0-100), an ordinal release disposition (Production Ready / Limited Release / Beta Only / Reject), and a high-risk failure flag. System-expert agreement was quantified using ICC(2,1) and linearly weighted Cohen's kappa, benchmarked against the human inter-rater baseline. Results: The mean consensus quality score was 72.4 (SD = 13.0); 57.3% of skills fell below the Limited Release threshold. MedSkillAudit achieved ICC(2,1) = 0.449 (95% CI: 0.250-0.610), exceeding the human inter-rater ICC of 0.300. System-consensus score divergence (SD = 9.5) was smaller than inter-expert divergence (SD = 12.4), with no directional bias (Wilcoxon p = 0.613). Protocol Design showed the strongest category-level agreement (ICC = 0.551); Academic Writing showed a negative ICC (-0.567), reflecting a structural rubric-expert mismatch. Conclusions: Domain-specific pre-deployment audit may provide a practical foundation for governing medical research agent skills, complementing general-purpose quality checks with structured audit workflows tailored to scientific use cases.</p> - https://arxiv.org/abs/2604.20441 - Wed, 22 Apr 2026 00:00:00 +0000 - - - OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models - https://arxiv.org/abs/2605.00877 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00877.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yida Xue, Ningyu Zhang, Tingwei Wu, Zhe Ma, Daxiong Ji, Zhao Wang, Guozhou Zheng, Huajun Chen</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> The vast and underexplored ocean plays a critical role in regulating global climate and supporting marine biodiversity, yet artificial intelligence has so far delivered limited impact in this domain due to a fundamental data bottleneck. Specifically, ocean data are highly fragmented across disparate sources and inherently exhibit multi-modal, high-noise, and weakly labeled characteristics, lacking unified schemas and semantic alignment. Although Multimodal Large Language Models (MLLMs) have achieved remarkable success in general domains, their application to ocean science remains severely constrained by the absence of large-scale, well-aligned multimodal datasets tailored to marine environments. To bridge this gap, we introduce OceanPile, a large-scale multimodal corpus designed for ocean foundation models. It comprises three key components: OceanCorpus, a unified collection integrating sonar data, underwater imagery, marine science visuals, and scientific text from diverse authoritative sources; OceanInstruction, a high-quality instruction dataset synthesized via a novel pipeline guided by a hierarchical Ocean Concept Knowledge Graph; and OceanBenchmark, a manually curated evaluation benchmark for rigorous assessment. We establish a multi-stage quality control process to ensure scientific validity and alignment across modalities. Experimental validation demonstrates significant performance improvements for models trained on our data. All datasets are publicly released to advance the field of marine artificial intelligence and empower domain-specific MLLMs.</p> - https://arxiv.org/abs/2605.00877 - Sat, 25 Apr 2026 00:00:00 +0000 - - - Diffusion Model as a Generalist Segmentation Learner - https://arxiv.org/abs/2604.24575 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24575.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoxiao Wang, Antao Xiang, Haiyang Sun, Peilin Sun, Changhao Pan, Yifu Chen, Minjie Hong, Weijie Wang, Shuang Chen, Yue Chen, Zhou Zhao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors. In this paper, we demonstrate that these priors can be utilized for text-conditioned semantic and open-vocabulary segmentation, and this approach can be generalized to various downstream tasks to make a general-purpose diffusion segmentation framework. Concretely, we introduce DiGSeg (Diffusion Models as a Generalist Segmentation Learner), which repurposes a pretrained diffusion model into a unified segmentation framework. Our approach encodes the input image and ground-truth mask into the latent space and concatenates them as conditioning signals for the diffusion U-Net. A parallel CLIP-aligned text pathway injects language features across multiple scales, enabling the model to align textual queries with evolving visual representations. This design transforms an off-the-shelf diffusion backbone into a universal interface that produces structured segmentation masks conditioned on both appearance and arbitrary text prompts. Extensive experiments demonstrate state-of-the-art performance on standard semantic segmentation benchmarks, as well as strong open-vocabulary generalization and cross-domain transfer to medical, remote sensing, and agricultural scenarios-without domain-specific architectural customization. These results indicate that modern diffusion backbones can serve as generalist segmentation learners rather than pure generators, narrowing the gap between visual generation and visual understanding.</p> - https://arxiv.org/abs/2604.24575 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Soft Anisotropic Diagrams for Differentiable Image Representation - https://arxiv.org/abs/2604.21984 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.21984.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Laki Iinbor, Zhiyang Dou, Wojciech Matusik</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We introduce Soft Anisotropic Diagrams (SAD), an explicit and differentiable image representation parameterized by a set of adaptive sites in the image plane. In SAD, each site specifies an anisotropic metric and an additively weighted distance score, and we compute pixel colors as a softmax blend over a small per-pixel top-K subset of sites. We induce a soft anisotropic additively weighted Voronoi partition (i.e., an Apollonius diagram) with learnable per-site temperatures, preserving informative gradients while allowing clear, content-aligned boundaries and explicit ownership. Such a formulation enables efficient rendering by maintaining a per-query top-K map that approximates nearest neighbors under the same shading score, allowing GPU-friendly, fixed-size local computation. We update this list using our top-K propagation scheme inspired by jump flooding, augmented with stochastic injection to provide probabilistic global coverage. Training follows a GPU-first pipeline with gradient-weighted initialization, Adam optimization, and adaptive budget control through densification and pruning. Across standard benchmarks, SAD consistently outperforms Image-GS and Instant-NGP at matched bitrate. On Kodak, SAD reaches 46.0 dB PSNR with 2.2 s encoding time (vs. 28 s for Image-GS), and delivers 4-19 times end-to-end training speedups over state-of-the-art baselines. We demonstrate the effectiveness of SAD by showcasing the seamless integration with differentiable pipelines for forward and inverse problems, efficiency of fast random access, and compact storage.</p> - https://arxiv.org/abs/2604.21984 - Mon, 27 Apr 2026 00:00:00 +0000 - - - From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills - https://arxiv.org/abs/2604.24026 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24026.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiliang Liang, Hansi Wang, Zhong Liang, Yang Liu</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> LLM agents increasingly rely on reusable skills, capability packages that combine instructions, control flow, constraints, and tool calls. In most current agent systems, however, skills are still represented by text-heavy artifacts, including SKILL.md-style documents and structured records whose machine-usable evidence remains embedded largely in natural-language descriptions. This poses a challenge for skill-centered agent systems: managing skill collections and using skills to support agent both require reasoning over invocation interfaces, execution structure, and concrete side effects that are often entangled in a single textual surface. An explicit representation of skill knowledge may therefore help make these artifacts easier for machines to acquire and leverage. Drawing on Memory Organization Packets, Script Theory, and Conceptual Dependency from Schank and Abelson's classical work on linguistic knowledge representation, we introduce what is, to our knowledge, the first structured representation for agent skill artifacts that disentangles skill-level scheduling signals, scene-level execution structure, and logic-level action and resource-use evidence: the Scheduling-Structural-Logical (SSL) representation. We instantiate SSL with an LLM-based normalizer and evaluate it on a corpus of skills in two tasks, Skill Discovery and Risk Assessment, and superiorly outperform the text-only baselines: in Skill Discovery, SSL improves MRR from 0.573 to 0.707; in Risk Assessment, it improves macro F1 from 0.744 to 0.787. These findings reveal that explicit, source-grounded structure makes agent skills easier to search and review. They also suggest that SSL is best understood as a practical step toward more inspectable, reusable, and operationally actionable skill representations for agent systems, rather than as a finished standard or an end-to-end mechanism for managing and using skills.</p> - https://arxiv.org/abs/2604.24026 - Mon, 27 Apr 2026 00:00:00 +0000 - - - X2SAM: Any Segmentation in Images and Videos - https://arxiv.org/abs/2605.00891 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00891.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Wang, Limeng Qiao, Chi Zhang, Lin Ma, Guanglu Wan, Xiangyuan Lan, Xiaodan Liang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have demonstrated strong image-level visual understanding and reasoning, yet their pixel-level perception across both images and videos remains limited. Foundation segmentation models such as the SAM series produce high-quality masks, but they rely on low-level visual prompts and cannot natively interpret complex conversational instructions. Existing segmentation MLLMs narrow this gap, but are usually specialized for either images or videos and rarely support both textual and visual prompts in one interface. We introduce X2SAM, a unified segmentation MLLM that extends any-segmentation capabilities from images to videos. Given conversational instructions and visual prompts, X2SAM couples an LLM with a Mask Memory module that stores guided vision features for temporally consistent video mask generation. The same formulation supports generic, open-vocabulary, referring, reasoning, grounded conversation generation, interactive, and visual grounded segmentation across image and video inputs. We further introduce the Video Visual Grounded (V-VGD) segmentation benchmark, which evaluates whether a model can segment object tracks in videos from interactive visual prompts. With a unified joint training strategy over heterogeneous image and video datasets, X2SAM delivers strong video segmentation performance, remains competitive on image segmentation benchmarks, and preserves general image and video chat ability.</p> - https://arxiv.org/abs/2605.00891 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Prior-Aligned Data Cleaning for Tabular Foundation Models - https://arxiv.org/abs/2604.25154 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25154.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Laure Berti-Equille</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Tabular Foundation Models (TFMs) achieve state-of-the-art zero-shot accuracy on small tabular datasets by meta-learning over synthetic data-generating processes -- making them highly attractive for practitioners who cannot afford large annotated corpora. However, their in-context learning mechanism assumes approximately clean inputs: missing values, outliers, and duplicates in the real-world data create a prior mismatch that degrades both accuracy and confidence calibration simultaneously. Correcting this mismatch requires sequential decisions over cleaning operators whose interactions no static preprocessing rule can anticipate -a natural fit for reinforcement learning~(RL). We introduce L2C2, the first deep RL framework framing tabular data cleaning as prior alignment: a learned policy sequences operators to minimize the distributional gap between dirty input and the TFM's synthetic prior. Six experiments on ten OpenML benchmark datasets establish: 1) three of seven reward designs collapse to degenerate trivial cleaning strategies -- principled reward engineering is scientifically non-trivial; 2) the novel TFMAwareReward reward we propose selects structurally distinct pipelines on 4/10 datasets and achieves higher TabPFN accuracy on those diverging cases (mean 0.851 vs. 0.843; Wilcoxon p=0.063, n=4) while never underperforming; 3) parameterized cleaning actions improve best-found pipeline reward on 9/10 datasets (Wilcoxon p=0.004); and 4) a policy pre-trained on one single source dataset exceeds scratch training at the 2,000-step fine-tuning checkpoint on all three held-out datasets (up to +28.8% after full fine-tuning) demonstrating cross-dataset transfer of prior-alignment knowledge. These findings establish that prior alignment is a principled data preparation strategy for TFM deployment on real-world tabular data.</p> - https://arxiv.org/abs/2604.25154 - Tue, 28 Apr 2026 00:00:00 +0000 - - - How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum - https://arxiv.org/abs/2604.25907 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25907.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chu-Cheng Lin, Eugene Ie</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Adapting reasoning models to new tasks during post-training with only output-level supervision stalls under reinforcement learning from verifiable rewards (RLVR) when the initial success probability p_0 is small. Using the Tsallis q-logarithm, we define a loss family J_Q that interpolates between RLVR (at q{=}0, the exploitation pole) and the log-marginal-likelihood over latent trajectories (at q{=}1, the density-estimation pole). All members share the same per-example gradient direction, differing only by a scalar amplification P_{θ^{-q}} that reweights each instance independently of the learning rate. This amplification is the mechanism that addresses cold-start stalling: under gradient flow, the exploitation pole requires Ω(1{p_0}) time to escape cold start, while the density-estimation pole escapes in Θbig(log(1{p_0})big); intermediate q trades escape speed against noise memorization. Because P_θ is intractable, we derive two Monte Carlo estimators from the two factorizations of the gradient: Gradient-Amplified RL (GARL) samples from the prior and amplifies the RL gradient, and Posterior-Attenuated Fine-Tuning (PAFT) importance-resamples from the posterior and runs standard SFT. Both have bias Obig(q{M P_θ^{q+1}}big); GARL has lower variance, PAFT has semantically coherent gradients. On FinQA, HotPotQA, and MuSiQue, GARL at q{=}0.75 substantially mitigates cold-start stalling, escaping cold start where GRPO fails entirely. In warm start, GARL at low q dominates FinQA where training is stable; on HotPotQA and MuSiQue, GARL destabilizes during training, and PAFT at q{=}0.75 provides stable gradients (best overall on HotPotQA at 47.9 maj@16, +14.4 over GRPO).</p> - https://arxiv.org/abs/2604.25907 - Tue, 28 Apr 2026 00:00:00 +0000 - - - HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help? - https://arxiv.org/abs/2604.09408 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.09408.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohamed Elfeki, Tu Trinh, Kelvin Luu, Guangze Luo, Nathan Hunt, Ernesto Montoya, Nandan Marwaha, Yannis He, Charles Wang, Fernando Crabedo, Alessa Castilo, Bing Liu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Frontier coding agents solve complex tasks when given complete context but collapse when specifications are incomplete or ambiguous. The bottleneck is not raw capability, but judgment: knowing when to act autonomously and when to ask for help. Current benchmarks are blind to this failure mode. They supply unambiguous detailed instructions and solely reward execution correctness, so an agent that makes a lucky guess for a missing requirement will score identically to one that would have asked to be certain. We present HiL-Bench (Human-in-the-Loop Benchmark) to measure this selective escalation skill. Each task contains human-validated blockers (missing information, ambiguous requests, contradictory information) that surface only through progressive exploration, not upfront inspection. Our core metric, Ask-F1, the harmonic mean of question precision and blocker recall, captures the tension between over-asking and silent guessing; its structure architecturally prevents gaming through question spam. Evaluation across SWE and text-to-SQL domains reveals a large universal judgment gap: no frontier model recovers more than a fraction of its full-information performance when deciding whether to ask. Failure analysis identifies three key help-seeking patterns: overconfident wrong beliefs with no gap detection; high uncertainty detection yet persistent errors; broad, imprecise escalation without self-correction. These consistent patterns confirm poor help-seeking is a model-level flaw, not task-specific. RL training on shaped Ask-F1 reward shows judgment is trainable: a 32B model improves both help-seeking quality and task pass rate, with gains that transfer across domains. The model does not learn domain-specific heuristics for when to ask; it learns to detect unresolvable uncertainty and act on it.</p> - https://arxiv.org/abs/2604.09408 - Wed, 29 Apr 2026 00:00:00 +0000 - - - Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models - https://arxiv.org/abs/2604.27124 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27124.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vijay Sadashivaiah, Georgios Dasoulas, Judith Mueller, Soumya Ghosh</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Training stable biological foundation models requires rethinking attention mechanisms: we find that using sigmoid attention as a drop in replacement for softmax attention a) produces better learned representations: on six diverse single-cell datasets, sigmoid achieves 25% higher cell-type separation, better cell-type cohesion metrics, and lower validation loss, b) faster training, models with sigmoid attention train up to 10% faster than their softmax counterparts, and c) more stable training by eliminating inherent sources of instability in softmax attention. We establish that sigmoid attention has globally bounded derivatives (leq 0.25) as opposed to softmax, and a diagonal Jacobian structure in contrast with softmax's dense coupling, which together help alleviate training instabilities. In stress tests on 160M-parameter bidirectional attention models trained without gradient clipping on 8K-token sequences, softmax diverges catastrophically, with gradients exploding by four orders of magnitude, while sigmoid remains stable. Finally, we implement and open-source TritonSigmoid, an efficient GPU kernel that achieves 515 TFLOPS on H100 GPUs, outperforming both FlashAttention-2 and FlashSigmoid, with native padding support, which is essential for biological sequences. Our results establish sigmoid attention as both theoretically grounded and empirically superior for biological foundation models. Code is available at https://github.com/MSDLLCpapers/triton-sigmoid</p> - https://arxiv.org/abs/2604.27124 - Wed, 29 Apr 2026 00:00:00 +0000 - - - ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models - https://arxiv.org/abs/2405.13729 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2405.13729.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Xu, Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Shiqing Xin, Changhe Tu, Taku Komura, Wenping Wang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, additional attributes are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes can be insufficiently covered by existing training schemes of diffusion generative models, potentially limiting test time performance. We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc. Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, ComboStoc enables a new way of test time generation which uses asynchronous time steps for different dimensions and attributes, thus allowing for varying degrees of control over them. Our code is available at: https://github.com/Xrvitd/ComboStoc</p> - https://arxiv.org/abs/2405.13729 - Wed, 29 Apr 2026 00:00:00 +0000 - - - Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions - https://arxiv.org/abs/2604.23774 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23774.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Etai Sella, Hao Phung, Nitay Amiel, Or Litany, Or Patashnik, Hadar Averbuch-Elor</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Text-based 2D image editing models have recently reached an impressive level of maturity, motivating a growing body of work that heavily depends on these models to drive 3D edits. While effective for appearance-based modifications, such 2D-centric 3D editing pipelines often struggle with fine-grained 3D editing, where localized structural changes must be applied while strictly preserving an object's overall identity. To address this limitation, we propose Prox-E, a training-free framework that enables fine-grained 3D control through an explicit, primitive-based geometric abstraction. Our framework first abstracts an input 3D shape into a compact set of geometric primitives. A pretrained vision-language model (VLM) then edits this abstraction to specify primitive-level changes. These structural edits are subsequently used to guide a 3D generative model, enabling fine-grained, localized modifications while preserving unchanged regions of the original shape. Through extensive experiments, we demonstrate that our method consistently balances identity preservation, shape quality, and instruction fidelity more effectively than various existing approaches, including 2D-based 3D editors and training-based methods.</p> - https://arxiv.org/abs/2604.23774 - Wed, 29 Apr 2026 00:00:00 +0000 - - - Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction - https://arxiv.org/abs/2604.27221 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxuan Huang, Yihang Chen, Zhiyuan He, Yuxiang Chen, Ka Yiu Lee, Huichi Zhou, Weilin Luo, Meng Fang, Jun Wang</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current systems struggle on both fronts. Breadth-oriented tasks demand schema-aligned outputs with wide coverage and cross-entity consistency, while depth-oriented tasks require coherent reasoning over long, branching search trajectories. We introduce Web2BigTable, a multi-agent framework for web-to-table search that supports both regimes. Web2BigTable adopts a bi-level architecture in which an upper-level orchestrator decomposes the task into sub-problems and lower-level worker agents solve them in parallel. Through a closed-loop run--verify--reflect process, the framework jointly improves decomposition and execution over time via persistent, human-readable external memory, with self-evolving updates to each single-agent. During execution, workers coordinate through a shared workspace that makes partial findings visible, allowing them to reduce redundant exploration, reconcile conflicting evidence, and adapt to emerging coverage gaps. Web2BigTable sets a new state of the art on WideSearch, reaching an Avg@4 Success Rate of 38.50 (7.5times the second best at 5.10), Row F1 of 63.53 (+25.03 over the second best), and Item F1 of 80.12 (+14.42 over the second best). It also generalises to depth-oriented search on XBench-DeepSearch, achieving 73.0 accuracy. Code is available at https://github.com/web2bigtable/web2bigtable.</p> - https://arxiv.org/abs/2604.27221 - Wed, 29 Apr 2026 00:00:00 +0000 - - - Assessing Pancreatic Ductal Adenocarcinoma Vascular Invasion: the PDACVI Benchmark - https://arxiv.org/abs/2604.27582 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27582.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> M. Riera-Marín, O. K. Sikha, J. Rodríguez-Comas, M. S. May, T. Kirscher, X. Coubez, P. Meyer, S. Faisan, Z. Pan, X. Zhou, X. Liang, C. Hémon, V. Boussot, J. -L. Dillenseger, J. -C. Nunes, K. -C. Kahl, C. Lüth, J. Traub, P. -H. Conze, M. M. Duh, A. Aubanell, R. de Figueiredo Cardoso, S. Egger-Hackenschmidt, J. García-López, M. A. González-Ballester, A. Galdran</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Surgical resection remains the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC), and eligibility depends on accurate assessment of vascular invasion (VI), i.e., tumor extension into adjacent critical vessels. Despite its importance for preoperative staging and surgical planning, computational VI assessment remains underexplored. Two major challenges are the lack of public datasets and the diagnostic ambiguity at the tumor-vessel interface, which leads to substantial inter-rater variability even among expert radiologists. To address these limitations, we introduce the CURVAS-PDACVI Dataset and Challenge, an open benchmark for uncertainty-aware AI in PDAC staging based on a densely annotated dataset with five independent expert annotations per scan. We also propose a multi-metric evaluation framework that extends beyond spatial overlap to include probabilistic calibration and VI assessment. Evaluation of six state-of-the-art methods shows that strong global volumetric overlap does not necessarily translate into reliable performance at clinically critical tumor-vessel interfaces. In particular, methods optimized for binary segmentation perform competitively on average overlap metrics, but often degrade in high-complexity cases with low expert consensus, either collapsing in volume or overextending at uncertain boundaries. In contrast, methods that model inter-rater disagreement produce better calibrated probabilistic maps and show greater robustness in these ambiguous cases. The benchmark highlights the limitations of volumetric accuracy as a proxy for localized surgical utility, motivating uncertainty-aware probabilistic models for preoperative decision-making.</p> - https://arxiv.org/abs/2604.27582 + World Model for Robot Learning: A Comprehensive Survey + https://arxiv.org/abs/2605.00080 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00080.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bohan Hou, Gen Li, Jindou Jia, Tuo An, Xinying Guo, Sicong Leng, Haoran Geng, Yanjie Ze, Tatsuya Harada, Philip Torr, Oier Mees, Marc Pollefeys, Zhuang Liu, Jiajun Wu, Pieter Abbeel, Jitendra Malik, Yilun Du, Jianfei Yang</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planning, simulation, evaluation, data generation, and have advanced rapidly with the rise of foundation models and large-scale video generation. However, the literature remains fragmented across architectures, functional roles, and embodied application domains. To address this gap, we present a comprehensive review of world models from a robot-learning perspective. We examine how world models are coupled with robot policies, how they serve as learned simulators for reinforcement learning and evaluation, and how robotic video world models have progressed from imagination-based generation to controllable, structured, and foundation-scale formulations. We further connect these ideas to navigation and autonomous driving, and summarize representative datasets, benchmarks, and evaluation protocols. Overall, this survey systematically reviews the rapidly growing literature on world models for robot learning, clarifies key paradigms and applications, and highlights major challenges and future directions for predictive modeling in embodied agents. To facilitate continued access to newly emerging works, benchmarks, and resources, we will maintain and regularly update the accompanying GitHub repository alongside this survey.</p> + https://arxiv.org/abs/2605.00080 Thu, 30 Apr 2026 00:00:00 +0000 - MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks - https://arxiv.org/abs/2604.27818 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27818.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jona te Lintelo, Lichao Wu, Marina Krček, Sengim Karayalçin, Stjepan Picek</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However, this sparse activation paradigm also introduces new safety challenges. Since only a subset of experts is engaged for each input, model behavior becomes coupled to routing decisions, yielding a difficult-to-control mechanism that can vary across safety-relevant scenarios. At the same time, adapting model behavior through full fine-tuning or retraining is costly, especially when developers need to rapidly configure the same model for different safety objectives. We present MASCing (MoE Activation Steering Configuration), the first framework that enables flexible reconfiguration of MoE behavior across diverse safety scenarios without retraining. MASCing uses an LSTM-based surrogate model to capture cross-layer routing dependencies and map routing logits to downstream behaviors. It then optimizes a steering matrix to identify behavior-relevant expert circuits and, at inference time, applies steering masks to the routing gates to override expert selection. This enables targeted enhancement or suppression of specific behaviors while preserving general language utility. To demonstrate its reconfigurability, we apply MASCing to two different safety-related objectives and observe consistent gains with negligible overhead across seven open-source MoE models. For multi-turn jailbreak defense, it improves the average defense success rate from 52.5% to 83.9%, with gains of up to 89.2%. For adult-content generation, MASCing enables models to comply with such requests that would otherwise be refused, increasing the average generation success rate from 52.6% to 82.0%, with gains of up to 93.0%. These results establish MASCing as a practical, lightweight, and flexible framework for scenario-specific safety reconfiguration in MoE models.</p> - https://arxiv.org/abs/2604.27818 + RouteProfile: Elucidating the Design Space of LLM Profiles for Routing + https://arxiv.org/abs/2605.00180 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00180.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingjun Xu, Hongji Pu, Tao Feng, Haozhen Zhang, Jiaxuan You, Ge Liu</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> As the large language model (LLM) ecosystem expands, individual models exhibit varying capabilities across queries, benchmarks, and domains, motivating the development of LLM routing. While prior work has largely focused on router mechanism design, LLM profiles, which capture model capabilities, remain underexplored. In this work, we ask: How does LLM profile design affect routing performance across different routers? Addressing this question helps clarify the role of profiles in routing, disentangle profile design from router design, and enable fairer comparison and more principled development of routing systems. To this end, we view LLM profiling as a structured information integration problem over heterogeneous interaction histories. We develop a general design space of LLM profiles, named RouteProfile, along four key dimensions: organizational form, representation type, aggregation depth, and learning configuration. Through systematic evaluation across three representative routers under both standard and new-LLM generalization settings, we show that: (1) structured profiles consistently outperform flat ones; (2) query-level signals are more reliable than coarse domain-level signals; and (3) generalization to newly introduced models benefits most from structured profiles under trainable configurations. Overall, our work highlights LLM profile design as an important direction for future routing research.</p> + https://arxiv.org/abs/2605.00180 Thu, 30 Apr 2026 00:00:00 +0000 - Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO - https://arxiv.org/abs/2604.27488 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27488.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Tian, Jiawei Chen, Lifan Zheng, Mingxiang Tao, Xinyi Zeng, Zhaoxia Yin, Hang Su, Xian Sun</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We introduce Skills-Coach, a novel automated framework designed to significantly enhance the self-evolution of skills within Large Language Model (LLM)-based agents. Addressing the current fragmentation of the skill ecosystem, Skills-Coach explores the boundaries of skill capabilities, thereby facilitating the comprehensive competency coverage essential for intelligent applications. The framework comprises four core modules: a Diverse Task Generation Module that systematically creates a comprehensive test suite for various skills; a Lightweight Optimization Module dedicated to optimizing skill prompts and their corresponding code; a Comparative Execution Module facilitating the execution and evaluation of both original and optimized skills; and a Traceable Evaluation Module, which rigorously evaluates performance against specified criteria. Skills-Coach offers flexible execution options through its virtual and real modes. To validate its efficacy, we introduce Skill-X, a comprehensive benchmark dataset consisting of 48 diverse skills. Experimental results demonstrate that Skills-Coach achieves significant performance improvements in skill capability across a wide range of categories, highlighting its potential to advance the development of more robust and adaptable LLM-based agents.</p> - https://arxiv.org/abs/2604.27488 - Thu, 30 Apr 2026 00:00:00 +0000 - - - When Do Diffusion Models learn to Generate Multiple Objects? - https://arxiv.org/abs/2605.00273 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00273.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujin Jeong, Arnas Uselis, Iro Laina, Seong Joon Oh, Anna Rohrbach</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how much of this limitation arises from the data itself. To disentangle data effects, we consider two regimes across different dataset sizes: (1) concept generalization, where each individual concept is observed during training under potentially imbalanced data distributions, and (2) compositional generalization, where specific combinations of concepts are systematically held out. To study these regimes, we introduce mosaic (Multi-Object Spatial relations, AttrIbution, Counting), a controlled framework for dataset generation. By training diffusion models on mosaic, we find that scene complexity plays a dominant role rather than concept imbalance, and that counting is uniquely difficult to learn in low-data regimes. Moreover, compositional generalization collapses as more concept combinations are held out during training. These findings highlight fundamental limitations of diffusion models and motivate stronger inductive biases and data design for robust multi-object compositional generation.</p> - https://arxiv.org/abs/2605.00273 - Thu, 30 Apr 2026 00:00:00 +0000 - - - WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments - https://arxiv.org/abs/2604.27776 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27776.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinchao Li, Yunxin Li, Chenrui Zhao, Zhenran Xu, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating across multiple applications to accomplish complex profession-specific workflows. To bridge this gap, we present a computer-use benchmark in cross-application workflows, named WindowsWorld, designed to systematically assess GUI Agents on complex multi-step tasks that mirror real-world professional activities. Our methodology uses a multi-agent framework steered by 16 occupations to generate four difficulty-level tasks with intermediate inspection, which are then refined by human review and executed in a simulated environment. The resulting benchmark contains 181 tasks with an average of 5.0 sub-goals across 17 common desktop applications, of which 78% are inherently multi-application. Experimental results of leading large models and agents show that: 1) All computer-use agents perform poorly on multi-application tasks (< 21% success rate), far below the performance of simple single-app tasks; 2) They largely fail at tasks requiring conditional judgment and reasoning across geq 3 applications, stalling at early sub-goals; 3) Low execution efficiency, where tasks often fail despite far exceeding human step limits. Code, benchmark data, and evaluation resources are available at github.com/HITsz-TMG/WindowsWorld.</p> - https://arxiv.org/abs/2604.27776 - Thu, 30 Apr 2026 00:00:00 +0000 - - - Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling - https://arxiv.org/abs/2604.28075 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28075.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ansar Aynetdinov, Patrick Haller, Alan Akbik</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Recent research has shown that filtering massive English web corpora into high-quality subsets significantly improves training efficiency. However, for high-resource non-English languages like German, French, or Japanese, aggressive filtering creates a strategic dilemma: should practitioners prioritize diversity by training once on large amounts of lightly filtered web data, or prioritize quality by strictly filtering for a high-quality core and repeating it over multiple epochs? We investigate this trade-off for German by constructing hierarchical quality filters applied to 500M web documents, comparing multi-epoch training on the filtered subsets against single-pass training on a diverse corpus. Our experiments across multiple model scales and token budgets show that repeating high-quality data consistently outperforms single-pass training on larger, less filtered sets. Notably, the performance gap persists even after 7 epochs. Our findings suggest that for non-English LLMs, semantic concentration through quality filtering offers a more viable path to efficient language modeling than simply maximizing unique data volume. We release our German language models (called Boldt), as well as our cleaned evaluation benchmarks to the research community. Our experiments indicate that they achieve state-of-the-art results despite training on 10-360x fewer tokens than comparable models.</p> - https://arxiv.org/abs/2604.28075 - Thu, 30 Apr 2026 00:00:00 +0000 - - - MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction - https://arxiv.org/abs/2604.27393 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27393.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junbo Cui, Bokai Xu, Chongyi Wang, Tianyu Yu, Weiyue Sun, Yingjing Xu, Tianran Wang, Zhihui He, Wenshuo Ma, Tianchi Cai, Jiancheng Gui, Luoyuan Zhang, Xian Sun, Fuwei Huang, Moye Chen, Zhuo Lin, Hanyu Liu, Qingxin Gui, Qingzhe Han, Yuyang Wen, Huiping Liu, Rongkang Wang, Yaqi Zhang, Hongliang Wei, Chi Chen, You Li, Kechen Fang, Jie Zhou, Yuxuan Li, Guoyang Zeng, Chaojun Xiao, Yankai Lin, Xu Han, Maosong Sun, Zhiyuan Liu, Yuan Yao</p><p><b>Upvotes:</b> 60</p><p><b>Summary:</b> Recent progress in multimodal large language models (MLLMs) has brought AI capabilities from static offline data processing to real-time streaming interaction, yet they still remain far from human-level multimodal interaction. The key bottlenecks are no longer modality coverage or latency alone, but the interaction paradigm itself. First, perception and response are still separated into alternating phases, preventing models from incorporating new inputs for timely adjustment during generation. Second, most current models remain reactive, responding only to explicit user requests instead of acting proactively in the evolving multimodal environment. We present MiniCPM-o 4.5, our latest effort towards human-like multimodal interaction, which mitigates these gaps by real-time full-duplex omni-modal interaction. It can see, listen, and speak simultaneously in real-time, while also exhibiting proactive behaviors such as issuing reminders or comments based on its continuous understanding of the live scene. The key technique behind MiniCPM-o 4.5 is Omni-Flow, a unified streaming framework that aligns omni-modal inputs and outputs along a shared temporal axis. This formulation converts conventional turn-based interaction into a full-duplex, time-aligned process, enabling simultaneous perception and response and allowing proactive behavior to arise within the same framework. With a total of 9B parameters, MiniCPM-o 4.5 approaches Gemini 2.5 Flash in vision-language capabilities, delivering state-of-the-art open-source performance at its scale. It also surpasses Qwen3-Omni-30B-A3B in omni-modal understanding and delivers better speech generation, with significantly higher computation efficiency. Driven by its efficient architecture design and inference optimization, the model can perform real-time full-duplex omni-modal interaction on edge devices with less than 12GB RAM cost.</p> - https://arxiv.org/abs/2604.27393 - Thu, 30 Apr 2026 00:00:00 +0000 - - - HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation - https://arxiv.org/abs/2604.28196 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28196.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Zhou, Dingkang Liang, Xiwu Chen, Feiyang Tan, Dingyuan Zhang, Hengshuang Zhao, Xiang Bai</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominantly focus on future scene generation, often overlooking comprehensive 3D scene understanding. Conversely, while Large Language Models (LLMs) demonstrate impressive reasoning capabilities, they lack the capacity to predict future geometric evolution, creating a significant disparity between semantic interpretation and physical simulation. To bridge this gap, we propose HERMES++, a unified driving world model that integrates 3D scene understanding and future geometry prediction within a single framework. Our approach addresses the distinct requirements of these tasks through synergistic designs. First, a BEV representation consolidates multi-view spatial information into a structure compatible with LLMs. Second, we introduce LLM-enhanced world queries to facilitate knowledge transfer from the understanding branch. Third, a Current-to-Future Link is designed to bridge the temporal gap, conditioning geometric evolution on semantic context. Finally, to enforce structural integrity, we employ a Joint Geometric Optimization strategy that integrates explicit geometric constraints with implicit latent regularization to align internal representations with geometry-aware priors. Extensive evaluations on multiple benchmarks validate the effectiveness of our method. HERMES++ achieves strong performance, outperforming specialist approaches in both future point cloud prediction and 3D scene understanding tasks. The model and code will be publicly released at https://github.com/H-EmbodVis/HERMESV2.</p> - https://arxiv.org/abs/2604.28196 - Thu, 30 Apr 2026 00:00:00 +0000 - - - Healthcare AI GYM for Medical Agents - https://arxiv.org/abs/2605.02943 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minbyul Jeong</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Clinical reasoning demands multi-step interactions -- gathering patient history, ordering tests, interpreting results, and making safe treatment decisions -- yet a unified training environment provides the breadth of clinical domains and specialized tools to train generalizable medical AI agents through reinforcement learning remains elusive. We present a comprehensive empirical study of multi-turn agentic RL for medical AI, built on , a gymnasium-compatible environment spanning 10 clinical domains with 3.6K+ tasks, 135 domain-specific tools, and a knowledge base of 828K medical passages. Our analysis reveals that agentic multi-turn structure degrades into verbose single-turn monologues, characterized by monotonic length explosion and a simultaneous erosion of tool-use frequency. We characterize how this collapse, alongside distillation instability, stems from the misalignment of sparse terminal rewards with sequential clinical trajectories. We find that vanilla GRPO achieves strong final accuracy on some benchmarks but suffers from training instability, evidenced by significant oscillations in response length and prolonged convergence periods. To improve training efficiency and stability, we propose Turn-level Truncated On-Policy Distillation (TT-OPD), a self-distillation framework where a gradient-free EMA teacher leverages outcome-privileged information to provide dense, outcome-aware KL regularization at every conversation turn. TT-OPD achieves the best performance on 10 of 18 benchmarks with an average +3.9~pp improvement over the non-RL baseline with faster early convergence, controlled response length, and sustained multi-turn tool use.</p> - https://arxiv.org/abs/2605.02943 - Fri, 01 May 2026 00:00:00 +0000 - - - Recovering Hidden Reward in Diffusion-Based Policies - https://arxiv.org/abs/2605.00623 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00623.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanbiao Ji, Qiuchang Li, Yuting Hu, Shaokai Wu, Wenyuan Xie, Guodong Zhang, Qicheng He, Deyi Ji, Yue Ding, Hongtao Lu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> This paper introduces EnergyFlow, a framework that unifies generative action modeling with inverse reinforcement learning by parameterizing a scalar energy function whose gradient is the denoising field. We establish that under maximum-entropy optimality, the score function learned via denoising score matching recovers the gradient of the expert's soft Q-function, enabling reward extraction without adversarial training. Formally, we prove that constraining the learned field to be conservative reduces hypothesis complexity and tightens out-of-distribution generalization bounds. We further characterize the identifiability of recovered rewards and bound how score estimation errors propagate to action preferences. Empirically, EnergyFlow achieves state-of-the-art imitation performance on various manipulation tasks while providing an effective reward signal for downstream reinforcement learning that outperforms both adversarial IRL methods and likelihood-based alternatives. These results show that the structural constraints required for valid reward extraction simultaneously serve as beneficial inductive biases for policy generalization. The code is available at https://github.com/sotaagi/EnergyFlow.</p> - https://arxiv.org/abs/2605.00623 - Fri, 01 May 2026 00:00:00 +0000 - - - Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation - https://arxiv.org/abs/2605.00529 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00529.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziwen Zhao, Menglin Yang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical indexes to support queries at multiple granularities. However, existing Tree-RAG methods designed for single-document retrieval face critical challenges in scaling to cross-document multi-hop questions: (1) poor distribution adaptability, where k-means clustering introduces noise due to rigid distribution assumptions; (2) structural isolation, as tree indexes lack explicit cross-document connections; and (3) coarse abstraction, which obscures fine-grained details. To address these limitations, we propose Ψ-RAG, a tree-RAG framework with two key components. First, a hierarchical abstract tree index built through an iterative "merging and collapse" process that adapts to data distributions without a priori assumption. Second, a multi-granular retrieval agent that intelligently interacts with the knowledge base with reorganized queries and an agent-powered hybrid retriever. Ψ-RAG supports diverse tasks from token-level question answering to document-level summarization. On cross-document multi-hop QA benchmarks, it outperforms RAPTOR by 25.9% and HippoRAG 2 by 7.4% in average F1 score. Code is available at https://github.com/Newiz430/Psi-RAG.</p> - https://arxiv.org/abs/2605.00529 - Fri, 01 May 2026 00:00:00 +0000 - - - ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning - https://arxiv.org/abs/2605.00380 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00380.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihan Lin, Xiaohan Wang, Jie Cao, Jiajun Chai, Li Wang, Xiaodong Lu, Wei Lin, Ran He, Guojun Yin</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivization of positive rewards. Although methods like Negative Sample Reinforcement (NSR) mitigate this issue by upweighting penalty from negative samples, they may suppress the semantic distributions shared between positive and negative responses. To boost reasoning ability without losing diversity, this paper proposes negative sample projection Residual Reinforcement Learning (ResRL) that decouples similar semantic distributions among positive and negative responses. We theoretically link Lazy Likelihood Displacement (LLD) to negative-positive head-gradient interference and derive a single-forward proxy that upper-bounds representation alignment to guide conservative advantage reweighting. ResRL then projects negative-token hidden representations onto an SVD-based low-rank positive subspace and uses projection residuals to modulate negative gradients, improving reasoning while preserving diversity and outperforming strong baselines on average across twelve benchmarks spanning Mathematics, Code, Agent Tasks, and Function Calling. Notably, ResRL surpasses NSR on mathematical reasoning by 9.4\% in Avg@16 and 7.0\% in Pass@128. Code is available at https://github.com/1229095296/ResRL.git.</p> - https://arxiv.org/abs/2605.00380 - Fri, 01 May 2026 00:00:00 +0000 - - - Trees to Flows and Back: Unifying Decision Trees and Diffusion Models - https://arxiv.org/abs/2605.00414 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00414.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sai Niranjan Ramachandran, Suvrit Sra</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work unifies the two by establishing a crisp mathematical correspondence between hierarchical decision trees and diffusion processes in appropriate limiting regimes. Our unification reveals a shared optimization principle: Global Trajectory Score Matching (GTSM), for which gradient boosting (in an idealized version) is asymptotically optimal. We underscore the conceptual value of our work through two key practical instantiations: \treeflow, which achieves competitive generation quality on tabular data with higher fidelity and a 2\times computational speedup, and \dsmtree, a novel distillation method that transfers hierarchical decision logic into neural networks, matching teacher performance within 2\% on many benchmarks.</p> - https://arxiv.org/abs/2605.00414 - Fri, 01 May 2026 00:00:00 +0000 - - - End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer - https://arxiv.org/abs/2605.00503 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00503.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenda Chu, Bingliang Zhang, Jiaqi Han, Yizhuo Li, Linjie Yang, Yisong Yue, Qiushan Guo</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision from generation results to the tokenizer. This contrasts with prior two-stage approaches that train tokenizers and generative models separately. We further investigate leveraging vision foundation models to improve 1D tokenizers for autoregressive modeling. Our autoregressive generative model achieves strong empirical results, including a state-of-the-art FID score of 1.48 without guidance on ImageNet 256x256 generation.</p> - https://arxiv.org/abs/2605.00503 - Fri, 01 May 2026 00:00:00 +0000 - - - Learning while Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies - https://arxiv.org/abs/2605.00416 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00416.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Wang, Xinchen Li, Pengwei Xie, Pu Yang, Buqing Nie, Yunuo Cai, Qinglin Zhang, Chendi Qu, Jeffrey Wu, Jianheng Song, Xinlin Ren, Jingshun Huang, Mingjie Pan, Siyuan Feng, Zhi Chen, Jianlan Luo</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Generalist robot policies increasingly benefit from large-scale pretraining, but offline data alone is insufficient for robust real-world deployment. Deployed robots encounter distribution shifts, long-tail failures, task variations, and human correction opportunities that fixed demonstration datasets cannot fully capture. We present Learning While Deploying (LWD), a fleet-scale offline-to-online reinforcement learning framework for continual post-training of generalist Vision-Language-Action (VLA) policies. Starting from a pretrained VLA policy, LWD closes the loop between deployment, shared physical experience, policy improvement, and redeployment by using autonomous rollouts and human interventions collected across a robot fleet. To stabilize learning from heterogeneous, sparse-reward fleet data, LWD combines Distributional Implicit Value Learning (DIVL) for robust value estimation with Q-learning via Adjoint Matching (QAM) for policy extraction in flow-based VLA action generators. We validate LWD on a fleet of 16 dual-arm robots across eight real-world manipulation tasks, including semantic grocery restocking and 3--5 minute long-horizon tasks. A single generalist policy improves as fleet experience accumulates, reaching an average success rate of 95%, with the largest gains on long-horizon tasks.</p> - https://arxiv.org/abs/2605.00416 - Fri, 01 May 2026 00:00:00 +0000 - - - Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning - https://arxiv.org/abs/2605.00347 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00347.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengshuai Shi, Wenzhe Li, Xinran Liang, Yizhou Lu, Wenjia Yang, Ruirong Feng, Seth Karten, Ziran Yang, Zihan Ding, Gabriel Sarch, Danqi Chen, Karthik Narasimhan, Chi Jin</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Given the rapidly growing capabilities of vision-language models (VLMs), extending them to interactive decision-making tasks such as video games has emerged as a promising frontier. However, existing approaches either rely on large-scale supervised fine-tuning (SFT) on human trajectories or apply reinforcement learning (RL) only in relatively short-horizon settings (typically around 20--30 turns). In this work, we study RL-based training of VLMs for long-horizon decision-making in Super Mario Land, a visually grounded environment requiring 100+ turns of interaction with coordinated perception, reasoning, and action. We begin with a systematic investigation of key algorithmic components and propose an adapted variant of PPO with a lightweight turn-level critic, which substantially improves training stability and sample efficiency over critic-free methods such as GRPO and Reinforce++. We further show that pretrained VLMs provide strong action priors, significantly improving sample efficiency during RL training and reducing the need for manual design choices such as action engineering, compared to classical deep RL trained from scratch. Building on these insights, we introduce Odysseus, an open training framework for VLM agents, achieving substantial gains across multiple levels of the game and at least 3 times average game progresses than frontier models. Moreover, the trained models exhibit consistent improvements under both in-game and cross-game generalization settings, while maintaining general-domain capabilities. Overall, our results identify key ingredients for making RL stable and effective in long-horizon, multi-modal settings, and provide practical guidance for developing VLMs as embodied agents.</p> - https://arxiv.org/abs/2605.00347 - Fri, 01 May 2026 00:00:00 +0000 - - - Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance - https://arxiv.org/abs/2605.00553 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00553.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minchan Kwon, Sunghyun Baek, Minseo Kim, Jaemyung Yu, Dongyoon Han, Junmo Kim</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effective and diverse attacks in red-teaming is important, but achieving both is challenging. Generative Flow Networks (GFNs) that perform distribution matching are a promising methods, but they are notorious for training instability and mode collapse. In particular, unstable rewards in red-teaming accelerate mode collapse. We propose Stable-GFN (S-GFN), which eliminates partition function Z estimation in GFN and reduces training instability. S-GFN avoids Z-estimation through pairwise comparisons and employs a robust masking methodology against noisy rewards. Additionally, we propose a fluency stabilizer to prevent the model from getting stuck in local optima that produce gibberish. S-GFN provides more stable training while maintaining the optimal policy of GFN. We demonstrate the overwhelming attack performance and diversity of S-GFN across various settings.</p> - https://arxiv.org/abs/2605.00553 - Fri, 01 May 2026 00:00:00 +0000 - - - Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs - https://arxiv.org/abs/2605.00814 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00814.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Huang, Xiaoye Qu, Yafu Li, Tong Zhu, Zefeng He, Muxin Fu, Daizong Liu, Wei-Long Zheng, Yu Cheng</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a "Visual Signal Dilution" phenomenon, where the accumulation of textual history expands the attention partition function, causing visual attention to decay inversely with generated sequence length. To counteract this, we propose Persistent Visual Memory (PVM), a lightweight learnable module designed to ensure sustained, on-demand visual perception. Integrated as a parallel branch alongside the Feed-Forward Network (FFN) in LVLMs, PVM establishes a distance-agnostic retrieval pathway that directly provides visual embeddings for precise visual perception, thereby structurally mitigating the signal suppression inherent to deep generation. Extensive experiments on Qwen3-VL models demonstrate that PVM brings notable improvements with negligible parameter overhead, delivering consistent average accuracy gains across both 4B and 8B scales, particularly in complex reasoning tasks that demand persistent visual perception. Furthermore, in-depth analysis reveals that PVM can resist length-induced signal decay and accelerate internal prediction convergence.</p> - https://arxiv.org/abs/2605.00814 - Fri, 01 May 2026 00:00:00 +0000 - - - Map2World: Segment Map Conditioned Text to 3D World Generation - https://arxiv.org/abs/2605.00781 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00781.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaeyoung Chung, Suyoung Lee, Jianfeng Xiang, Jiaolong Yang, Kyoung Mu Lee</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> 3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world generation have shown promising results; however, these methods are constrained by grid layouts and suffer from inconsistencies in object scale throughout the entire world. In this work, we introduce a novel framework, Map2World, that first enables 3D world generation conditioned on user-defined segment maps of arbitrary shapes and scales, ensuring global-scale consistency and flexibility across expansive environments. To further enhance the quality, we propose a detail enhancer network that generates fine details of the world. The detail enhancer enables the addition of fine-grained details without compromising overall scene coherence by incorporating global structure information. We design the entire pipeline to leverage strong priors from asset generators, achieving robust generalization across diverse domains, even under limited training data for scene generation. Extensive experiments demonstrate that our method significantly outperforms existing approaches in user-controllability, scale consistency, and content coherence, enabling users to generate 3D worlds under more complex conditions.</p> - https://arxiv.org/abs/2605.00781 - Fri, 01 May 2026 00:00:00 +0000 - - - Let ViT Speak: Generative Language-Image Pre-training - https://arxiv.org/abs/2605.00809 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00809.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Fang, Mengcheng Lan, Zilong Huang, Weixian Lei, Yunqing Zhao, Yujie Zhong, Yingchen Yu, Qi She, Yao Zhao, Yunchao Wei</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> In this paper, we present Generative Language-Image Pre-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models (MLLMs). To better align vision encoders with the autoregressive nature of LLMs, GenLIP trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective, without contrastive batch construction or an additional text decoder. This design offers three key advantages: (1) Simplicity: a single transformer jointly models visual and textual tokens; (2) Scalability: it scales effectively with both data and model size; and (3) Performance: it achieves competitive or superior results across diverse multimodal benchmarks. Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding, making it a strong foundation for vision encoders in MLLMs.</p> - https://arxiv.org/abs/2605.00809 - Fri, 01 May 2026 00:00:00 +0000 - - - Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL - https://arxiv.org/abs/2604.28123 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28123.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sudong Wang, Weiquan Huang, Xiaomin Yu, Zuhao Yang, Hehai Lin, Keming Wu, Chaojun Xiao, Chen Chen, Wenxuan Wang, Beier Zhu, Yunjian Zhang, Chengwei Qin</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). However, SFT introduces distributional drift that neither preserves the model's original capabilities nor faithfully matches the supervision distribution. This problem is further amplified in multimodal reasoning, where perception errors and reasoning failures follow distinct drift patterns that compound during subsequent RL. We introduce PRISM, a three-stage pipeline that mitigates this drift by inserting an explicit distribution-alignment stage between SFT and RLVR. Building on the principle of on-policy distillation (OPD), PRISM casts alignment as a black-box, response-level adversarial game between the policy and a Mixture-of-Experts (MoE) discriminator with dedicated perception and reasoning experts, providing disentangled corrective signals that steer the policy toward the supervision distribution without requiring access to teacher logits. While 1.26M public demonstrations suffice for broad SFT initialization, distribution alignment demands higher-fidelity supervision; we therefore curate 113K additional demonstrations from Gemini 3 Flash, featuring dense visual grounding and step-by-step reasoning on the hardest unsolved problems. Experiments on Qwen3-VL show that PRISM consistently improves downstream RLVR performance across multiple RL algorithms (GRPO, DAPO, GSPO) and diverse multimodal benchmarks, improving average accuracy by +4.4 and +6.0 points over the SFT-to-RLVR baseline on 4B and 8B, respectively. Our code, data, and model checkpoints are publicly available at https://github.com/XIAO4579/PRISM.</p> - https://arxiv.org/abs/2604.28123 - Fri, 01 May 2026 00:00:00 +0000 - - - UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors - https://arxiv.org/abs/2605.00658 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00658.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Houyuan Chen, Hong Li, Xianghao Kong, Tianrui Zhu, Shaocong Xu, Weiqing Xiao, Yuwei Guo, Chongjie Ye, Lvmin Zhang, Hao Zhao, Anyi Rao</p><p><b>Upvotes:</b> 80</p><p><b>Summary:</b> Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting, which fixes the input-output mapping and limits the modeling of correlations across modalities. We present UniVidX, a unified multimodal framework that leverages VDM priors for versatile video generation. UniVidX formulates pixel-aligned tasks as conditional generation in a shared multimodal space, adapts to modality-specific distributions while preserving the backbone's native priors, and promotes cross-modal consistency during synthesis. It is built on three key designs. Stochastic Condition Masking (SCM) randomly partitions modalities into clean conditions and noisy targets during training, enabling omni-directional conditional generation instead of fixed mappings. Decoupled Gated LoRA (DGL) introduces per-modality LoRAs that are activated when a modality serves as the generation target, preserving the strong priors of the VDM. Cross-Modal Self-Attention (CMSA) shares keys and values across modalities while keeping modality-specific queries, facilitating information exchange and inter-modal alignment. We instantiate UniVidX in two domains: UniVid-Intrinsic, for RGB videos and intrinsic maps including albedo, irradiance, and normal; and UniVid-Alpha, for blended RGB videos and their constituent RGBA layers. Experiments show that both models achieve performance competitive with state-of-the-art methods across distinct tasks and generalize robustly to in-the-wild scenarios, even when trained on fewer than 1,000 videos. Project page: https://houyuanchen111.github.io/UniVidX.github.io/</p> - https://arxiv.org/abs/2605.00658 - Fri, 01 May 2026 00:00:00 +0000 - - - Agentic AI Systems Should Be Designed as Marginal Token Allocators - https://arxiv.org/abs/2605.01214 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01214.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siqi Zhu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> This position paper argues that agentic AI systems should be designed and evaluated as marginal token allocation economies rather than as text generators priced by the unit. We follow a single request -- a developer asking a coding agent to fix a failing test -- through four economic layers that today are designed in isolation: a router that decides which model answers, an agent that decides whether to plan, act, verify, or defer, a serving stack that decides how to produce each token, and a training pipeline that decides whether the trace is worth learning from. We show that all four layers are solving the same first-order condition -- marginal benefit equals marginal cost plus latency cost plus risk cost -- with different index sets and different prices. The framing is deliberately minimal: we do not propose a complete theory of AI economics. But adopting marginal token allocation as the shared accounting object explains why systems that locally minimize tokens globally misallocate them, predicts a small set of recurring failure modes (over-routing, over-delegation, under-verification, serving congestion, stale rollouts, cache misuse), and points to a concrete research agenda in token-aware evaluation, autonomy pricing, congestion-priced serving, and risk-adjusted RL budgeting.</p> - https://arxiv.org/abs/2605.01214 - Sat, 02 May 2026 00:00:00 +0000 - - - Prescriptive Scaling Laws for Data Constrained Training - https://arxiv.org/abs/2605.01640 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01640.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Justin Lovelace, Christian Belardi, Srivatsa Kundurthy, Shriya Sudhakar, Kilian Q. Weinberger</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Training compute is increasingly outpacing the availability of high-quality data. This shifts the central challenge from optimal compute allocation to extracting maximum value from limited data. The widely adopted Chinchilla scaling law assumes every training token is unique. This limits its ability to guide pretraining decisions in data-constrained regimes. We model the excess loss under repetition with a simple additive overfitting penalty and find that it accurately describes model behavior. Our scaling law yields qualitatively new compute-optimal allocation advice. Beyond a point, further repetition is counterproductive and compute is better spent on model capacity. We show that following our law's recommended configuration improves performance in data-constrained regimes. Finally, because our one-parameter form isolates overfitting in a single coefficient, it enables direct comparison across training configurations. As a case study, we show that strong weight decay (λ=1.0) reduces this coefficient by approximately 70%, providing a scaling-law explanation for recent findings that optimal weight decay in data-constrained regimes is an order of magnitude larger than standard practice.</p> - https://arxiv.org/abs/2605.01640 - Sat, 02 May 2026 00:00:00 +0000 - - - SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion - https://arxiv.org/abs/2605.01466 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01466.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoyang Li, Zhichao You, Tianrui Li</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, yet we identify that standard hard projection severs this connection: projecting a sparse point cloud onto the image plane yields an extremely sparse support, which hinders visual prior propagation, a failure mode we term Cross-Modal Entropy Collapse. To address this practical limitation, we propose SplAttN, which replaces hard projection with Differentiable Gaussian Splatting to produce a dense, continuous image-plane representation. By reformulating projection as continuous density estimation, SplAttN avoids collapsed sparse support, facilitates gradient flow, and improves cross-modal connection learnability. Extensive experiments show that SplAttN achieves state-of-the-art performance on PCN and ShapeNet-55/34. Crucially, we utilize the real-world KITTI benchmark as a stress test for multi-modal reliance. Counter-factual evaluation reveals that while baselines degenerate into unimodal template retrievers insensitive to visual removal, SplAttN maintains a robust dependency on visual cues, validating that our method establishes an effective cross-modal connection. Code is available at https://github.com/zay002/SplAttN.</p> - https://arxiv.org/abs/2605.01466 - Sat, 02 May 2026 00:00:00 +0000 - - - ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue - https://arxiv.org/abs/2605.01371 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01371.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daoxuan Zhang, Ping Chen, Jianyi Zhou, Shuo Yang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The rapid advancement of Multimodal Large Language Models (MLLMs) has empowered Unmanned Aerial Vehicle (UAV) with exceptional capabilities in spatial reasoning, semantic understanding, and complex decision-making, making them inherently suited for UAV Search and Rescue (SAR). However, existing UAV SAR research is dominated by traditional vision and path-planning methods and lacks a comprehensive and unified benchmark for embodied agents. To bridge this gap, we first propose the novel task of Embodied Search and Rescue (ESAR), which requires aerial agents to autonomously explore complex environments, identify rescue clues, and reason about victim locations to execute informed decision-making. Additionally, we present ESARBench, the first comprehensive benchmark designed to evaluate MLLM-driven UAV agents in highly realistic SAR scenarios. Leveraging Unreal Engine 5 and AirSim, we construct four high-fidelity, large-scale open environments mapped directly from real-world Geographic Information System (GIS) data to ensure photorealistic landscapes. To rigorously simulate actual rescue operations, our benchmark incorporates dynamic variables including weather conditions, time of day, and stochastic clue placement. Furthermore, we create a dataset of 600 tasks modeled after real-world rescue cases and propose a robust set of evaluation metrics. We evaluate diverse baselines, ranging from traditional heuristics to advanced ground and aerial MLLM-based ObjectNav agents. Experimental results highlight the challenges in ESAR, revealing critical bottlenecks in spatial memory, aerial adaptation, and the trade-off between search efficiency and flight safety. We hope ESARBench serves as a valuable resource to advance research on Embodied Search and Rescue domain. Source code and project page: https://4amgodvzx.github.io/ESAR.github.io.</p> - https://arxiv.org/abs/2605.01371 - Sat, 02 May 2026 00:00:00 +0000 - - - Hallucinations Undermine Trust; Metacognition is a Way Forward - https://arxiv.org/abs/2605.01428 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01428.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gal Yona, Mor Geva, Yossi Matias</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Despite significant strides in factual reliability, errors -- often termed hallucinations -- remain a major concern for generative AI, especially as LLMs are increasingly expected to be helpful in more complex or nuanced setups. Yet even in the simplest setting -- factoid question-answering with clear ground truth-frontier models without external tools continue to hallucinate. We argue that most factuality gains in this domain have come from expanding the model's knowledge boundary (encoding more facts) rather than improving awareness of that boundary (distinguishing known from unknown). We conjecture that the latter is inherently difficult: models may lack the discriminative power to perfectly separate truths from errors, creating an unavoidable tradeoff between eliminating hallucinations and preserving utility. This tradeoff dissolves under a different framing. If we understand hallucinations as confident errors -- incorrect information delivered without appropriate qualification -- a third path emerges beyond the answer-or-abstain dichotomy: expressing uncertainty. We propose faithful uncertainty: aligning linguistic uncertainty with intrinsic uncertainty. This is one facet of metacognition -- the ability to be aware of one's own uncertainty and to act on it. For direct interaction, acting on uncertainty means communicating it honestly; for agentic systems, it becomes the control layer governing when to search and what to trust. Metacognition is thus essential for LLMs to be both trustworthy and capable; we conclude by highlighting open problems for progress towards this objective.</p> - https://arxiv.org/abs/2605.01428 - Sat, 02 May 2026 00:00:00 +0000 - - - Linear-Time Global Visual Modeling without Explicit Attention - https://arxiv.org/abs/2605.01711 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01711.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruize He, Dongchen Han, Gao Huang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quadratic computational complexity. In this work, we offer a novel perspective: we demonstrate that attention can be mathematically reframed as a Multi-Layer Perceptron (MLP) equipped with dynamically predicted parameters. Through this lens, we explain attention's global modeling power not as explicit token-wise aggregation, but as an implicit process where dynamically generated parameters act as a compressed representation of the global context. Inspired by this insight, we investigate a fundamental question: can we achieve Transformer-level sequence global modeling entirely through dynamic parameterization while maintaining linear complexity, effectively replacing explicit attention? To explore this, we design various dynamic parameter prediction strategies and integrate them into standard network layers. Extensive empirical studies on vision models demonstrate that dynamic parameterization can indeed serve as a highly effective, linear-complexity alternative to explicit attention, opening new pathways for efficient sequence modeling. Code is available at https://github.com/LeapLabTHU/WeightFormer.</p> - https://arxiv.org/abs/2605.01711 - Sun, 03 May 2026 00:00:00 +0000 - - - TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis - https://arxiv.org/abs/2605.01717 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01717.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinran Li, Xinze Che, Yifan Lyu, Zhiqi Huang, Xiujuan Xu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Conversational Aspect-based Sentiment Quadruple Analysis (DiaASQ) needs to capture the complex interrelationships in multiple rounds of dialogues. Existing methods usually employ simple Graph Convolutional Networks (GCN), which introduce structural noise and fail to consider the temporal sequence of the dialogues, or use standard RoPE, which implicitly captures relative distances in a flat sequence but cannot clearly separate the token-level syntactic order from the utterance-level progression, and may suffer from the Distance Dilution problem. To address these issues, we propose a new framework that combines Thread-Constrained Directed Acyclic Graph (TC-DAG) and Discourse-Aware Rotary Position Embedding (D-RoPE). Specifically, TC-DAG filters out cross-thread noise based on thread constraints, maintains global connectivity through root anchoring, and incorporates the temporal sequence of the dialogues. D-RoPE aligns multi-layer semantics using dual-stream projection and multi-scale frequency signals, captures thread dependencies using tree-like distances, and alleviates the token-level Distance Dilution problem by incorporating utterance-level progressions. Experimental results on two benchmark datasets demonstrate that our framework achieves state-of-the-art performance.</p> - https://arxiv.org/abs/2605.01717 - Sun, 03 May 2026 00:00:00 +0000 - - - Motion-Aware Caching for Efficient Autoregressive Video Generation - https://arxiv.org/abs/2605.01725 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01725.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jing Xu, Yuexiao Ma, Songwei Liu, Xuzhe Zheng, Shiwei Liu, Chenqian Yan, Xiawu Zheng, Rongrong Ji, Fei Chao, Xing Wang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can accelerate generation by skipping redundant denoising steps, existing methods rely on coarse-grained chunk-level skipping that fails to capture fine-grained pixel dynamics. This oversight is critical: pixels with high motion require more denoising steps to prevent error accumulation, while static pixels tolerate aggressive skipping. We formalize this insight theoretically by linking cache errors to residual instability, and propose MotionCache, a motion-aware cache framework that exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics. MotionCache employs a coarse-to-fine strategy: an initial warm-up phase establishes semantic coherence, followed by motion-weighted cache reuse that dynamically adjusts update frequencies per token. Extensive experiments on state-of-the-art models like SkyReels-V2 and MAGI-1 demonstrate that MotionCache achieves significant speedups of 6.28times and 1.64times respectively, while effectively preserving generation quality (VBench: 1%downarrow and 0.01%downarrow respectively). The code is available at https://github.com/ywlq/MotionCache.</p> - https://arxiv.org/abs/2605.01725 - Sun, 03 May 2026 00:00:00 +0000 - - - Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction - https://arxiv.org/abs/2605.05242 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05242.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuofeng Li, Haoxiang Zhang, Cong Wei, Pan Lu, Ping Nie, Yi Lu, Yuyang Bai, Shangbin Feng, Hangxiao Zhu, Ming Zhong, Yuyu Zhang, Jianwen Xie, Yejin Choi, James Zou, Jiawei Han, Wenhu Chen, Jimmy Lin, Dongfu Jiang, Yu Zhang</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoning. This abstraction is efficient, but for agentic search, it becomes a bottleneck: exact lexical constraints, sparse clue conjunctions, local context checks, and multi-step hypothesis refinement are difficult to implement by calling a conventional off-the-shelf retriever, and evidence filtered out early cannot be recovered by stronger downstream reasoning. Agentic tasks further exacerbate this limitation because they require agents to orchestrate multiple steps, including discovering intermediate entities, combining weak clues, and revising the plan after observing partial evidence. To tackle the limitation, we study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools (e.g., grep, file reads, shell commands, lightweight scripts), without any embedding model, vector index, or retrieval API. This approach requires no offline indexing and adapts naturally to evolving local corpora. Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines on several BRIGHT and BEIR datasets, and attains strong accuracy on BrowseComp-Plus and multi-hop QA without relying on any conventional semantic retriever. Our results indicate that as language agents become stronger, retrieval quality depends not only on reasoning ability but also on the resolution of the interface through which the model interacts with the corpus, with which DCI opens a broader interface-design space for agentic search.</p> - https://arxiv.org/abs/2605.05242 - Sun, 03 May 2026 00:00:00 +0000 - - - From Context to Skills: Can Language Models Learn from Context Skillfully? - https://arxiv.org/abs/2604.27660 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27660.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuzheng Si, Haozhe Zhao, Yu Lei, Qingyi Wang, Dingwei Chen, Zhitong Wang, Zhenhailong Wang, Kangyang Luo, Zheng Wang, Gang Chen, Fanchao Qi, Minjia Zhang, Maosong Sun</p><p><b>Upvotes:</b> 148</p><p><b>Summary:</b> Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive solution is inference-time skill augmentation: extracting the rules and procedures from context into natural-language skills. However, constructing such skills for context learning scenarios faces two challenges: the prohibitive cost of manual skill annotation for long, technically dense contexts, and the lack of external feedback for automated skill construction. In this paper, we propose Ctx2Skill, a self-evolving framework that autonomously discovers, refines, and selects context-specific skills without human supervision or external feedback. At its core, a multi-agent self-play loop has a Challenger that generates probing tasks and rubrics, a Reasoner that attempts to solve them guided by an evolving skill set, and a neutral Judge that provides binary feedback. Crucially, both the Challenger and the Reasoner evolve through accumulated skills: dedicated Proposer and Generator agents analyze failure cases and synthesize them into targeted skill updates for both sides, enabling automated skill discovery and refinement. To prevent adversarial collapse caused by increasingly extreme task generation and over-specialized skill accumulation, we further introduce a Cross-time Replay mechanism that identifies the skill set achieving the best balance across representative cases for the Reasoner side, ensuring robust and generalizable skill evolution. The resulting skills can be plugged into any language model to obtain better context learning capability. Evaluated on four context learning tasks from CL-bench, Ctx2Skill consistently improves solving rates across backbone models.</p> - https://arxiv.org/abs/2604.27660 - Sun, 03 May 2026 00:00:00 +0000 - - - Perceptual Flow Network for Visually Grounded Reasoning - https://arxiv.org/abs/2605.02730 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02730.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yangfu Li, Yuning Gong, Hongjian Zhan, Teng Li, Yuanhuiyi Lyu, Tianyi Chen, Qi Liu, Ziyuan Huang, Zhihang Zhong, Dandan Zheng, Yue Lu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories, leading to language bias and hallucination. To mitigate this, current methods introduce geometric priors from visual experts as additional supervision. However, we observe that such supervision is typically suboptimal: it is biased toward geometric precision and offers limited reasoning utility. To bridge this gap, we propose Perceptual Flow Network (PFlowNet), which eschews rigid alignment with the expert priors and achieves interpretable yet more effective visual reasoning. Specifically, PFlowNet decouples perception from reasoning to establish a self-conditioned generation process. Based on this, it integrates multi-dimensional rewards with vicinal geometric shaping via variational reinforcement learning, thereby facilitating reasoning-oriented perceptual behaviors while preserving visual reliability. PFlowNet delivers a provable performance guarantee and competitive empirical results, particularly setting new SOTA records on V* Bench (90.6%) and MME-RealWorld-lite (67.0%).</p> - https://arxiv.org/abs/2605.02730 + Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training + https://arxiv.org/abs/2511.07328 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.07328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Artyom Sorokin, Nazar Buzun, Alexander Anokhin, Oleg Inozemcev, Egor Vedernikov, Petr Anokhin, Mikhail Burtsev, Trushkov Alexey, Yin Wenshuai, Evgeny Burnaev</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most existing RAG methods focus on single-step retrieval, which is often insufficient for answering complex questions that require multi-step search. Recently, multi-step retrieval approaches have emerged, typically involving the fine-tuning of small LLMs to perform multi-step retrieval. This type of fine-tuning is highly resource-intensive and does not enable the use of larger LLMs. In this work, we propose Q-RAG, a novel approach that fine-tunes the Embedder model for multi-step retrieval using reinforcement learning (RL). Q-RAG offers a competitive, resource-efficient alternative to existing multi-step retrieval methods for open-domain question answering and achieves state-of-the-art results on the popular long-context benchmarks BabiLong and RULER for contexts up to 10M tokens. Code is available at https://github.com/griver/Q-RAG</p> + https://arxiv.org/abs/2511.07328 Mon, 04 May 2026 00:00:00 +0000 - Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces - https://arxiv.org/abs/2605.02801 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02801.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenchen Zhang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and stopped. This paper studies RL for LLM-based multi-agent systems through orchestration traces: temporal interaction graphs whose events include sub-agent spawning, delegation, communication, tool use, return, aggregation, and stopping decisions. Using this lens, we identify three technical axes. First, reward design spans eight families, including orchestration rewards for parallelism speedup, split correctness, and aggregation quality. Second, reward and credit signals attach to eight credit- or signal-bearing units from token to team; explicit counterfactual message-level credit remains especially sparse in our curated pool. Third, orchestration learning decomposes into five sub-decisions: when to spawn, whom to delegate to, how to communicate, how to aggregate, and when to stop. In our curated pool as of May 4, 2026, we found no explicit RL training method for the stopping decision. We connect academic methods to public industrial evidence from Kimi Agent Swarm, OpenAI Codex, and Anthropic Claude Code. The resulting scale gap is a gap between publicly reported deployment envelopes and open academic evaluation regimes, not independent verification of industrial training traces. We release the artifact at https://github.com/xxzcc/awesome-llm-mas-rl, including an 84-entry tagged paper pool, a 32-record exclusion log, scripted corpus statistics, and a minimal JSON schema for replayable orchestration traces.</p> - https://arxiv.org/abs/2605.02801 - Mon, 04 May 2026 00:00:00 +0000 - - - PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments - https://arxiv.org/abs/2605.02240 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruoqi Liu, Imran Q. Mohiuddin, Austin J. Schoeffler, Kavita Renduchintala, Ashwin Nayak, Prasantha L. Vemu, Shivam C. Vedak, Kameron C. Black, John L. Havlik, Isaac Ogunmola, Stephen P. Ma, Roopa Dhatt, Jonathan H. Chen</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We introduce PhysicianBench, a benchmark for evaluating LLM agents on physician tasks grounded in real clinical setting within electronic health record (EHR) environments. Existing medical agent benchmarks primarily focus on static knowledge recall, single-step atomic actions, or action intent without verifiable execution against the environment. As a result, they fail to capture the long-horizon, composite workflows that characterize real clinical systems. PhysicianBench comprises 100 long-horizon tasks adapted from real consultation cases between primary care and subspecialty physicians, with each task independently reviewed by a separate panel of physicians. Tasks are instantiated in an EHR environment with real patient records and accessed through the same standard APIs used by commercial EHR vendors. Tasks span 21 specialties (e.g., cardiology, endocrinology, oncology, psychiatry) and diverse workflow types (e.g., diagnosis interpretation, medication prescribing, treatment planning), requiring an average of 27 tool calls per task. Solving each task requires retrieving data across encounters, reasoning over heterogeneous clinical information, executing consequential clinical actions, and producing clinical documentation. Each task is decomposed into structured checkpoints (670 in total across the benchmark) capturing distinct stages of completion graded by task-specific scripts with execution-grounded verification. Across 13 proprietary and open-source LLM agents, the best-performing model achieves only 46% success rate (pass@1), while open-source models reach at most 19%, revealing a substantial gap between current agent capabilities and the demands of real-world clinical workflows. PhysicianBench provides a realistic and execution-grounded benchmark for measuring progress toward autonomous clinical agents.</p> - https://arxiv.org/abs/2605.02240 - Mon, 04 May 2026 00:00:00 +0000 - - - T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning - https://arxiv.org/abs/2605.02178 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02178.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haixin Wang, Hejie Cui, Chenwei Zhang, Xin Liu, Shuowei Jin, Shijie Geng, Xinyang Zhang, Nasser Zalmout, Zhenyu Shi, Yizhou Sun</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent progress in multi-turn reinforcement learning (RL) has significantly improved reasoning LLMs' performances on complex interactive tasks. Despite advances in stabilization techniques such as fine-grained credit assignment and trajectory filtering, instability remains pervasive and often leads to training collapse. We argue that this instability stems from inefficient exploration in multi-turn settings, where policies continue to generate low-information actions that neither reduce uncertainty nor advance task progress. To address this issue, we propose Token- and Turn-level Policy Optimization (T^2PO), an uncertainty-aware framework that explicitly controls exploration at fine-grained levels. At the token level, T^2PO monitors uncertainty dynamics and triggers a thinking intervention once the marginal uncertainty change falls below a threshold. At the turn level, T^2PO identifies interactions with negligible exploration progress and dynamically resamples such turns to avoid wasted rollouts. We evaluate T^2PO in diverse environments, including WebShop, ALFWorld, and Search QA, demonstrating substantial gains in training stability and performance improvements with better exploration efficiency. Code is available at: https://github.com/WillDreamer/T2PO.</p> - https://arxiv.org/abs/2605.02178 - Mon, 04 May 2026 00:00:00 +0000 - - - Generative Modeling with Orbit-Space Particle Flow Matching - https://arxiv.org/abs/2605.02222 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02222.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sinan Wang, Jinjin He, Shenyifan Lu, Ruicheng Wang, Greg Turk, Bo Zhu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We present Orbit-Space Geometric Probability Paths (OGPP), a particle-native flow-matching framework for generative modeling of particle systems. OGPP is motivated by two insights: (i) particles are defined up to permutation symmetries, so anonymous indexing inflates per-index target variance and yields curved, hard-to-learn flows; and (ii) particles live in physical space, so the flow terminal velocity has physical meaning and can encode geometric attributes, e.g., surface normals. OGPP instantiates three key components: (1) orbit-space canonicalization of the probability-path terminal endpoint, (2) particle index embeddings for role specialization, and (3) geometric probability paths with arc-length-aware terminal velocities that generate normals as a byproduct of the flow. We evaluate OGPP on minimal-surface benchmarks, where it reduces metric error by up to two orders of magnitude in a single inference step; on ShapeNet, where it matches the state of the art with 5x fewer steps and reaches airplane EMD comparable to DiT-3D with 26x fewer parameters and 5x fewer steps; and on single-shape encoding, where it produces normals and reconstructions competitive with 6D generators while operating entirely in 3D.</p> - https://arxiv.org/abs/2605.02222 - Mon, 04 May 2026 00:00:00 +0000 - - - SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors - https://arxiv.org/abs/2411.18966 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2411.18966.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Xu, Wenyue Chen, Jiepeng Wang, Yuan Liu, Peng Wang, Cheng Lin, Shiqing Xin, Xin Li, Wenping Wang, Taku Komura</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation. In this paper, we introduce a new method called SVGS (Spatially Varying Gaussian Splatting) that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability. We have implemented bilinear interpolation, movable kernels, and tiny neural networks as spatially varying functions. SVGS employs 2D Gaussian surfels as primitives, which significantly enhances novel-view synthesis while maintaining high-quality geometric reconstruction. This approach is particularly effective in practical applications, as scenes combining complex textures with relatively simple geometry occur frequently in real-world environments. Quantitative and qualitative experimental results demonstrate that all three functions outperform the baseline, with the best movable kernels achieving superior novel view synthesis performance on multiple datasets, highlighting the strong potential of spatially varying functions. Project page: https://ruixu.me/html/SuperGaussians/index.html</p> - https://arxiv.org/abs/2411.18966 - Mon, 04 May 2026 00:00:00 +0000 - - - AcademiClaw: When Students Set Challenges for AI Agents - https://arxiv.org/abs/2605.02661 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02661.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Yu, Pengrui Lu, Weiye Si, Hongliang Lu, Jiabao Wu, Kaiwen Tao, Kun Wang, Lingyu Yang, Qiran Zhang, Xiuting Guo, Xuanyu Wang, Yang Wang, Yanjie Wang, Yi Yang, Zijian Hu, Ziyi Yang, Zonghan Zhou, Binghao Qiang, Borui Zhang, Chenning Li, Enchang Zhang, Feifan Chen, Feng Jian, Fengyin Sun, Hao Qiu, Hao Zheng, Haoran Zhu, Hongyu Liu, Jianbin Deng, Jiaxin Song, Jiaying Chi, Jiayou Shi, Jie Fang, Jinghui Zhong, Jingyu Zhou, Jinze Li, Junfeng Yi, Junyan Yu, Junzhi Xue, Ni Song, Pengyi Chen, Qi Chen, Quansheng Li, Rui Tao, Shenghai Gong, Shenhang Lu, Tianqi Shen, Tianxiang Zhu, Tiehan Kang, Tingyu Li, Wendi Wu, Xiao Shen, Xiao Zhou, Xiaotao Zhang, Xinrong Li, Xuankun Yang, Xun Zhang, Yan Li, Ye Lu, Yi Wang, Yibo Zhou, Yichi Zhang, Yihao Sun, Yijun Huang, Yixin Zhu, Yixuan Wu, Yuchen Sun, Yue Wu, Yuheng Sun, Yukun Li, Yutian Tu, Yuxuan Qin, Yuzhuo Wu, Zeyu Li, Zhengyu Lou, Zhenning Ran, Zizhu He, Pengfei Liu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Benchmarks within the OpenClaw ecosystem have thus far evaluated exclusively assistant-level tasks, leaving the academic-level capabilities of OpenClaw largely unexamined. We introduce AcademiClaw, a bilingual benchmark of 80 complex, long-horizon tasks sourced directly from university students' real academic workflows -- homework, research projects, competitions, and personal projects -- that they found current AI agents unable to solve effectively. Curated from 230 student-submitted candidates through rigorous expert review, the final task set spans 25+ professional domains, ranging from olympiad-level mathematics and linguistics problems to GPU-intensive reinforcement learning and full-stack system debugging, with 16 tasks requiring CUDA GPU execution. Each task executes in an isolated Docker sandbox and is scored on task completion by multi-dimensional rubrics combining six complementary techniques, with an independent five-category safety audit providing additional behavioral analysis. Experiments on six frontier models show that even the best achieves only a 55\% pass rate. Further analysis uncovers sharp capability boundaries across task domains, divergent behavioral strategies among models, and a disconnect between token consumption and output quality, providing fine-grained diagnostic signals beyond what aggregate metrics reveal. We hope that AcademiClaw and its open-sourced data and code can serve as a useful resource for the OpenClaw community, driving progress toward agents that are more capable and versatile across the full breadth of real-world academic demands. All data and code are available at https://github.com/GAIR-NLP/AcademiClaw.</p> - https://arxiv.org/abs/2605.02661 - Mon, 04 May 2026 00:00:00 +0000 - - - Video Generation with Predictive Latents - https://arxiv.org/abs/2605.02134 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02134.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yian Zhao, Feng Wang, Qiushan Guo, Chang Liu, Xiangyang Ji, Jian Zhang, Jie Chen</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable reconstruction quality, continued optimization of reconstruction does not necessarily translate into improved generative performance. How to enhance the diffusability of video latents remains a critical and unresolved challenge. In this work, inspired by principles of predictive world modeling, we investigate the potential of predictive learning to improve the video generative modeling. To this end, we introduce a simple and effective predictive reconstruction objective that unifies predictive learning with video reconstruction. Specifically, we randomly discard future frames and encode only partial past observations, while training the decoder to reconstruct the observed frames and predict future ones simultaneously. This design encourages the latent space to encode temporally predictive structures and build a more coherent understanding of video dynamics, thereby improving generation quality. Our model, termed Predictive Video VAE (PV-VAE), achieves superior performance on video generation, with 52% faster convergence and a 34.42 FVD improvement over the Wan2.2 VAE on UCF101. Furthermore, comprehensive analyses demonstrate that PV-VAE not only exhibits favorable scalability, with generative performance improving alongside VAE training, but also yields consistent gains in downstream video understanding, underscoring a latent space that effectively captures temporal coherence and motion priors.</p> - https://arxiv.org/abs/2605.02134 - Mon, 04 May 2026 00:00:00 +0000 - - - HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness - https://arxiv.org/abs/2605.02396 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02396.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianing Wang, Linsen Guo, Zhengyu Chen, Qi Guo, Hongyu Zang, Wenjie Shi, Haoxiang Ma, Xiangyu Xi, Xiaoyu Li, Wei Wang, Xunliang Cai</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Recent advances in agentic harness with orchestration frameworks that coordinate multiple agents with memory, skills, and tool use have achieved remarkable success in complex reasoning tasks. However, the underlying mechanism that truly drives performance remains obscured behind intricate system designs. In this paper, we propose HeavySkill, a perspective that views heavy thinking not only as a minimal execution unit in orchestration harness but also as an inner skill internalized within the model's parameters that drives the orchestrator to solve complex tasks. We identify this skill as a two-stage pipeline, i.e., parallel reasoning then summarization, which can operate beneath any agentic harness. We present a systematic empirical study of HeavySkill across diverse domains. Our results show that this inner skill consistently outperforms traditional Best-of-N (BoN) strategies; notably, stronger LLMs can even approach Pass@N performance. Crucially, we demonstrate that the depth and width of heavy thinking, as a learnable skill, can be further scaled via reinforcement learning, offering a promising path toward self-evolving LLMs that internalize complex reasoning without relying on brittle orchestration layers.</p> - https://arxiv.org/abs/2605.02396 - Mon, 04 May 2026 00:00:00 +0000 - - - ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration - https://arxiv.org/abs/2605.03042 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03042.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruofeng Yang, Yongcan Li, Shuai Li</p><p><b>Upvotes:</b> 101</p><p><b>Summary:</b> This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance mechanisms, and early deployment experience. The performance of agent systems built on LLMs depends on both the model weights and the harness around them, which governs what information to store, retrieve, and present to the model. For long-horizon research workflows, the central failure mode is not a visible breakdown but a plausible unsupported success: a long-running agent can produce claims whose evidential support is incomplete, misreported, or silently inherited from the executor's framing. Therefore, we present ARIS as a research harness that coordinates machine-learning research workflows through cross-model adversarial collaboration as a default configuration: an executor model drives forward progress while a reviewer from a different model family is recommended to critique intermediate artifacts and request revisions. ARIS has three architectural layers. The execution layer provides more than 65 reusable Markdown-defined skills, model integrations via MCP, a persistent research wiki for iterative reuse of prior findings, and deterministic figure generation. The orchestration layer coordinates five end-to-end workflows with adjustable effort settings and configurable routing to reviewer models. The assurance layer includes a three-stage process for checking whether experimental claims are supported by evidence: integrity verification, result-to-claim mapping, and claim auditing that cross-checks manuscript statements against the claim ledger and raw evidence, as well as a five-pass scientific-editing pipeline, mathematical-proof checks, and visual inspection of the rendered PDF. A prototype self-improvement loop records research traces and proposes harness improvements that are adopted only after reviewer approval.</p> - https://arxiv.org/abs/2605.03042 - Mon, 04 May 2026 00:00:00 +0000 - - - MolmoAct2: Action Reasoning Models for Real-world Deployment - https://arxiv.org/abs/2605.02881 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoquan Fang, Jiafei Duan, Donovan Clay, Sam Wang, Shuo Liu, Weikai Huang, Xiang Fan, Wei-Chuan Tsai, Shirui Chen, Yi Ru Wang, Shanli Xing, Jaemin Cho, Jae Sung Park, Ainaz Eftekhar, Peter Sushko, Karen Farley, Angad Wadhwa, Cole Harrison, Winson Han, Ying-Chun Lee, Eli VanderBilt, Rose Hendrix, Suveen Ellawela, Lucas Ngoo, Joyce Chai, Zhongzheng Ren, Ali Farhadi, Dieter Fox, Ranjay Krishna</p><p><b>Upvotes:</b> 268</p><p><b>Summary:</b> Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment. Frontier models are closed, open-weight alternatives are tied to expensive hardware, reasoning-augmented policies pay prohibitive latency for their grounding, and fine-tuned success rates remain below the threshold for dependable use. We present MolmoAct2, a fully open action reasoning model built for practical deployment, advancing its predecessor along five axes. We introduce MolmoER, a VLM backbone specialized for spatial and embodied reasoning, trained on a 3.3M-sample corpus with a specialize-then-rehearse recipe. We release three new datasets spanning low-to-medium cost platforms, including MolmoAct2-BimanualYAM, 720 hours of teleoperated bimanual trajectories that constitute the largest open bimanual dataset to date, together with quality-filtered Franka (DROID) and SO100/101 subsets. We provide OpenFAST, an open-weight, open-data action tokenizer trained on millions of trajectories across five embodiments. We redesign the architecture to graft a flow-matching continuous-action expert onto a discrete-token VLM via per-layer KV-cache conditioning. Finally, we propose MolmoThink, an adaptive-depth reasoning variant that re-predicts depth tokens only for scene regions that change between timesteps, retaining geometric grounding at a fraction of prior latency. In the most extensive empirical study of any open VLA to date, spanning 7 simulation and real-world benchmarks, MolmoAct2 outperforms strong baselines including Pi-05, while MolmoER surpasses GPT-5 and Gemini Robotics ER-1.5 across 13 embodied-reasoning benchmarks. We release model weights, training code, and complete training data. Project page: https://allenai.org/blog/molmoact2</p> - https://arxiv.org/abs/2605.02881 - Mon, 04 May 2026 00:00:00 +0000 - - - The Scaling Properties of Implicit Deductive Reasoning in Transformers - https://arxiv.org/abs/2605.04330 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04330.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Enrico Vompa, Tanel Tammet</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We investigate the scaling properties of implicit deductive reasoning over Horn clauses in depth-bounded Transformers. By systematically decorrelating provability from spurious features and enforcing algorithmic alignment, we find that in sufficiently deep models with a bidirectional prefix mask, implicit reasoning approaches explicit CoT performance across graph topologies and problem widths, though CoT remains necessary for depth extrapolation.</p> - https://arxiv.org/abs/2605.04330 - Tue, 05 May 2026 00:00:00 +0000 - - - A Benchmark for Interactive World Models with a Unified Action Generation Framework - https://arxiv.org/abs/2605.03941 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianjie Fang, Yingshan Lei, Qin Wan, Ziyou Wang, Yuchao Huang, Yongyan Xu, Baining Zhao, Weichen Zhang, Chen Gao, Xinlei Chen, Yong Li</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable environments for perception, reasoning, and action. Yet current research still lacks large-scale datasets and unified benchmarks to evaluate their physical interaction capabilities. To address this, we propose iWorld-Bench, a comprehensive benchmark for training and testing world models on interaction-related abilities such as distance perception and memory. We construct a diverse dataset with 330k video clips and select 2.1k high-quality samples covering varied perspectives, weather, and scenes. As existing world models differ in interaction modalities, we introduce an Action Generation Framework to unify evaluation and design six task types, generating 4.9k test samples. These tasks jointly assess model performance across visual generation, trajectory following, and memory. Evaluating 14 representative world models, we identify key limitations and provide insights for future research. The iWorld-Bench model leaderboard is publicly available at iWorld-Bench.com.</p> - https://arxiv.org/abs/2605.03941 - Tue, 05 May 2026 00:00:00 +0000 - - - APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music - https://arxiv.org/abs/2605.03395 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03395.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaavid Aktar Husain, Dorien Herremans</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Music popularity prediction has attracted growing research interest, with relevance to artists, platforms, and recommendation systems. However, the explosive rise of AI-generated music platforms has created an entirely new and largely unexplored landscape, where a surge of songs is produced and consumed daily without the traditional markers of artist reputation or label backing. Key, yet unexplored in this pursuit is aesthetic quality. We propose APEX, the first large-scale multi-task learning framework for AI-generated music, trained on over 211k songs (10k hours of audio) from Suno and Udio, that jointly predicts engagement-based popularity signals - streams and likes scores - alongside five perceptual aesthetic quality dimensions from frozen audio embeddings extracted from MERT, a self-supervised music understanding model. Aesthetic quality and popularity capture complementary aspects of music that together prove valuable: in an out-of-distribution evaluation on the Music Arena dataset, comprising pairwise human preference battles across eleven generative music systems unseen during training, including aesthetic features consistently improves preference prediction, demonstrating strong generalisation of the learned representations across generative architectures.</p> - https://arxiv.org/abs/2605.03395 - Tue, 05 May 2026 00:00:00 +0000 - - - Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback - https://arxiv.org/abs/2605.03848 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Edoardo Bianchi, Antonio Liotta</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Estimating how well a person performs an action, rather than which action is performed, is central to coaching, rehabilitation, and talent identification. This task is challenging because proficiency is encoded in subtle differences in timing, balance, body mechanics, and execution, often distributed across multiple views and short temporal events. We discuss three recent contributions to multi-view proficiency estimation on Ego-Exo4D. SkillFormer introduces a parameter-efficient discriminative architecture for selective multi-view fusion; PATS improves temporal sampling by preserving locally dense excerpts of fundamental movements; and ProfVLM reformulates proficiency estimation as conditional language generation, producing both a proficiency label and expert-style feedback through a gated cross-view projector and a compact language backbone. Together, these methods achieve state-of-the-art accuracy on Ego-Exo4D with up to 20x fewer trainable parameters and up to 3x fewer training epochs than video-transformer baselines, while moving from closed-set classification toward interpretable feedback generation. These results highlight a shift toward efficient, multi-view systems that combine selective fusion, proficiency-aware sampling, and actionable generative feedback.</p> - https://arxiv.org/abs/2605.03848 - Tue, 05 May 2026 00:00:00 +0000 - - - Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies - https://arxiv.org/abs/2605.03596 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03596.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zirui Tang, Xuanhe Zhou, Yumou Liu, Linchun Li, Weizheng Wang, Hongzhang Huang, Jun Zhou, Jiachen Song, Shaoli Yu, Jinqi Wang, Zihang Zhou, Hongyi Zhou, Yuting Lv, Jinyang Li, Jiashuo Liu, Ruoyu Chen, Chunwei Liu, GuoLiang Li, Jihua Kang, Fan Wu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advanced tasks effectively. Despite its importance, existing relevant benchmarks largely evaluate agents on pre-specified or synthesized files with limited real-world dependencies, leaving workspace-level evaluation underexplored. To this end, we introduce Workspace-Bench, a benchmark for evaluating AI agents on Workspace Learning invOlving Large-Scale File Dependencies. We construct realistic workspaces with 5 worker profiles, 74 file types, 20,476 files (up to 20GB) and curate 388 tasks, each with its own file dependency graph, evaluated across 7,399 total rubrics that require cross-file retrieval, contextual reasoning, and adaptive decision-making. We further provide Workspace-Bench-Lite, a 100-task subset that preserves the benchmark distribution while reducing evaluation costs by about 70%. We evaluate 4 popular agent harnesses and 7 foundation models. Experimental results show that current agents remain far from reliable workspace learning, where the best reaches only 68.7%, substantially below the human result of 80.7%, and the average performance across agents is only 47.4%.</p> - https://arxiv.org/abs/2605.03596 - Tue, 05 May 2026 00:00:00 +0000 - - - PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination - https://arxiv.org/abs/2605.03571 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03571.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiyao Wang, Xinyi Chen, Longze Chen, Hongbo Wang, Hamid Alinejad-Rokny, Yuan Lin, Min Yang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Patent examination is a complex, multi-stage process requiring both technical expertise and legal reasoning, increasingly challenged by rising application volumes. Prior benchmarks predominantly view patent examination as discriminative classification or static extraction, failing to capture its inherently interactive and iterative nature, similar to the peer review and rebuttal process in academic publishing. In this paper, we introduce PatRe, the first benchmark that models the full patent examination lifecycle, including Office Action generation and applicant rebuttal. PatRe comprises 480 real-world cases and supports both oracle and retrieval-simulated evaluation settings. Our benchmark reframes patent examination as a dynamic, multi-turn process of justification and response. Extensive experiments across various LLMs reveal critical insights into model performance, including differences between proprietary and open-source models, as well as task asymmetries between examiner analysis and applicant-side rebuttal. These findings highlight both the potential and current limitations of LLMs in modeling complex, real-world legal reasoning and technical novelty judgment in patent examination. We release our code and dataset to facilitate future research on patent examination modeling.</p> - https://arxiv.org/abs/2605.03571 - Tue, 05 May 2026 00:00:00 +0000 - - - SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment - https://arxiv.org/abs/2605.04012 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04012.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Joseph Breda, Fadi Yousif, Beszel Hawkins, Marinela Cotoi, Miao Liu, Ray Luo, Po-Hsuan Cameron Chen, Mike Schaekermann, Samuel Schmidgall, Xin Liu, Girish Narayanswamy, Samuel Solomon, Maxwell A. Xu, Xiaoran Fan, Longfei Shangguan, Anran Wang, Bhavna Daryani, Buddy Herkenham, Cara Tan, Mark Malhotra, Shwetak Patel, John B. Hernandez, Quang Duong, Yun Liu, Zach Wasson, Dimitrios Antos, Bob Lou, Matthew Thompson, Jonathan Richina, Anupam Pathak, Nichole Young-Lin, Jake Sunshine, Daniel McDuff</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Language models excel at diagnostic assessments on currated medical case-studies and vignettes, performing on par with, or better than, clinical professionals. However, existing studies focus on complex scenarios with rich context making it difficult to draw conclusions about how these systems perform for patients reporting symptoms in everyday life. We deployed SymptomAI, a set of conversational AI agents for end-to-end patient interviewing and differential diagnosis (DDx), via the Fitbit app in a study that randomized participants (N=13,917) to interact with five AI agents. This corpus captures diverse communication and a realistic distribution of illnesses from a real world population. A subset of 1,228 participants reported a clinician-provided diagnosis, and 517 of these were further evaluated by a panel of clinicians during over 250 hours of annotation. SymptomAI DDx were significantly more accurate (OR = 2.47, p < 0.001) than those from independent clinicians given the same dialogue in a blinded randomized comparison. Moreover, agentic strategies which conduct a dedicated symptom interview that elicit additional symptom information before providing a diagnosis, perform substantially better than baseline, user-guided conversations (p < 0.001). An auxiliary analysis on 1,509 conversations from a general US population panel validated that these results generalize beyond wearable device users. We used SymptomAI diagnoses as labels for all 13,917 participants to analyze over 500,000 days of wearable metrics across nearly 400 unique conditions. We identified strong associations between acute infections and physiological shifts (e.g., OR > 7 for influenza). While limited by self-reported ground truth, these results demonstrate the benefits of a dedicated and complete symptom interview compared to a user-guided symptom discussion, which is the default of most consumer LLMs.</p> - https://arxiv.org/abs/2605.04012 - Tue, 05 May 2026 00:00:00 +0000 - - - Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation - https://arxiv.org/abs/2605.04128 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04128.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lin Song, Wenbo Li, Guoqing Ma, Wei Tang, Bo Wang, Yuan Zhang, Yijun Yang, Yicheng Xiao, Jianhui Liu, Yanbing Zhang, Guohui Zhang, Wenhu Zhang, Hang Xu, Nan Jiang, Xin Han, Haoze Sun, Maoquan Zhang, Haoyang Huang, Nan Duan</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing. JoyAI-Image couples a spatially enhanced Multimodal Large Language Model (MLLM) with a Multimodal Diffusion Transformer (MMDiT), allowing perception and generation to interact through a shared multimodal interface. Around this architecture, we build a scalable training recipe that combines unified instruction tuning, long-text rendering supervision, spatially grounded data, and both general and spatial editing signals. This design gives the model broad multimodal capability while strengthening geometry-aware reasoning and controllable visual synthesis. Experiments across understanding, generation, long-text rendering, and editing benchmarks show that JoyAI-Image achieves state-of-the-art or highly competitive performance. More importantly, the bidirectional loop between enhanced understanding, controllable spatial editing, and novel-view-assisted reasoning enables the model to move beyond general visual competence toward stronger spatial intelligence. These results suggest a promising path for unified visual models in downstream applications such as vision-language-action systems and world models.</p> - https://arxiv.org/abs/2605.04128 - Tue, 05 May 2026 00:00:00 +0000 - - - Audio-Visual Intelligence in Large Foundation Models - https://arxiv.org/abs/2605.04045 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04045.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> You Qin, Kai Liu, Shengqiong Wu, Kai Wang, Shijian Deng, Yapeng Tian, Junbin Xiao, Yazhou Xing, Yinghao Ma, Bobo Li, Roger Zimmermann, Lei Cui, Furu Wei, Jiebo Luo, Hao Fei</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Audio-Visual Intelligence (AVI) has emerged as a central frontier in artificial intelligence, bridging auditory and visual modalities to enable machines that can perceive, generate, and interact in the multimodal real world. In the era of large foundation models, joint modeling of audio and vision has become increasingly crucial, i.e., not only for understanding but also for controllable generation and reasoning across dynamic, temporally grounded signals. Recent advances, such as Meta MovieGen and Google Veo-3, highlight the growing industrial and academic focus on unified audio-vision architectures that learn from massive multimodal data. However, despite rapid progress, the literature remains fragmented, spanning diverse tasks, inconsistent taxonomies, and heterogeneous evaluation practices that impede systematic comparison and knowledge integration. This survey provides the first comprehensive review of AVI through the lens of large foundation models. We establish a unified taxonomy covering the broad landscape of AVI tasks, ranging from understanding (e.g., speech recognition, sound localization) to generation (e.g., audio-driven video synthesis, video-to-audio) and interaction (e.g., dialogue, embodied, or agentic interfaces). We synthesize methodological foundations, including modality tokenization, cross-modal fusion, autoregressive and diffusion-based generation, large-scale pretraining, instruction alignment, and preference optimization. Furthermore, we curate representative datasets, benchmarks, and evaluation metrics, offering a structured comparison across task families and identifying open challenges in synchronization, spatial reasoning, controllability, and safety. By consolidating this rapidly expanding field into a coherent framework, this survey aims to serve as a foundational reference for future research on large-scale AVI.</p> - https://arxiv.org/abs/2605.04045 - Tue, 05 May 2026 00:00:00 +0000 - - - Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems - https://arxiv.org/abs/2605.04018 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04018.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yilun Zhao, Jinbiao Wei, Tingyu Song, Siyue Zhang, Chen Zhao, Arman Cohan</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Reasoning-intensive retrieval aims to surface evidence that supports downstream reasoning rather than merely matching topical similarity. This capability is increasingly important for agentic search systems, where retrievers must provide complementary evidence across iterative search and synthesis. However, existing work remains limited on both evaluation and training: benchmarks such as BRIGHT provide narrow gold sets and evaluate retrievers in isolation, while synthetic training corpora often optimize single-passage relevance rather than evidence portfolio construction. We introduce BRIGHT-Pro, an expert-annotated benchmark that expands each query with multi-aspect gold evidence and evaluates retrievers under both static and agentic search protocols. We further construct RTriever-Synth, an aspect-decomposed synthetic corpus that generates complementary positives and positive-conditioned hard negatives, and use it to LoRA fine-tune RTriever-4B from Qwen3-Embedding-4B. Experiments across lexical, general-purpose, and reasoning-intensive retrievers show that aspect-aware and agentic evaluation expose behaviors hidden by standard metrics, while RTriever-4B substantially improves over its base model.</p> - https://arxiv.org/abs/2605.04018 - Tue, 05 May 2026 00:00:00 +0000 - - - OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories - https://arxiv.org/abs/2605.04036 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04036.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuwen Du, Rui Ye, Shuo Tang, Keduan Huang, Xinyu Zhu, Yuzhu Cai, Siheng Chen</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominated by industrial giants. The typical industry recipe involves a highly resource-intensive pipeline spanning pre-training, continual pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL). In this report, we show that when fueled with informative and high-difficulty trajectories, a simple SFT approach could be surprisingly powerful for training frontier search agents. By introducing three simple data synthesis modifications: scaling knowledge graph size for richer exploration, expanding the tool set size for broader functionality, and strict low-step filtering, we establish a stronger baseline. Trained on merely 10.6k data points, our OpenSeeker-v2 achieves state-of-the-art performance across 4 benchmarks (30B-sized agents with ReAct paradigm): 46.0% on BrowseComp, 58.1% on BrowseComp-ZH, 34.6% on Humanity's Last Exam, and 78.0% on xbench, surpassing even Tongyi DeepResearch trained with heavy CPT+SFT+RL pipeline, which achieves 43.4%, 46.7%, 32.9%, and 75.0%, respectively. Notably, OpenSeeker-v2 represents the first state-of-the-art search agent within its model scale and paradigm to be developed by a purely academic team using only SFT. We are excited to open-source the OpenSeeker-v2 model weights and share our simple yet effective findings to make frontier search agent research more accessible to the community.</p> - https://arxiv.org/abs/2605.04036 - Tue, 05 May 2026 00:00:00 +0000 - - - RLDX-1 Technical Report - https://arxiv.org/abs/2605.03269 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03269.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongyoung Kim, Huiwon Jang, Myungkyu Koo, Suhyeok Jang, Taeyoung Kim, Beomjun Kim, Byungjun Yoon, Changsung Jang, Daewon Choi, Dongsu Han, Donguk Lee, Heeseung Kwon, Hojin Jeon, Jaehyun Kang, Jaekyoung Bae, Jihyuk Lee, Jimin Lee, John Won, Joonwoo Ahn, Junhyeong Park, Junyoung Sung, Kyungmin Lee, Minseong Han, Minsung Yoon, Sejune Joo, Seonil Son, Seungcheol Park, Seunggeun Cho, Seungjun Moon, Seungku Kim, Yonghoon Dong, Yongjin Cho, Youngchan Kim, Chang Hwan Kim, Dohyeon Kim, Hazel Lee, Heecheol Kim, Hensen Ahn, Hyungkyu Ryu, Hyunsoo Choi, Hyunsoo Shin, Jaeheon Jung, Jaewoo Kim, Jinwook Kim, Joochul Chang, Joonsoo Kim, Junghun Park, Jungwoo Park, Junho Cho, Junhyeok Park, Junwon Lee, Kangwook Lee, Kwanghoon Kim, Kyoungwhan Choe, Manoj Bhadu, Nayoung Oh, Sangjun Kim, Sangwoo Kim, Seunghoon Shim, Seunghyun Kim, Seungjun Lee, Seungyup Ka, Sungryol Yang, Wook Jung, Yashu Shukla, Yeonjae Lee, Yeonwoo Bae, Jinwoo Shin</p><p><b>Upvotes:</b> 104</p><p><b>Summary:</b> While Vision-Language-Action models (VLAs) have shown remarkable progress toward human-like generalist robotic policies through the versatile intelligence (i.e. broad scene understanding and language-conditioned generalization) inherited from pre-trained Vision-Language Models, they still struggle with complex real-world tasks requiring broader functional capabilities (e.g. motion awareness, memory-aware decision making, and physical sensing). To address this, we introduce RLDX-1, a general-purpose robotic policy for dexterous manipulation built on the Multi-Stream Action Transformer (MSAT), an architecture that unifies these capabilities by integrating heterogeneous modalities through modality-specific streams with cross-modal joint self-attention. RLDX-1 further combines this architecture with system-level design choices, including synthesizing training data for rare manipulation scenarios, learning procedures specialized for human-like manipulation, and inference optimizations for real-time deployment. Through empirical evaluation, we show that RLDX-1 consistently outperforms recent frontier VLAs (e.g. π_{0.5} and GR00T N1.6) across both simulation benchmarks and real-world tasks that require broad functional capabilities beyond general versatility. In particular, RLDX-1 shows superiority in ALLEX humanoid tasks by achieving success rates of 86.8% while π_{0.5} and GR00T N1.6 achieve around 40%, highlighting the ability of RLDX-1 to control a high-DoF humanoid robot under diverse functional demands. Together, these results position RLDX-1 as a promising step toward reliable VLAs for complex, contact-rich, and dynamic real-world dexterous manipulation.</p> - https://arxiv.org/abs/2605.03269 - Tue, 05 May 2026 00:00:00 +0000 - - - Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation - https://arxiv.org/abs/2605.03849 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03849.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Wu, Mengqi Huang, Shaojin Wu, Weinan Jia, Yuxin Wang, Zhendong Mao, Yongdong Zhang</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the de facto choice. Existing methods, however, train the student to match the teacher's output indiscriminately, treating every rollout, frame, and pixel as equally reliable supervision. We argue that this caps distilled quality, since it overlooks two complementary axes of variance in DMD supervision: Inter-Reliability across student rollouts whose supervision varies in reliability, and Intra-Perplexity across spatial regions and temporal frames that contribute unequally to where quality can still be improved. The objective thus conflates two questions under a uniform weight: whether to learn from each rollout, and where to concentrate optimization within it. To address this, we propose Stream-R1, a Reliability-Perplexity Aware Reward Distillation framework that adaptively reweights the distillation objective at both rollout and spatiotemporal-element levels through a single shared reward-guided mechanism. At the Inter-Reliability level, Stream-R1 rescales each rollout's loss by an exponential of a pretrained video reward score, so that rollouts with reliable supervision dominate optimization. At the Intra-Perplexity level, it back-propagates the same reward model to extract per-pixel gradient saliency, which is factored into spatial and temporal weights that concentrate optimization pressure on regions and frames where refinement yields the largest expected gain. An adaptive balancing mechanism prevents any single quality axis from dominating across visual quality, motion quality, and text alignment. Stream-R1 attains consistent improvements on all three dimensions over distillation baselines on standard streaming video generation benchmarks, without architectural modification or additional inference cost.</p> - https://arxiv.org/abs/2605.03849 - Tue, 05 May 2026 00:00:00 +0000 - - - A Foundation Model for Zero-Shot Logical Rule Induction - https://arxiv.org/abs/2605.04916 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04916.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yin Jun Phua</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Inductive Logic Programming (ILP) learns interpretable logical rules from data. Existing methods are transductive: their learned parameters are bound to specific predicates and require retraining for each new task. We introduce Neural Rule Inducer (NRI), a pretrained model for zero-shot rule induction. Rather than encoding literal identities, NRI represents literals using domain-agnostic statistical properties such as class-conditional rates, entropy, and co-occurrence, which generalize across variable identities and counts without retraining. The model consists of a statistical encoder and a parallel slot-based decoder. Parallel decoding preserves the permutation invariance of logical disjunction; an autoregressive decoder would instead impose an arbitrary clause order. Product T-norm relaxation makes rule execution differentiable, allowing end-to-end training on prediction accuracy alone. We evaluate NRI on rule recovery, robustness to label noise and spurious correlations, and zero-shot transfer to real-world benchmarks, and we believe this work opens up the possibility of foundation models for symbolic reasoning. Code and the reference checkpoint are available at https://github.com/phuayj/neural-rule-inducer.</p> - https://arxiv.org/abs/2605.04916 + DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents + https://arxiv.org/abs/2605.04808 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04808.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaorun Chen, Xun Liu, Haibo Tong, Chengquan Guo, Yuzhou Nie, Jiawei Zhang, Mintong Kang, Chejian Xu, Qichang Liu, Xiaogeng Liu, Tianneng Shi, Chaowei Xiao, Sanmi Koyejo, Percy Liang, Wenbo Guo, Dawn Song, Bo Li</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and flexibility, such agents raise significant security and safety concerns. A growing number of real-world incidents have shown that adversaries can easily manipulate agents into performing harmful actions, such as leaking API keys, deleting user data, or initiating unauthorized transactions. Evaluating agent security is inherently challenging, as agents operate in dynamic, untrusted environments involving external tools, heterogeneous data sources, and frequent user interactions. However, realistic, controllable, and reproducible environments for large-scale risk assessment remain largely underexplored. To address this gap, we introduce the DecodingTrust-Agent Platform (DTap), the first controllable and interactive red-teaming platform for AI agents, spanning 14 real-world domains and over 50 simulation environments that replicate widely used systems such as Google Workspace, Paypal, and Slack. To scale the risk assessment of agents in DTap, we further propose DTap-Red, the first autonomous red-teaming agent that systematically explores diverse injection vectors (e.g., prompt, tool, skill, environment, combinations) and autonomously discovers effective attack strategies tailored to varying malicious goals. Using DTap-Red, we curate DTap-Bench, a large-scale red-teaming dataset comprising high-quality instances across domains, each paired with a verifiable judge to automatically validate attack outcomes. Through DTap, we conduct large-scale evaluations of popular AI agents built on various backbone models, spanning security policies, risk categories, and attack strategies, revealing systematic vulnerability patterns and providing valuable insights for developing secure next-generation agents.</p> + https://arxiv.org/abs/2605.04808 Wed, 06 May 2026 00:00:00 +0000 - KernelBench-X: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels - https://arxiv.org/abs/2605.04956 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04956.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Wang, Jintao Zhang, Kai Jiang, Haoxu Wang, Jianfei Chen, Jun Zhu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered: where does this capability break down, and why? We present KernelBench-X, a benchmark designed to answer this question through category-aware evaluation of correctness and hardware efficiency across 176 tasks in 15 categories. Our systematic comparison of five representative methods yields three main findings. First, task structure determines correctness more than method design. Category explains nearly three times more variance in semantic correctness than method (9.4% vs 3.3% explained deviance), and 72% of Fusion tasks fail across all five methods while Math tasks are solved consistently. Second, iterative refinement improves correctness, but not performance. Across GEAK iterations, compile rate rises from 52.3% to 68.8% while average speedup declines from 1.58times to 1.44times; newly rescued kernels consistently underperform persistently correct ones (1.16times vs 1.58times speedup in round~0to1). Third, correctness does not imply efficiency. 46.6% of correct kernels are slower than the PyTorch eager baseline, and cross-hardware speedup variance reaches 21.4times. Besides, quantization remains completely unsolved (0/30 successes) despite non-trivial compilation rates, revealing systematic misunderstanding of numerical computation contracts rather than surface-level syntax errors. These findings suggest that future progress depends on handling global coordination, explicitly modeling numerical precision, and incorporating hardware efficiency into generation. The code is available at https://github.com/BonnieW05/KernelBenchX</p> - https://arxiv.org/abs/2605.04956 + Beyond Retrieval: A Multitask Benchmark and Model for Code Search + https://arxiv.org/abs/2605.04615 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04615.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siqiao Xue, Zihan Liao, Jin Qin, Ziyin Zhang, Yixiang Mu, Fan Zhou, Hang Yu</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Code search has usually been evaluated as first-stage retrieval, even though production systems rely on broader pipelines with reranking and developer-style queries. Existing benchmarks also suffer from data contamination, label noise, and degenerate binary relevance. In this paper, we introduce CoREB, a contamination-limited, multitask code retrieval and reranking benchmark, together with a fine-tuned code reranker, that goes beyond retrieval to cover the full code search pipeline. CoREB is built from counterfactually rewritten LiveCodeBench problems in five programming languages and delivered as timed releases with graded relevance judgments. We benchmark eleven embedding models and five rerankers across three tasks: text-to-code, code-to-text, and code-to-code. Our experiments reveal that: \circone code-specialised embeddings dominate code-to-code retrieval ({sim}2{times} over general encoders), yet no single model wins all three tasks; \circtwo short keyword queries, the format closest to real developer search, collapse every model to near-zero nDCG@10; \circthree off-the-shelf rerankers are task-asymmetric, with a 12-point swing on code-to-code and no baseline net-positive across all tasks; \circfour our fine-tuned CoREB-Reranker is the first to achieve consistent gains across all three tasks. The data and model are released.</p> + https://arxiv.org/abs/2605.04615 Wed, 06 May 2026 00:00:00 +0000 - RemoteZero: Geospatial Reasoning with Zero Human Annotations - https://arxiv.org/abs/2605.04451 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04451.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liang Yao, Fan Liu, Shengxiang Xu, Chuanyi Zhang, Rui Min, Shimin Di, Yuhui Zheng</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Geospatial reasoning requires models to resolve complex spatial semantics and user intent into precise target locations for Earth observation. Recent progress has liberated the reasoning path from manual curation, allowing models to generate their own inference chains. Yet a final dependency remains: they are still supervised by human-annotated ground-truth coordinates. This leaves the reasoning process autonomous, but not its spatial endpoint, and prevents true self-evolution on abundant unlabeled remote sensing data. To break this bottleneck, we introduce RemoteZero, a box-supervision-free framework for geospatial reasoning. RemoteZero is motivated by a simple asymmetry: an MLLM is typically better at verifying whether a region satisfies a query than at directly generating precise coordinates. Leveraging this stronger discriminative ability, RemoteZero replaces geometric supervision with intrinsic semantic verification and enables GRPO training without box annotations. The resulting framework further supports iterative self-evolution, allowing the model to improve from unlabeled remote sensing imagery through its own verification signal. Experiments show that RemoteZero achieves competitive performance against strong supervised methods, demonstrating the potential of self-verifying training for geospatial reasoning localization.</p> - https://arxiv.org/abs/2605.04451 - Wed, 06 May 2026 00:00:00 +0000 - - - TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding - https://arxiv.org/abs/2605.04962 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04962.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minjie Qiang, Mingming Zhang, Xiaoyi Bao, Xing Fu, Yu Cheng, Weiqiang Wang, Zhongqing Wang, Ningtao Wang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack retrieval-compatible vector outputs, whereas text embedding models often fail to capture tabular structure and numerical semantics. To bridge this gap, we first introduce the Tabular Embedding Benchmark (TabBench), a comprehensive suite designed to evaluate the tabular understanding capability of embedding models. We then propose TabEmbed, the first generalist embedding model that unifies tabular classification and retrieval within a shared embedding space. By reformulating diverse tabular tasks as semantic matching problems, TabEmbed leverages large-scale contrastive learning with positive-aware hard negative mining to discern fine-grained structural and numerical nuances. Experimental results on TabBench demonstrate that TabEmbed significantly outperforms state-of-the-art text embedding models, establishing a new baseline for universal tabular representation learning. Code and datasets are publicly available at https://github.com/qiangminjie27/TabEmbed and https://huggingface.co/datasets/qiangminjie27/TabBench.</p> - https://arxiv.org/abs/2605.04962 - Wed, 06 May 2026 00:00:00 +0000 - - - ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving - https://arxiv.org/abs/2605.04647 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04647.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huimin Wang, Yue Wang, Bihao Cui, Pengxiang Li, Ben Lu, Mingqian Wang, Tong Wang, Chuan Tang, Teng Zhang, Kun Zhan</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> We introduce ReflectDrive-2, a masked discrete diffusion planner with separate action expert for autonomous driving that represents plans as discrete trajectory tokens and generates them through parallel masked decoding. This discrete token space enables in-place trajectory revision: AutoEdit rewrites selected tokens using the same model, without requiring an auxiliary refinement network. To train this capability, we use a two-stage procedure. First, we construct structure-aware perturbations of expert trajectories along longitudinal progress and lateral heading directions and supervise the model to recover the original expert trajectory. We then fine-tune the full decision--draft--reflect rollout with reinforcement learning (RL), assigning terminal driving reward to the final post-edit trajectory and propagating policy-gradient credit through full-rollout transitions. Full-rollout RL proves crucial for coupling drafting and editing: under supervised training alone, inference-time AutoEdit improves PDMS by at most 0.3, whereas RL increases its gain to 1.9. We also co-design an efficient reflective decoding stack for the decision--draft--reflect pipeline, combining shared-prefix KV reuse, Alternating Step Decode, and fused on-device unmasking. On NAVSIM, ReflectDrive-2 achieves 91.0 PDMS with camera-only input and 94.8 PDMS in a best-of-6 oracle setting, while running at 31.8 ms average latency on NVIDIA Thor.</p> - https://arxiv.org/abs/2605.04647 - Wed, 06 May 2026 00:00:00 +0000 - - - StableI2I: Spotting Unintended Changes in Image-to-Image Transition - https://arxiv.org/abs/2605.04453 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04453.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayang Li, Shuo Cao, Xiaohui Li, Zhizhen Zhang, Kaiwen Zhu, Yule Duan, Yu Qiao, Jian Zhang, Yihao Liu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetics of the generated images. However, they largely fail to assess whether the output image preserves the semantic correspondence and spatial structure of the input image. To address this limitation, we propose StableI2I, a unified and dynamic evaluation framework that explicitly measures content fidelity and pre--post consistency across a wide range of I2I tasks without requiring reference images, including image editing and image restoration. In addition, we construct StableI2I-Bench, a benchmark designed to systematically evaluate the accuracy of MLLMs on such fidelity and consistency assessment tasks. Extensive experimental results demonstrate that StableI2I provides accurate, fine-grained, and interpretable evaluations of content fidelity and consistency, with strong correlations to human subjective judgments. Our framework serves as a practical and reliable evaluation tool for diagnosing content consistency and benchmarking model performance in real-world I2I systems.</p> - https://arxiv.org/abs/2605.04453 - Wed, 06 May 2026 00:00:00 +0000 - - - Lightning Unified Video Editing via In-Context Sparse Attention - https://arxiv.org/abs/2605.04569 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04569.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shitong Shao, Zikai Zhou, Haopeng Li, Yingwei Song, Wenliang Zhong, Lichen Bai, Zeke Xie</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Video editing has evolved toward In-Context Learning (ICL) paradigms, yet the resulting quadratic attention costs create a critical computational bottleneck. In this work, we propose In-context Sparse Attention (ISA), the first near-lossless empirical sparse framework tailored for ICL video editing. Our design is grounded in two key insights: first, context tokens exhibit significantly lower saliency than source tokens; second, we theoretically prove and empirically validate that Query sharpness correlates with approximation error. Motivated by these findings, ISA implements an efficient pre-selection strategy to prune redundant context, followed by a dynamic query grouping mechanism that routes high-error queries to full attention and low-error ones to a computationally efficient 0-th order Taylor sparse attention. Furthermore, we build \texttt{LIVEditor} , a novel lightning video editing model via ISA and a proposed video-editing data pipeline that curated a 1.7M high-quality dataset. Extensive experiments demonstrate that LIVEditor achieves a sim60% reduction in attention-module latency while surpassing state-of-the-art methods across EditVerseBench, IVE-Bench, and VIE-Bench, delivering near-lossless acceleration without compromising visual fidelity.</p> - https://arxiv.org/abs/2605.04569 - Wed, 06 May 2026 00:00:00 +0000 - - - CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing - https://arxiv.org/abs/2605.02910 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02910.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Qian, Hyeonjeong Ha, Jiayu Liu, Jeonghwan Kim, Jiateng Liu, Bingxuan Li, Aditi Tiwari, Dwip Dalal, Zhenhailong Wang, Xiusi Chen, Mahdi Namazifar, Yunzhu Li, Heng Ji</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative problem-solving remains underexplored. We study this capability through the lens of creative tool use, where a model repurposes available objects by reasoning about their affordances and attributes rather than relying on canonical usage. As a first step, we introduce CreativityBench, a benchmark for evaluating affordance-based creativity in LLMs. To this end, we build a large-scale affordance knowledge base (KB) with 4K entities and 150K+ affordance annotations, explicitly linking objects, parts, attributes, and actionable uses. Building on this KB, we generate 14K grounded tasks that require identifying non-obvious yet physically plausible solutions under constraints. Evaluations across 10 state-of-the-art LLMs, including closed and open-source models, show that models can often select a plausible object, but fail to identify the correct parts, their affordances, and the underlying physical mechanism needed to solve the task, leading to a significant drop in performance. Furthermore, improvements from model scaling quickly saturate, strong general reasoning does not reliably translate to creative affordance discovery, and common inference-time strategies such as Chain-of-Thought yield limited gains. These results suggest that creative tool use remains a major challenge for current models, and that CreativityBench provides a useful testbed for studying this missing dimension of intelligence, with potential implications for planning and reasoning modules in future agents.</p> - https://arxiv.org/abs/2605.02910 - Wed, 06 May 2026 00:00:00 +0000 - - - D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models - https://arxiv.org/abs/2605.05204 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05204.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dengyang Jiang, Xin Jin, Dongyang Liu, Zanyi Wang, Mingzhe Zheng, Ruoyi Du, Xiangpeng Yang, Qilong Wu, Zhen Li, Peng Gao, Harry Yang, Steven Hoi</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant challenges for directly continuous supervised fine-tuning. For example, applying the commonly used fine-tuning technique would compromises their inherent few-step inference capability. To address this, we propose D-OPSD, a novel training paradigm for step-distilled diffusion models that enables on-policy learning during supervised fine-tuning. We first find that the modern diffusion model where the LLM/VLM serves as the encoder can inherit its encoder's in-context capabilities. This enables us to make the training as an on-policy self-distillation process. Specifically, during training, we make the model acts as both the teacher and the student with different contexts, where the student is conditioned only on the text feature, while the teacher is conditioned on the multimodal feature of both the text prompt and the target image. Training minimizes the two predicted distributions over the student's own roll-outs. By optimized on the model's own trajectory and under it's own supervision, D-OPSD enables the model to learn new concept, style, etc. without sacrificing the original few-step capacity.</p> - https://arxiv.org/abs/2605.05204 - Wed, 06 May 2026 00:00:00 +0000 - - - PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World - https://arxiv.org/abs/2605.05163 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05163.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunhan Yang, Chunshi Wang, Junliang Ye, Yang Li, Zanxin Chen, Zehuan Huang, Yao Mu, Zhuo Chen, Chunchao Guo, Xihui Liu</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on static geometry, overlooking the functional properties essential for interaction. We propose that interactive asset generation must be rooted in functional logic and hierarchical physics. To bridge this gap, we introduce PhysForge, a decoupled two-stage framework supported by PhysDB, a large-scale dataset of 150,000 assets with four-tier physical annotations. First, a VLM acts as a "physical architect" to plan a "Hierarchical Physical Blueprint" defining material, functional, and kinematic constraints. Second, a physics-grounded diffusion model realizes this blueprint by synthesizing high-fidelity geometry alongside precise kinematic parameters via a novel KineVoxel Injection (KVI) mechanism. Experiments demonstrate that PhysForge produces functionally plausible, simulation-ready assets, providing a robust data engine for interactive 3D content and embodied agents.</p> - https://arxiv.org/abs/2605.05163 - Wed, 06 May 2026 00:00:00 +0000 - - - RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation - https://arxiv.org/abs/2605.04523 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04523.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ivan Bondarenko, Roman Derunets, Oleg Sedukhin, Mikhail Komarov, Ivan Chernov, Mikhail Kulakov</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> We present our winning system for Task~B (generation with reference passages) in SemEval-2026 Task~8: MTRAGEval. Our method is a heterogeneous ensemble of seven LLMs with two prompting variants, where a GPT-4o-mini judge selects the best candidate per instance. We ranked 1st out of 26 teams, achieving a conditioned harmonic mean of 0.7827 and outperforming the strongest baseline (gpt-oss-120b, 0.6390). Ablations show that diversity in model families, scales, and prompting strategies is essential, with the ensemble consistently beating any single model. We also introduce Meno-Lite-0.1, a 7B domain-adapted model with a strong cost--performance trade-off, and analyse MTRAGEval, highlighting annotation limitations and directions for improvement. Our code is publicly available: https://github.com/RaguTeam/ragu_mtrag_semeval</p> - https://arxiv.org/abs/2605.04523 - Wed, 06 May 2026 00:00:00 +0000 - - - OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents - https://arxiv.org/abs/2605.05185 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuang Chen, Kaituo Feng, Hangting Chen, Wenxuan Huang, Dasen Dai, Quanxin Shou, Yunlong Lin, Xiangyu Yue, Shenghua Gao, Tianyu Pang</p><p><b>Upvotes:</b> 92</p><p><b>Summary:</b> Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimodal search agents remain difficult to reproduce, largely due to the absence of open high-quality training data, transparent trajectory synthesis pipelines, or detailed training recipes. To this end, we introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning. First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding, which jointly reduce shortcuts and one-step retrieval collapse. Based on this pipeline, we curate two training datasets, SearchVL-SFT-36k for SFT and SearchVL-RL-8k for RL. Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction, enabling agents to combine active perception with external knowledge acquisition. Finally, we propose a multi-turn fatal-aware GRPO training algorithm that handles cascading tool failures by masking post-failure tokens while preserving useful pre-failure reasoning through one-sided advantage clamping. Built on this recipe, OpenSearch-VL delivers substantial performance gains, with over 10-point average improvements across seven benchmarks, and achieves results comparable to proprietary commercial models on several tasks. We will release all data, code, and models to support open research on multimodal deep search agents.</p> - https://arxiv.org/abs/2605.05185 - Wed, 06 May 2026 00:00:00 +0000 - - - Stream-T1: Test-Time Scaling for Streaming Video Generation - https://arxiv.org/abs/2605.04461 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04461.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yijing Tu, Shaojin Wu, Mengqi Huang, Wenchuan Wang, Yuxin Wang, Chunxiao Liu, Zhendong Mao</p><p><b>Upvotes:</b> 98</p><p><b>Summary:</b> While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on diffusion models suffer from exorbitant candidate exploration costs and lack temporal guidance. To address these structural bottlenecks, we propose shifting the focus to streaming video generation. We identify that its chunk-level synthesis and few denoising steps are intrinsically suited for TTS, significantly lowering computational overhead while enabling fine-grained temporal control. Driven by this insight, we introduced Stream-T1, a pioneering comprehensive TTS framework exclusively tailored for streaming video generation. Specifically, Stream-T1 is composed of three units: (1) Stream -Scaled Noise Propagation, which actively refines the initial latent noise of the generating chunk using historically proven, high-quality previous chunk noise, effectively establishes temporal dependency and utilizing the historical Gaussian prior to guide the current generation; (2) Stream -Scaled Reward Pruning, which comprehensively evaluates generated candidates to strike an optimal balance between local spatial aesthetics and global temporal coherence by integrating immediate short-term assessments with sliding-window-based long-term evaluations; (3) Stream-Scaled Memory Sinking, which dynamically routes the context evicted from KV-cache into distinct updating pathways guided by the reward feedback, ensuring that previously generated visual information effectively anchors and guides the subsequent video stream. Evaluated on both 5s and 30s comprehensive video benchmarks, Stream-T1 demonstrates profound superiority, significantly improving temporal consistency, motion smoothness, and frame-level visual quality.</p> - https://arxiv.org/abs/2605.04461 - Wed, 06 May 2026 00:00:00 +0000 - - - PianoCoRe: Combined and Refined Piano MIDI Dataset - https://arxiv.org/abs/2605.06627 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06627.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ilya Borovik</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Symbolic music datasets with matched scores and performances are essential for many music information retrieval (MIR) tasks. Yet, existing resources often cover a narrow range of composers, lack performance variety, omit note-level alignments, or use inconsistent naming formats. This work presents PianoCoRe, a large-scale piano MIDI dataset that unifies and refines major open-source piano corpora. The dataset contains 250,046 performances of 5,625 pieces written by 483 composers, totaling 21,763 h of performed music. PianoCoRe is released in tiered subsets to support different applications: from large-scale analysis and pre-training (PianoCoRe-C and deduplicated PianoCoRe-B) to expressive performance modeling with note-level score alignment (PianoCoRe-A/A*). The note-aligned subset, PianoCoRe-A, provides the largest open-source collection of 157,207 performances aligned to 1,591 scores to date. In addition to the dataset, the contributions are: (1) a MIDI quality classifier for detecting corrupted and score-like transcriptions and (2) RAScoP, an alignment refinement pipeline that cleans temporal alignment errors and interpolates missing notes. The analysis shows that the refinement reduces temporal noise and eliminates tempo outliers. Moreover, an expressive performance rendering model trained on PianoCoRe demonstrates improved robustness to unseen pieces compared to models trained on raw or smaller datasets. PianoCoRe provides a ready-to-use foundation for the next generation of expressive piano performance research.</p> - https://arxiv.org/abs/2605.06627 + A^2RD: Agentic Autoregressive Diffusion for Long Video Consistency + https://arxiv.org/abs/2605.06924 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06924.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Do Xuan Long, Yale Song, Min-Yen Kan, Tomas Pfister, Long T. Le</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Synthesizing consistent and coherent long video remains a fundamental challenge. Existing methods suffer from semantic drift and narrative collapse over long horizons. We present A^2RD, an Agentic Auto-Regressive Diffusion architecture that decouples creative synthesis from consistency enforcement. A^2RD formulates long video synthesis as a closed-loop process that synthesizes and self-improves video segment-by-segment through a Retrieve--Synthesize--Refine--Update cycle. It comprises three core components: (i) Multimodal Video Memory that tracks video progression across modalities; (ii) Adaptive Segment Generation that switches among generation modes for natural progression and visual consistency; and (iii) Hierarchical Test-Time Self-Improvement that self-improves each segment at frame and video levels to prevent error propagation. We further introduce LVBench-C, a challenging benchmark with non-linear entity and environment transitions to stress-test long-horizon consistency. Across public and LVBench-C benchmarks spanning one- to ten-minute videos, A^2RD outperforms state-of-the-art baselines by up to 30% in consistency and 20% in narrative coherence. Human evaluations corroborate these gains while also highlighting notable improvements in motion and transition smoothness.</p> + https://arxiv.org/abs/2605.06924 Thu, 07 May 2026 00:00:00 +0000 - XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity - https://arxiv.org/abs/2605.05662 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05662.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dasol Choi, Eugenia Kim, Jaewon Noh, Sang Seo, Eunmi Kim, Myunggyo Oh, Yunjin Park, Brigitta Jesica Kartono, Josef Pichlmeier, Helena Berndt, Sai Krishna Mendu, Glenn Johannes Tungka, Özlem Gökçe, Suresh Gehlot, Katherine Pratt, Amanda Minnich, Haon Park</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as distinct from universal harms. We introduce XL-SafetyBench. a suite of 5,500 test cases across 10 country-language pairs, comprising a Jailbreak Benchmark of country-grounded adversarial prompts and a Cultural Benchmark where local sensitivities are embedded within innocuous requests. Each item is constructed via a multi-stage pipeline that combines LLM-assisted discovery, automated validation gates, and dual independent native-speaker annotators per country. To distinguish principled refusal from comprehension failure, we evaluate Attack Success Rate (ASR) alongside two complementary metrics we introduce: Neutral-Safe Rate (NSR) and Cultural Sensitivity Rate (CSR). Evaluating 10 frontier and 27 local LLMs reveals two key findings. First, jailbreak robustness and cultural awareness do not show a coupled relationship among frontier models, so a composite safety score obscures per-axis variation. Second, local models exhibit a near-linear ASR-NSR trade-off (r = -0.81), indicating that their apparent safety reflects generation failure rather than genuine alignment. XL-SafetyBench enables more nuanced, cross-cultural safety evaluation in the multilingual era.</p> - https://arxiv.org/abs/2605.05662 + UniSD: Towards a Unified Self-Distillation Framework for Large Language Models + https://arxiv.org/abs/2605.06597 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06597.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiqiao Jin, Yiyang Wang, Lucheng Fu, Yijia Xiao, Yinyi Luo, Haoxin Liu, B. Aditya Prakash, Josiah Hester, Jindong Wang, Srijan Kumar</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD in autoregressive LLMs remains challenging because self-generated trajectories are free-form, correctness is task-dependent, and plausible rationales can still provide unstable or unreliable supervision. Existing methods mainly examine isolated design choices, leaving their effectiveness, roles, and interactions unclear. In this paper, we propose UniSD, a unified framework to systematically study self-distillation. UniSD integrates complementary mechanisms that address supervision reliability, representation alignment, and training stability, including multi-teacher agreement, EMA teacher stabilization, token-level contrastive learning, feature matching, and divergence clipping. Across six benchmarks and six models from three model families, UniSD reveals when self-distillation improves over static imitation, which components drive the gains, and how these components interact across tasks. Guided by these insights, we construct UniSDfull, an integrated pipeline that combines complementary components and achieves the strongest overall performance, improving over the base model by +5.4 points and the strongest baseline by +2.8 points. Extensive evaluation highlights self-distillation as a practical and steerable approach for efficient LLM adaptation without stronger external teachers.</p> + https://arxiv.org/abs/2605.06597 Thu, 07 May 2026 00:00:00 +0000 - The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models - https://arxiv.org/abs/2605.06196 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06196.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chonghan Qin, Xiachong Feng, Ziyun Song, Xiaocheng Feng, Jing Xiong, Lingpeng Kong</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large language models (LLMs) are routinely prompted to take on social roles ranging from individuals to institutions, yet it remains unclear whether their internal representations encode the granularity of such roles, from micro-level individual experience to macro-level organizational, institutional, or national reasoning. We show that they do. We define a contrast-based Granularity Axis as the difference between mean macro- and micro-role hidden states. In Qwen3-8B, this axis aligns with the principal axis (PC1) of the role representation space at cosine 0.972 and accounts for 52.6% of its variance, indicating that granularity is the dominant geometric axis organizing prompted social roles. We construct 75 social roles across five granularity levels and collect 91,200 role-conditioned responses over shared questions and prompt variants, then extract role-level hidden states and project them onto the axis. Role projections increase monotonically across all five levels, remain stable across layers, prompt variants, endpoint definitions, held-out splits, and score-filtered subsets, and transfer to Llama-3.1-8B-Instruct. The axis is also causally relevant: activation steering along it shifts response granularity in the predicted direction, with Llama moving from 2.00 to 3.17 on a five-point macro scale under positive steering on prompts that admit local responses. The two models differ in controllability, suggesting that steering depends on each model's default operating regime. Overall, our findings suggest that social role granularity is not merely a stylistic surface feature, but a structured, ordered, and causally manipulable latent direction in role-conditioned language model behavior.</p> - https://arxiv.org/abs/2605.06196 + 4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding + https://arxiv.org/abs/2605.05997 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05997.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhangquan Chen, Manyuan Zhang, Xinlei Yu, Xiang An, Bo Li, Xin Xie, ZiDong Wang, Mingze Sun, Shuang Chen, Hongyu Li, Xiaobin Hu, Ruqi Huang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Dynamic spatial reasoning from monocular video is essential for bridging visual intelligence and the physical world, yet remains challenging for vision-language models (VLMs). Prior approaches either verbalize spatial-temporal reasoning entirely as text, which is inherently verbose and imprecise for complex dynamics, or rely on external geometric modules that increase inference complexity without fostering intrinsic model capability. In this paper, we present 4DThinker, the first framework that enables VLMs to "think with 4D" through dynamic latent mental imagery, i.e., internally simulating how scenes evolve within the continuous hidden space. Specifically, we first introduce a scalable, annotation-free data generation pipeline that synthesizes 4D reasoning data from raw videos. We then propose Dynamic-Imagery Fine-Tuning (DIFT), which jointly supervises textual tokens and 4D latents to ground the model in dynamic visual semantics. Building on this, 4D Reinforcement Learning (4DRL) further tackles complex reasoning tasks via outcome-based rewards, restricting policy gradients to text tokens to ensure stable optimization. Extensive experiments across multiple dynamic spatial reasoning benchmarks demonstrate that 4DThinker consistently outperforms strong baselines and offers a new perspective toward 4D reasoning in VLMs. Our code is available at https://github.com/zhangquanchen/4DThinker.</p> + https://arxiv.org/abs/2605.05997 Thu, 07 May 2026 00:00:00 +0000 - SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation - https://arxiv.org/abs/2605.06356 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06356.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> YaoYang Liu, Yuechen Zhang, Wenbo Li, Yufei Zhao, Rui Liu, Long Chen</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> High-resolution image-to-video (I2V) generation aims to synthesize realistic temporal dynamics while preserving fine-grained appearance details of the input image. At 2K resolution, it becomes extremely challenging, and existing solutions suffer from various weaknesses: 1) end-to-end models are often prohibitively expensive in memory and latency; 2) cascading low-resolution generation with a generic video super-resolution tends to hallucinate details and drift from input-specific local structures, since the super-resolution stage is not explicitly conditioned on the input image. To this end, we propose SwiftI2V, an efficient framework tailored for high-resolution I2V. Following the widely used two-stage design, it addresses the efficiency--fidelity dilemma by first generating a low-resolution motion reference to reduce token costs and ease the modeling burden, then performing a strongly image-conditioned 2K synthesis guided by the motion to recover input-faithful details with controlled overhead. Specifically, to make generation more scalable, SwiftI2V introduces Conditional Segment-wise Generation (CSG) to synthesize videos segment-by-segment with a bounded per-step token budget, and adopts bidirectional contextual interaction within each segment to improve cross-segment coherence and input fidelity. On VBench-I2V at 2K resolution, SwiftI2V achieves performance comparable to end-to-end baselines while reducing total GPU-time by 202x. Particularly, it enables practical 2K I2V generation on a single datacenter GPU (e.g., H800) or consumer GPU (e.g., RTX 4090).</p> - https://arxiv.org/abs/2605.06356 + UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification + https://arxiv.org/abs/2605.06221 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qihang Fan, Huaibo Huang, Zhiying Wu, Bingning Wang, Ran He</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> As large language models (LLMs) continue to advance rapidly, they are becoming increasingly capable while simultaneously demanding ever-longer context lengths. To improve the inference efficiency of long-context processing, several novel low-complexity hybrid architectures have recently been proposed, effectively alleviating the computational burden of long-context inference. However, existing research on long-context prefill acceleration remains predominantly focused on sparse attention mechanisms, which achieve their maximum speedup only on full-attention models. When transferred to emerging architectures--such as linear/full attention hybrids or sliding window/full attention hybrids--these prefill acceleration approaches suffer significant performance degradation. Furthermore, such methods are generally incompatible with continuous batching, making them difficult to integrate into modern inference engines such as vLLM. To this end, we propose UniPrefill, a prefill acceleration framework applicable to virtually any model architecture, which directly accelerates the model's computation at the token level. We further implement UniPrefill as a continuous batching operator and extend vLLM's scheduling strategy to natively support prefill-decode co-processing and tensor parallel for UniPrefill, enabling its seamless integration into vLLM. UniPrefill achieves up to 2.1x speedup in Time-To-First-Token (TTFT), with the acceleration becoming increasingly pronounced as the number of concurrent requests grows.</p> + https://arxiv.org/abs/2605.06221 Thu, 07 May 2026 00:00:00 +0000 - TIDE: Every Layer Knows the Token Beneath the Context - https://arxiv.org/abs/2605.06216 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06216.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ajay Jaiswal, Lauren Hannah, Han-Byul Kim, Duc Hoang, Mehrdad Farajtabar, Minsik Cho</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We revisit a universally accepted but under-examined design choice in every modern LLM: a token index is looked up once at the input embedding layer and then permanently discarded. This single-injection assumption induces two structural failures: (i) the Rare Token Problem, where a Zipf-type distribution of vocabulary causes rare-token embeddings are chronically under-trained due to receiving a fraction of the cumulative gradient signal compared to common tokens; and (ii) the Contextual Collapse Problem, where limited parameters models map distributionally similar tokens to indistinguishable hidden states. As an attempt to address both, we propose TIDE, which augments the standard transformer with EmbeddingMemory: an ensemble of K independent MemoryBlocks that map token indices to context-free semantic vectors, computed once and injected into every layer through a depth-conditioned softmax router with a learnable null bank. We theoretically and empirically establish the benefits of TIDE in addressing the issues associated with single-token identity injection as well as improve performance across multiple language modeling and downstream tasks.</p> - https://arxiv.org/abs/2605.06216 + Long Context Pre-Training with Lighthouse Attention + https://arxiv.org/abs/2605.06554 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06554.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Peng, Subho Ghosh, Jeffrey Quesnelle</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based hierarchical attention algorithm that wraps around ordinary SDPA and can be easily removed towards the end of the training. Our hierarchical selection is also gradient-free, which exempts us from dealing with a complicated and potentially inefficient backward pass kernel. Our contribution is three-fold: (i) A subquadratic hierarchical pre- and post-processing step that does adaptive compression and decompression of the sequence. (ii) A symmetrical compression strategy that pools queries, keys and values at the same time, while preserving left-to-right causality, which greatly improves parallelism. (iii) A two stage training approach which we pre-train for the majority of the time with Lighthouse Attention and recover a full attention model at the end with a short training. We run preliminary small scale LLM pre-training experiments that show the effectiveness of our method compared to full attention training with all other settings matched, where we achieve a faster total training time and lower final loss after the recovery phase. Full code is available at: https://github.com/ighoshsubho/lighthouse-attention</p> + https://arxiv.org/abs/2605.06554 Thu, 07 May 2026 00:00:00 +0000 - EMO: Pretraining Mixture of Experts for Emergent Modularity - https://arxiv.org/abs/2605.06663 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06663.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ryan Wang, Akshita Bhagia, Sewon Min</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs) seemingly offer a potential alternative by activating only a subset of experts per input, but in practice, restricting inference to a subset of experts for a given domain leads to severe performance degradation. This limits their practicality in memory-constrained settings, especially as models grow larger and sparser. We introduce EMO, an MoE designed for modularity-the independent use and composition of expert subsets-without requiring human-defined priors. Our key idea is to encourage tokens from similar domains to rely on similar experts. Since tokens within a document often share a domain, EMO restricts them to select experts from a shared pool, while allowing different documents to use different pools. This simple constraint enables coherent expert groupings to emerge during pretraining using document boundaries alone. We pretrain a 1B-active, 14B-total EMO on 1T tokens. As a full model, it matches standard MoE performance. Crucially, it enables selective expert use: retaining only 25% (12.5%) of experts incurs just a 1% (3%) absolute drop, whereas standard MoEs break under the same setting. We further find that expert subsets in EMO specialize at semantic levels (e.g., domains such as math or code), in contrast to the low-level syntactic specialization observed in standard MoEs. Altogether, our results demonstrate a path toward modular, memory-efficient deployment of large, sparse models and open new opportunities for composable architectures.</p> - https://arxiv.org/abs/2605.06663 + Efficient Pre-Training with Token Superposition + https://arxiv.org/abs/2605.06546 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06546.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Peng, Théo Gigant, Jeffrey Quesnelle</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training (TST), a simple drop-in method that significantly improves the data throughput per FLOPs during pre-training without modifying the parallelism, optimizer, tokenizer, data, or model architecture. TST is done in two phases: (i) A highly efficient superposition phase where we combine many contiguous tokens into one bag and train using a multi-hot cross-entropy (MCE) objective, and (ii) a recovery phase where we revert back to standard training. We extensively evaluate TST on the scale of 270M and 600M parameters and validate on 3B and a 10B A1B mixture of experts model, demonstrating that it is highly robust in different settings. Ultimately, TST consistently outperforms baseline loss and downstream evaluations, and under equal-loss settings, TST yields up to a 2.5x reduction in total pre-training time at the 10B A1B scale.</p> + https://arxiv.org/abs/2605.06546 Thu, 07 May 2026 00:00:00 +0000 - UniPool: A Globally Shared Expert Pool for Mixture-of-Experts - https://arxiv.org/abs/2605.06665 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06665.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minbin Huang, Han Shi, Chuanyang Zheng, Yimeng Wu, Guoxuan Chen, Xintong Yu, Yichun Yin, Hong Cheng</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Modern Mixture-of-Experts (MoE) architectures allocate expert capacity through a rigid per-layer rule: each transformer layer owns a separate expert set. This convention couples depth scaling with linear expert-parameter growth and assumes that every layer needs isolated expert capacity. However, recent analyses and our routing probe challenge this allocation rule: replacing a deeper layer's learned top-k router with uniform random routing drops downstream accuracy by only 1.0-1.6 points across multiple production MoE models. Motivated by this redundancy, we propose UniPool, an MoE architecture that treats expert capacity as a global architectural budget by replacing per-layer expert ownership with a single shared pool accessed by independent per-layer routers. To enable stable and balanced training under sharing, we introduce a pool-level auxiliary loss that balances expert utilization across the entire pool, and adopt NormRouter to provide sparse and scale-stable routing into the shared expert pool. Across five LLaMA-architecture model scales (182M, 469M, 650M, 830M, and 978M parameters) trained on 30B tokens from the Pile, UniPool consistently improves validation loss and perplexity over the matched vanilla MoE baselines. Across these scales, UniPool reduces validation loss by up to 0.0386 relative to vanilla MoE. Beyond raw loss improvement, our results identify pool size as an explicit depth-scaling hyperparameter: reduced-pool UniPool variants using only 41.6%-66.7% of the vanilla expert-parameter budget match or outperform layer-wise MoE at the tested scales. This shows that, under a shared-pool design, expert parameters need not grow linearly with depth; they can grow sublinearly while remaining more efficient and effective than vanilla MoE. Further analysis shows that UniPool's benefits compose with finer-grained expert decomposition.</p> - https://arxiv.org/abs/2605.06665 + STALE: Can LLM Agents Know When Their Memories Are No Longer Valid? + https://arxiv.org/abs/2605.06527 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06527.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanxiang Chao, Yihan Bai, Rui Sheng, Tianle Li, Yushi Sun</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new evidence emerges. We identify a critical and underexplored failure mode, Implicit Conflict: a later observation invalidates an earlier memory without explicit negation, requiring contextual inference and commonsense reasoning to detect. To rigorously evaluate this capability, we introduce STALE, a benchmark of 400 expert-validated conflict scenarios (1,200 evaluation queries across three probing dimensions) spanning over 100 everyday topics with contexts up to 150K tokens. We propose a three-dimensional probing framework that tests State Resolution (detecting that a prior belief is outdated), Premise Resistance (rejecting queries that falsely presuppose a stale state), and Implicit Policy Adaptation (proactively applying updated states in downstream behavior). A systematic evaluation of frontier LLMs and specialized memory frameworks reveals a pervasive gap between retrieving updated evidence and acting on it, with even the best evaluated model achieving only 55.2% overall accuracy. Models often accept outdated assumptions embedded in a user's query, and they struggle to recognize when a change in one aspect of the user's state should invalidate related memories. To establish an initial baseline for state-aware memory, we further present CUPMem, a prototype that strengthens write-time revision through structured state consolidation and propagation-aware search, suggesting that explicit state adjudication is a promising direction for robust agentic memory.</p> + https://arxiv.org/abs/2605.06527 Thu, 07 May 2026 00:00:00 +0000 - AI Co-Mathematician: Accelerating Mathematicians with Agentic AI - https://arxiv.org/abs/2605.06651 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06651.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniel Zheng, Ingrid von Glehn, Yori Zwols, Iuliya Beloshapka, Lars Buesing, Daniel M. Roy, Martin Wattenberg, Bogdan Georgiev, Tatiana Schmidt, Andrew Cowie, Fernanda Viegas, Dimitri Kanevsky, Vineet Kahlon, Hartmut Maennel, Sophia Alj, George Holland, Alex Davies, Pushmeet Kohli</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support for the exploratory and iterative reality of mathematical workflows, including ideation, literature search, computational exploration, theorem proving and theory building. By providing an asynchronous, stateful workspace that manages uncertainty, refines user intent, tracks failed hypotheses, and outputs native mathematical artifacts, the system mirrors human collaborative workflows. In early tests, the AI co-mathematician helped researchers solve open problems, identify new research directions, and uncover overlooked literature references. Besides demonstrating a highly interactive paradigm for AI-assisted mathematical discovery, the AI co-mathematician also achieves state of the art results on hard problem-solving benchmarks, including scoring 48% on FrontierMath Tier 4, a new high score among all AI systems evaluated.</p> - https://arxiv.org/abs/2605.06651 + HumanNet: Scaling Human-centric Video Learning to One Million Hours + https://arxiv.org/abs/2605.06747 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06747.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufan Deng, Daquan Zhou</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Progress in embodied intelligence increasingly depends on scalable data infrastructure. While vision and language have scaled with internet corpora, learning physical interaction remains constrained by the lack of large, diverse, and richly annotated human activity data. We present HumanNet, a one-million-hour human-centric video corpus that captures how humans interact with the physical world at scale. HumanNet spans both first-person and third-person perspectives and covers fine-grained activities, human-object interactions, tool use, and long-horizon behaviors across diverse real-world environments. Beyond raw video, the dataset provides interaction-centric annotations, including captions, motion descriptions, and hand and body-related signals, enabling motion-aware and interaction-aware learning. Beyond scale, HumanNet introduces a systematic data curation paradigm for embodied learning, where human-centric filtering, temporal structuring, viewpoint diversity, and annotation enrichment are treated as first-class design principles. This design transforms unstructured internet video into a scalable substrate for representation learning, activity understanding, motion generation, and human-to-robot transfer. We conduct a first-step validation on the value of this design through controlled vision-language-action ablation: under a fixed set of validation data, continued training from the Qwen VLM model with 1000 hours of egocentric video drawn from HumanNet surpasses the continued training with 100 hours of real-robot data from Magic Cobot, indicating that egocentric human video could be a scalable and cost-effective substitute for robot data. By building this project, we aim to explore the opportunity to scale embodied foundation models using human-centric videos, rather than relying solely on robot-specific data.</p> + https://arxiv.org/abs/2605.06747 Thu, 07 May 2026 00:00:00 +0000 - Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key - https://arxiv.org/abs/2605.06638 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianle Wang, Zhaoyang Wang, Guangchen Lan, Xinpeng Wei, Sipeng Zhang, Guanwen Qiu, Abulhair Saparov</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Reinforcement learning (RL) has been applied to improve large language model (LLM) reasoning, yet the systematic study of how training scales with task difficulty has been hampered by the lack of controlled, scalable environments. We introduce ScaleLogic, a synthetic logical reasoning framework that offers independent control over two axes of difficulty: the depth of the required proof planning (i.e., the horizon) and the expressiveness of the underlying logic. Our proposed framework supports a wide range of logics: from simple implication-only logic ("if-then") towards more expressive first-order reasoning with conjunction ("and"), disjunction ("or"), negation ("not"), and universal quantification ("for all"). Using this framework, we show that the RL training compute T follows a power law with respect to reasoning depth D (T propto D^γ, R^{2} > 0.99), and that the scaling exponent γ increases monotonically with logical expressiveness, from 1.04 to 2.60. On downstream mathematics and general reasoning benchmarks, more expressive training settings yield both larger performance gains (up to +10.66 points) and more compute-efficient transfer compared to less expressive settings, demonstrating that what a model is trained on, not just how much it is trained, shapes downstream transfer. We further show that the power-law relationship holds across multiple RL methods, and curriculum-based training substantially improves scaling efficiency.</p> - https://arxiv.org/abs/2605.06638 + Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex + https://arxiv.org/abs/2605.06139 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06139.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yun Qu, Qi Wang, Yixiu Mao, Heming Zou, Yuhang Jiang, Yingyue Li, Wutong Xu, Lizhou Cai, Weijie Liu, Clive Bai, Kai Yang, Yangkun Chen, Saiyong Yang, Xiangyang Ji</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity. Among existing recipes, group-based policy gradient is prevalent, which samples a group of responses per prompt and updates the policy via group-relative advantage signals. This work reveals that these optimization strategies share a common geometric structure: each implicitly defines a target distribution on the response simplex and projects toward it via first-order approximation. Building on this insight, we propose Listwise Policy Optimization (LPO) to explicitly conduct the target-projection, which demystifies the implicit target by restricting the proximal RL objective to the response simplex, and then projects the policy via exact divergence minimization. This framework provides (i) monotonic improvement on the listwise objective with bounded, zero-sum, and self-correcting projection gradients, and (ii) flexibility in divergence selection with distinct structural properties through the decoupled projection step. On diverse reasoning tasks and LLM backbones, LPO consistently improves training performance over typical policy gradient baselines under matched targets, while intrinsically preserving optimization stability and response diversity.</p> + https://arxiv.org/abs/2605.06139 Thu, 07 May 2026 00:00:00 +0000 - A^2TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping - https://arxiv.org/abs/2605.06200 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06200.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dingwei Chen, Zefang Zong, Zhipeng Ma, Leo Luo, Yang Li, Chengming Li, Peng Chen, Jie Jiang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Reinforcement learning for agentic large language models (LLMs) typically relies on a sparse, trajectory-level outcome reward, making it difficult to evaluate the contribution of individual tool-calls within multi-turn interactions. Existing approaches to such process credit assignment either depend on separate external process reward models that introduce additional consumption, or tree-based structural rollout that merely redistributes the outcome signal while constraining trajectory diversity. A promising alternative leverages the per-turn change in the policy's predicted probability of the ground-truth, termed Information Gain (IG), as an intrinsic process signal without an external evaluator. However, prior work on leveraging IG signals within the RL training loop faces three systematic challenges: normalizing across turns that face heterogeneous positional contexts can distort the relative standing of individual turns, accumulating a variable number of terms causes advantage magnitudes to drift with trajectory depth, and a fixed clipping range governs policy updates identically for turns with vastly different IG signals. In this paper, we propose A^2TGPO (Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping), which retains IG as the intrinsic signal but re-designs how it is normalized, accumulated, and consumed: (i) turn-group normalization: normalizes IG within each (prompt, turn-index) group so that each turn is compared only against peers at the same interaction depth; (ii) variance-rescaled discounted accumulation: divides cumulative normalized IG by square root of accumulated terms to keep advantage magnitudes comparable across turn positions; and (iii) adaptive turn-level clipping: modulates each turn's clipping range based on its normalized IG, widening the update region for informative turns and narrowing it for uninformative ones.</p> - https://arxiv.org/abs/2605.06200 + MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation + https://arxiv.org/abs/2512.18181 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.18181.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaixing Yang, Jiashu Zhu, Xulong Tang, Ziqiao Peng, Xiangyue Zhang, Puwei Wang, Jiahong Wu, Xiangxiang Chu, Hongyan Liu, Jun He</p><p><b>Upvotes:</b> 85</p><p><b>Summary:</b> With the rise of online dance-video platforms and rapid advances in AI-generated content (AIGC), music-driven dance generation has emerged as a compelling research direction. Despite substantial progress in related domains such as music-driven 3D dance generation, pose-driven image animation, and audio-driven talking-head synthesis, existing methods cannot be directly adapted to this task. Moreover, the limited studies in this area still struggle to jointly achieve high-quality visual appearance and realistic human motion. Accordingly, we present MACE-Dance, a music-driven dance video generation framework with cascaded Mixture-of-Experts (MoE). The Motion Expert performs music-to-3D motion generation while enforcing kinematic plausibility and artistic expressiveness, whereas the Appearance Expert carries out motion- and reference-conditioned video synthesis, preserving visual identity with spatiotemporal coherence. Specifically, the Motion Expert adopts a diffusion model with a BiMamba-Transformer hybrid architecture and a Guidance-Free Training (GFT) strategy, achieving state-of-the-art (SOTA) performance in 3D dance generation. The Appearance Expert employs a decoupled kinematic-aesthetic fine-tuning strategy, achieving state-of-the-art (SOTA) performance in pose-driven image animation. To better benchmark this task, we curate a large-scale and diverse dataset and design a motion-appearance evaluation protocol. Based on this protocol, MACE-Dance also achieves state-of-the-art performance. Code is available at https://github.com/AMAP-ML/MACE-Dance.</p> + https://arxiv.org/abs/2512.18181 Thu, 07 May 2026 00:00:00 +0000 - Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes - https://arxiv.org/abs/2605.05724 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05724.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingjie Ning, Xiaochuan Li, Ji Zeng, Hao Kang, Chenyan Xiong</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> We study auto research as a closed empirical loop driven by external measurement. Each submitted trial carries a hypothesis, an executable code edit, an evaluator-owned outcome, and feedback that shapes the next proposal. The output is not a generated paper or a single model checkpoint, but an auditable trajectory of proposals, code diffs, experiments, scores, and failure labels. We instantiate this loop with specialist agents that partition recipe surfaces and share measured lineage across trials. The central empirical finding is that lineage feedback lets agents turn evaluator outcomes, including crashes, budget overruns, size failures, and accuracy-gate misses, into later program-level recipe edits rather than one-shot suggestions. Across 1,197 headline-run trials plus 600 Parameter Golf control trials after one-time setup and launch, humans did not choose proposals, edit recipes, override scores, or repair failed trials during the search. In the three headline runs, the same submitted-trial loop reduces Parameter Golf validation bpb by 0.81%, raises NanoChat-D12 CORE by 38.7%, and reduces CIFAR-10 Airbench96 wallclock by 4.59%, with each task measured by its own external evaluator and legality checks. The trace includes a strict architecture-domain audit of 157 headline-run submissions and program rewrites such as a NanoChat attention-kernel path change. Within this scope the loop autonomously writes code, submits experiments, absorbs feedback, applies and combines known techniques inside each environment, and improves public starting recipes.</p> - https://arxiv.org/abs/2605.05724 + Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers + https://arxiv.org/abs/2605.06169 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06169.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pengqi Lu</p><p><b>Upvotes:</b> 183</p><p><b>Summary:</b> Scaling Diffusion Transformers (DiTs) to hundreds of layers introduces a structural vulnerability: networks can enter a silent, mean-dominated collapse state that homogenizes token representations and suppresses centered variation. Through mechanistic auditing, we isolate the trigger event of this collapse as Mean Mode Screaming (MMS). MMS can occur even when training appears stable, with a mean-coherent backward shock on residual writers that opens deep residual branches and drives the network into a mean-dominated state. We show this behavior is driven by an exact decomposition of these gradients into mean-coherent and centered components, compounded by the structural suppression of attention-logit gradients through the null space of the Softmax Jacobian once values homogenize. To address this, we propose Mean-Variance Split (MV-Split) Residuals, which combine a separately gained centered residual update with a leaky trunk-mean replacement. On a 400-layer single-stream DiT, MV-Split prevents the divergent collapse that crashes the un-stabilized baseline; it tracks close to the baseline's pre-crash trajectory while remaining substantially better than token-isotropic gating methods such as LayerScale across the full schedule. Finally, we present a 1000-layer DiT as a scale-validation run at boundary scales, establishing that the architecture remains stably trainable at extreme depth.</p> + https://arxiv.org/abs/2605.06169 Thu, 07 May 2026 00:00:00 +0000 - StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction - https://arxiv.org/abs/2605.06642 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06642.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyuan Xue, Yifan Zhou, Zidong Wang, Shengji Tang, Philip Torr, Wanli Ouyang, Lei Bai, Zhenfei Yin</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely purely reactive, which weakens both exploration and credit assignment over extended trajectories. In this work, we present Strategic Trajectory Abstraction (StraTA), a simple framework that introduces an explicit trajectory-level strategy into agentic reinforcement learning (RL). StraTA samples a compact strategy from the initial task state, conditions subsequent actions on that strategy, and trains strategy generation and action execution jointly with a hierarchical GRPO-style rollout design, further enhanced by diverse strategy rollout and critical self-judgment. Experiments on ALFWorld, WebShop, and SciWorld show that StraTA consistently improves both sample efficiency and final performance over strong baselines. StraTA reaches success rates of 93.1% on ALFWorld and 84.2% on WebShop. On SciWorld, StraTA attains a 63.5% overall score, outperforming frontier closed-source models.</p> - https://arxiv.org/abs/2605.06642 - Thu, 07 May 2026 00:00:00 +0000 + Normalizing Trajectory Models + https://arxiv.org/abs/2605.08078 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.08078.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiatao Gu, Tianrong Chen, Ying Shen, David Berthelot, Shuangfei Zhai, Josh Susskind</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Diffusion-based models decompose sampling into many small Gaussian denoising steps -- an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step methods address this through distillation, consistency training, or adversarial objectives, but sacrifice the likelihood framework in the process. We introduce Normalizing Trajectory Models (NTM), which models each reverse step as an expressive conditional normalizing flow with exact likelihood training. Architecturally, NTM combines shallow invertible blocks within each step with a deep parallel predictor across the trajectory, forming an end-to-end network trainable from scratch or initializable from pretrained flow-matching models. Its exact trajectory likelihood further enables self-distillation: a lightweight denoiser trained on the model's own score produces high-quality samples in four steps. On text-to-image benchmarks, NTM matches or outperforms strong image generation baselines in just four sampling steps while uniquely retaining exact likelihood over the generative trajectory.</p> + https://arxiv.org/abs/2605.08078 + Fri, 08 May 2026 00:00:00 +0000 - Continuous-Time Distribution Matching for Few-Step Diffusion Distillation - https://arxiv.org/abs/2605.06376 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06376.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tao Liu, Hao Yan, Mengting Chen, Taihang Hu, Zhengrong Yue, Zihao Pan, Jinsong Lan, Xiaoyong Zhu, Ming-Ming Cheng, Bo Zheng, Yaxing Wang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Step distillation has become a leading technique for accelerating diffusion models, among which Distribution Matching Distillation (DMD) and Consistency Distillation are two representative paradigms. While consistency methods enforce self-consistency along the full PF-ODE trajectory to steer it toward the clean data manifold, vanilla DMD relies on sparse supervision at a few predefined discrete timesteps. This restricted discrete-time formulation and mode-seeking nature of the reverse KL divergence tends to exhibit visual artifacts and over-smoothed outputs, often necessitating complex auxiliary modules -- such as GANs or reward models -- to restore visual fidelity. In this work, we introduce Continuous-Time Distribution Matching (CDM), migrating the DMD framework from discrete anchoring to continuous optimization for the first time. CDM achieves this through two continuous-time designs. First, we replace the fixed discrete schedule with a dynamic continuous schedule of random length, so that distribution matching is enforced at arbitrary points along sampling trajectories rather than only at a few fixed anchors. Second, we propose a continuous-time alignment objective that performs active off-trajectory matching on latents extrapolated via the student's velocity field, improving generalization and preserving fine visual details. Extensive experiments on different architectures, including SD3-Medium and Longcat-Image, demonstrate that CDM provides highly competitive visual fidelity for few-step image generation without relying on complex auxiliary objectives. Code is available at https://github.com/byliutao/cdm.</p> - https://arxiv.org/abs/2605.06376 - Thu, 07 May 2026 00:00:00 +0000 + MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning + https://arxiv.org/abs/2605.07850 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07850.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ionut-Vlad Modoranu, Mher Safaryan, Dan Alistarh</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> With the rise in scale for deep learning models to billions of parameters, the computational cost of fine-tuning remains a significant barrier to deployment. While Low-Rank Adaptation (LoRA) has become the standard for parameter-efficient fine-tuning, the need to set a predefined, static rank r requires exhaustive grid searches to balance efficiency and performance. Existing rank-adaptive solutions such as DyLoRA mitigate this by sampling ranks during the training from a predefined distribution. However, they often yield sub-optimal results at higher ranks due to lack of consistent gradient signals across the full hierarchy of ranks, thus making these methods data-inefficient. In this paper, we propose MatryoshkaLoRA, a general, Matryoshka-inspired training framework for LoRA that learns accurate hierarchical low-rank representations by inserting a fixed, carefully crafted diagonal matrix P between the existing LoRA adapters to scale their sub-ranks accordingly. By introducing this simple modification, our general framework recovers LoRA and DyLoRA only by changing P and ensures all sub-ranks embed the available gradient information efficiently. Our MatryoshkaLoRA supports dynamic rank selection with minimal degradation in accuracy. We further propose Area Under the Rank Accuracy Curve (AURAC), a metric that consistently evaluates the performance of hierarchical low-rank adapters. Our results demonstrate that MatryoshkaLoRA learns more accurate hierarchical low-rank representations than prior rank-adaptive approaches and achieves superior accuracy-performance trade-offs across ranks on the evaluated datasets. Our code is available at https://github.com/IST-DASLab/MatryoshkaLoRA.</p> + https://arxiv.org/abs/2605.07850 + Fri, 08 May 2026 00:00:00 +0000 - Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration - https://arxiv.org/abs/2605.05566 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05566.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Langlin Huang, Chengsong Huang, Jinyuan Li, Donghong Cai, Yuyi Yang, Jiaxin Huang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, in complex tasks, GRPO frequently suffers from the ``zero-advantage problem'': when all sampled rollouts for a query fail, the relative advantage collapses to zero. Consequently, the model loses effective training signals for these questions, wasting the training data and computational budget. While simply increasing the sampling budget for these questions is a common remedy, the static sampling policy inherently constrains reasoning exploration, limiting the success rate. In this paper, we propose Lorem Perturbation for Exploration (LoPE), a simple yet effective training framework to break this exploration bottleneck. We posit that task-irrelevant prompt-space perturbations can shift the model's output distribution enough to unlock orthogonal reasoning pathways for hard questions. Specifically, LoPE prepends sequences stochastically assembled from Lorem Ipsum vocabulary (a pseudo-Latin placeholder text) to the prompts before resampling. Experiments across 1.7B, 4B, and 7B models demonstrate that LoPE significantly outperforms resampling with the original prompts. Further analysis reveals that other Latin-based random sequences with low perplexity are also effective perturbations. Our results establish LoPE as a strong baseline for broadening exploration in LLM reinforcement learning.</p> - https://arxiv.org/abs/2605.05566 - Thu, 07 May 2026 00:00:00 +0000 + AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning + https://arxiv.org/abs/2605.00425 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00425.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haotian Zhao, Songlin Zhou, Yuxin Zhang, Stephen S. -T. Yau, Wenyu Zhang, Lun Tian, Tianshu Zhu, Yifeng Huang, Yucheng Zeng, Jingnan Gu, Daxiang Dong, Jianmin Wu</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards provide limited guidance for assigning credit to individual steps within long interaction trajectories. Existing approaches often introduce dense intermediate supervision, such as process reward models or auxiliary self-supervised signals, which increases supervision and tuning complexity and may limit generalization across tasks and domains. We present AEM, a supervision-free credit assignment method that adaptively modulates entropy dynamics during RL training to improve the exploration-exploitation trade-off. Since in agentic RL the environment is typically affected by a complete response, rather than an individual token, our analysis lifts entropy dynamics from the token level to the response level, aligning uncertainty estimation with the effective action granularity of LLM agents and reducing sensitivity to token-level sampling noise. We further show that entropy drift under natural-gradient updates is governed by the interaction between the sampled-response advantage and its relative surprisal. Motivated by this result, AEM derives a practical response-level uncertainty proxy and uses it to rescale advantages, leveraging the evolving balance between positive and negative samples to naturally transition from exploration to exploitation. Extensive experiments on ALFWorld, WebShop, and SWE-bench-Verified with models ranging from 1.5B to 32B demonstrate that AEM consistently improves strong RL baselines, including a +1.4\% gain when integrated into a state-of-the-art software-engineering RL training framework.</p> + https://arxiv.org/abs/2605.00425 + Fri, 08 May 2026 00:00:00 +0000 - SkillOS: Learning Skill Curation for Self-Evolving Agents - https://arxiv.org/abs/2605.06614 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06614.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siru Ouyang, Jun Yan, Yanfei Chen, Rujun Han, Zifeng Wang, Bhavana Dalvi Mishra, Rui Meng, Chun-Liang Li, Yizhu Jiao, Kaiwen Zha, Maohao Shen, Vishy Tirumalashetty, George Lee, Jiawei Han, Tomas Pfister, Chen-Yu Lee</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for self-evolution, where high-quality skill curation serves as the key bottleneck. Existing approaches either rely on manual skill curation, prescribe heuristic skill operations, or train for short-horizon skill operations. However, they still struggle to learn complex long-term curation policies from indirect and delayed feedback. To tackle this challenge, we propose SkillOS, an experience-driven RL training recipe for learning skill curation in self-evolving agents. SkillOS pairs a frozen agent executor that retrieves and applies skills with a trainable skill curator that updates an external SkillRepo from accumulated experience. To provide learning signals for curation, we design composite rewards and train on grouped task streams based on skill-relevant task dependencies, where earlier trajectories update the SkillRepo, and later related tasks evaluate these updates. Across multi-turn agentic tasks and single-turn reasoning tasks, SkillOS consistently outperforms memory-free and strong memory-based baselines in both effectiveness and efficiency, with the learned skill curator generalizing across different executor backbones and task domains. Further analyses show that the learned curator produces more targeted skill use, while the skills in SkillRepo evolve into more richly structured Markdown files that encode higher-level meta-skills over time.</p> - https://arxiv.org/abs/2605.06614 - Thu, 07 May 2026 00:00:00 +0000 + Rethinking State Tracking in Recurrent Models Through Error Control Dynamics + https://arxiv.org/abs/2605.07755 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07755.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiwan Chung, Heechan Choi, Seon Joo Kim</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> The theory of state tracking in recurrent architectures has predominantly focused on expressive capacity: whether a fixed architecture can theoretically realize a set of symbolic transition rules. We argue that equally important is error control, the dynamics governing hidden-state drift along the directions that distinguish symbolic states. We prove that affine recurrent networks, a class of models encompassing State-Space Models and Linear Attention, cannot correct errors along state-separating subspaces once they preserve state representations. Consequently, practical affine trackers do not learn robust state tracking; rather, they learn finite horizon solutions governed by accumulated state-relevant error. We characterize the mechanics of this failure, showing that tracking remains readable only while the accumulating within-class spread remains small relative to the initial between-class separation. We demonstrate empirically on group state-tracking tasks that this breakdown is predictable: tracking collapses when the distinguishability ratio crosses the readability threshold of the trained decoder. Across trained models, the point of this crossing predicts the horizon at which downstream accuracy fails. These results establish that robust state tracking is determined not only by an architecture's theoretical expressivity but crucially by its error control.</p> + https://arxiv.org/abs/2605.07755 + Fri, 08 May 2026 00:00:00 +0000 - MARBLE: Multi-Aspect Reward Balance for Diffusion RL - https://arxiv.org/abs/2605.06507 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06507.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Canyu Zhao, Hao Chen, Yunze Tong, Yu Qiao, Jiacheng Li, Chunhua Shen</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be optimized simultaneously. Existing practice deal with multiple rewards by training one specialist model per reward, optimizing a weighted-sum reward R(x)=sum_k w_k R_k(x), or sequentially fine-tuning with a hand-crafted stage schedule. These approaches either fail to produce a unified model that can be jointly trained on all rewards or necessitates heavy manually tuned sequential training. We find that the failure stems from using a naive weighted-sum reward aggregation. This approach suffers from a sample-level mismatch because most rollouts are specialist samples, highly informative for certain reward dimensions but irrelevant for others; consequently, weighted summation dilutes their supervision. To address this issue, we propose MARBLE (Multi-Aspect Reward BaLancE), a gradient-space optimization framework that maintains independent advantage estimators for each reward, computes per-reward policy gradients, and harmonizes them into a single update direction without manually-tuned reward weighting, by solving a Quadratic Programming problem. We further propose an amortized formulation that exploits the affine structure of the loss used in DiffusionNFT, to reduce the per-step cost from K+1 backward passes to near single-reward baseline cost, together with EMA smoothing on the balancing coefficients to stabilize updates against transient single-batch fluctuations. On SD3.5 Medium with five rewards, MARBLE improves all five reward dimensions simultaneously, turns the worst-aligned reward's gradient cosine from negative under weighted summation in 80% of mini-batches to consistently positive, and runs at 0.97X the training speed of baseline training.</p> - https://arxiv.org/abs/2605.06507 - Thu, 07 May 2026 00:00:00 +0000 + Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria + https://arxiv.org/abs/2605.08354 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.08354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juanxi Tian, Fengyuan Liu, Jiaming Han, Yilei Jiang, Yongliang Wu, Yesheng Liu, Haodong Li, Furong Xu, Wanhua Li</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise labels, collapsing nuanced preferences into opaque parametric proxies and exposing vulnerabilities to reward hacking. While recent Rubrics-as-Reward (RaR) methods attempt to recover this structure through explicit criteria, generating rubrics that are simultaneously reliable, scalable, and data-efficient remains an open problem. We introduce Auto-Rubric as Reward (ARR), a framework that reframes reward modeling from implicit weight optimization to explicit, criteria-based decomposition. Before any pairwise comparison, ARR externalizes a VLM's internalized preference knowledge as prompt-specific rubrics, translating holistic intent into independently verifiable quality dimensions. This conversion of implicit preference structure into inspectable, interpretable constraints substantially suppresses evaluation biases including positional bias, enabling both zero-shot deployment and few-shot conditioning on minimal supervision. To extend these gains into generative training, we propose Rubric Policy Optimization (RPO), which distills ARR's structured multi-dimensional evaluation into a robust binary reward, replacing opaque scalar regression with rubric-conditioned preference decisions that stabilize policy gradients. On text-to-image generation and image editing benchmarks, ARR-RPO outperforms pairwise reward models and VLM judges, demonstrating that explicitly externalizing implicit preference knowledge into structured rubrics achieves more reliable, data-efficient multimodal alignment, revealing that the bottleneck is the absence of a factorized interface, not a deficit of knowledge.</p> + https://arxiv.org/abs/2605.08354 + Fri, 08 May 2026 00:00:00 +0000 - When to Trust Imagination: Adaptive Action Execution for World Action Models - https://arxiv.org/abs/2605.06222 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06222.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Wang, Yue Zhang, Jiehong Lin, Kuncheng Luo, Jianan Wang, Zhongrui Wang, Xiaojuan Qi</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> World Action Models (WAMs) have recently emerged as a promising paradigm for robotic manipulation by jointly predicting future visual observations and future actions. However, current WAMs typically execute a fixed number of predicted actions after each model inference, leaving the robot blind to whether the imagined future remains consistent with the actual physical rollout. In this work, we formulate adaptive WAM execution as a future-reality verification problem: the robot should execute longer when the WAM-predicted future remains reliable, and replan earlier when reality deviates from imagination. To this end, we propose Future Forward Dynamics Causal Attention (FFDC), a lightweight verifier that jointly reasons over predicted future actions, predicted visual dynamics, real observations, and language instructions to estimate whether the remaining action rollout can still be trusted. FFDC enables adaptive action chunk sizes as an emergent consequence of prediction-observation consistency, preserving the efficiency of long-horizon execution while restoring responsiveness in contact-rich or difficult phases. We further introduce Mixture-of-Horizon Training to improve long-horizon trajectory coverage for adaptive execution. Experiments on the RoboTwin benchmark and in the real world demonstrate that our method achieves a strong robustness-efficiency trade-off: on RoboTwin, it reduces WAM forward passes by 69.10% and execution time by 34.02%, while improving success rate by 2.54% over the short-chunk baseline; in real-world experiments, it improves success rate by 35%.</p> - https://arxiv.org/abs/2605.06222 - Thu, 07 May 2026 00:00:00 +0000 + TextLDM: Language Modeling with Continuous Latent Diffusion + https://arxiv.org/abs/2605.07748 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07748.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxiu Jiang, Jingjing Ren, Wenbo Li, Bo Wang, Haoze Sun, Yijun Yang, Jianhui Liu, Yanbing Zhang, Shenghe Zheng, Yuan Zhang, Haoyang Huang, Nan Duan, Wangmeng Zuo</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Diffusion Transformers (DiT) trained with flow matching in a VAE latent space have unified visual generation across images and videos. A natural next step toward a single architecture for both generation (visual synthesis) and understanding (text generation) is to apply this framework to language modeling. We propose TextLDM, which transfers the visual latent diffusion recipe to text generation with minimal architectural modification. A Transformer-based VAE maps discrete tokens to continuous latents, enhanced by Representation Alignment (REPA) with a frozen pretrained language model to produce representations effective for conditional denoising. A standard DiT then performs flow matching in this latent space, identical in architecture to its visual counterpart. The central challenge we address is obtaining high-quality continuous text representations: we find that reconstruction fidelity alone is insufficient, and that aligning latent features with a pretrained language model via REPA is critical for downstream generation quality. Trained from scratch on OpenWebText2, TextLDM substantially outperforms prior diffusion language models and matches GPT-2 under the same settings. Our results establish that the visual DiT recipe transfers effectively to language, taking a concrete step toward unified diffusion architectures for multimodal generation and understanding.</p> + https://arxiv.org/abs/2605.07748 + Fri, 08 May 2026 00:00:00 +0000 - MiA-Signature: Approximating Global Activation for Long-Context Understanding - https://arxiv.org/abs/2605.06416 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06416.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqing Li, Jiangnan Li, Mo Yu, Zheng Lin, Weiping Wang, Jie Zhou</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> A growing body of work in cognitive science suggests that reportable conscious access is associated with global ignition over distributed memory systems, while such activation is only partially accessible as individuals cannot directly access or enumerate all activated contents. This tension suggests a plausible mechanism that cognition may rely on a compact representation that approximates the global influence of activation on downstream processing. Inspired by this idea, we introduce the concept of Mindscape Activation Signature (MiA-Signature), a compressed representation of the global activation pattern induced by a query. In LLM systems, this is instantiated via submodular-based selection of high-level concepts that cover the activated context space, optionally refined through lightweight iterative updates using working memory. The resulting MiA-Signature serves as a conditioning signal that approximates the effect of the full activation state while remaining computationally tractable. Integrating MiA-Signatures into both RAG and agentic systems yields consistent performance gains across multiple long-context understanding tasks.</p> - https://arxiv.org/abs/2605.06416 - Thu, 07 May 2026 00:00:00 +0000 + Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models + https://arxiv.org/abs/2605.07721 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07721.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Victor Conchello Vendrell, Arnau Padres Masdemont, Niccolò Grillo, Jordi Ros-Giralt, Arash Behboodi, Fabio Valerio Massoli</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without generating intermediate tokens. Models such as Ouro perform reasoning by iteratively updating internal representations while retaining a standard Key-Value (KV) cache across iterations, causing memory consumption to grow linearly with reasoning depth. Consequently, increasing the number of reasoning iterations can lead to prohibitive memory usage, limiting the practical scalability of such architectures. In this work, we propose Memory-Efficient Looped Transformer (MELT), a novel architecture that decouples reasoning depth from memory consumption. Instead of using a standard KV cache per layer and loop, MELT maintains a single KV cache per layer that is shared across reasoning loops. This cache is updated over time via a learnable gating mechanism. To enable stable and efficient training under this architecture, we propose to train MELT using chunk-wise training in a two phase procedure: interpolated transition, followed by attention-aligned distillation, both from the LoopLM starting model to MELT. Empirically, we show that MELT models fine-tuned from pretrained Ouro parameters outperform standard LLMs of comparable size, while maintaining a memory footprint comparable to those models and dramatically smaller than Ouro's. Overall, MELT achieves constant-memory iterative reasoning without sacrificing LoopLM performance, using only a lightweight post-training procedure.</p> + https://arxiv.org/abs/2605.07721 + Fri, 08 May 2026 00:00:00 +0000 - Continuous Latent Diffusion Language Model - https://arxiv.org/abs/2605.06548 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06548.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongcan Guo, Qinyu Zhao, Yian Zhao, Shen Nie, Rui Zhu, Qiushan Guo, Feng Wang, Tao Yang, Hengshuang Zhao, Guoqiang Wei, Yan Zeng</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing alternatives still struggle to jointly achieve generation efficiency, scalable representation learning, and effective global semantic modeling. We propose Cola DLM, a hierarchical latent diffusion language model that frames text generation through hierarchical information decomposition. Cola DLM first learns a stable text-to-latent mapping with a Text VAE, then models a global semantic prior in continuous latent space with a block-causal DiT, and finally generates text through conditional decoding. From a unified Markov-path perspective, its diffusion process performs latent prior transport rather than token-level observation recovery, thereby separating global semantic organization from local textual realization. This design yields a more flexible non-autoregressive inductive bias, supports semantic compression and prior fitting in continuous space, and naturally extends to other continuous modalities. Through experiments spanning 4 research questions, 8 benchmarks, strictly matched ~2B-parameter autoregressive and LLaDA baselines, and scaling curves up to about 2000 EFLOPs, we identify an effective overall configuration of Cola DLM and verify its strong scaling behavior for text generation. Taken together, the results establish hierarchical continuous latent prior modeling as a principled alternative to strictly token-level language modeling, where generation quality and scaling behavior may better reflect model capability than likelihood, while also suggesting a concrete path toward unified modeling across discrete text and continuous modalities.</p> - https://arxiv.org/abs/2605.06548 - Thu, 07 May 2026 00:00:00 +0000 + Anisotropic Modality Align + https://arxiv.org/abs/2605.07825 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07825.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaomin Yu, Yijiang Li, Yuhui Zhang, Hanzhen Zhao, Yue Yang, Hao Tang, Yue Song, Xiaobin Hu, Chengwei Qin, Shuicheng Yan, Hui Xiong</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Training multimodal large language models has long been limited by the scarcity of high-quality paired multimodal data. Recent studies show that the shared representation space of pretrained multimodal contrastive models can serve as a bridge, enabling models to perform multimodal training with unimodal data. However, the key premise of this paradigm remains insufficiently understood: can representations from different modalities be reliably interchanged? The core obstacle lies in the persistent Modality Gap in the shared space. In this work, we revisit the geometric nature of the modality gap. We find that modality representations already share compatible dominant semantic geometry. What truly hinders modality interchangeability is not a simple global shift, but an anisotropic residual structure concentrated along a small number of dominant directions. Based on this finding, we further propose the principle of anisotropic modality gap alignment: effective modality alignment should align with the target-modality distribution while preserving the semantic structure of the source modality. Guided by this principle, we propose an anisotropic geometric correction framework, AnisoAlign, for unpaired modality alignment. This framework leverages the internal geometric prior of the target modality and performs bounded correction on source-modality representations, thereby constructing substitute representations in the target modality. Experiments confirm its benefits in both geometric diagnostics and text-only MLLM training. Overall, this work recasts the modality gap from an empirical observation into a correctable, structured geometric phenomenon and provides a new representation alignment perspective for training multimodal models with unimodal data.</p> + https://arxiv.org/abs/2605.07825 + Fri, 08 May 2026 00:00:00 +0000 - Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning - https://arxiv.org/abs/2605.06130 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06130.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaorui Shi, Yuxin Chen, Zhengxi Lu, Yuchun Miao, Shugui Liu, Qi GU, Xunliang Cai, Xiang Wang, An Zhang</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and distills new skills from experience. Existing methods optimize these capabilities in isolation or with separate reward sources, resulting in partial and conflicting evolution. We propose Skill1, a framework that trains a single policy to co-evolve skill selection, utilization, and distillation toward a shared task-outcome objective. The policy generates a query to search the skill library, re-ranks candidates to select one, solves the task conditioned on it, and distills a new skill from the trajectory. All learning derives from a single task-outcome signal. Its low-frequency trend credits selection and its high-frequency variation credits distillation. Experiments on ALFWorld and WebShop show that Skill1 outperforms prior skill-based and reinforcement learning baselines. Training dynamics confirm the co-evolution of the three capabilities, and ablations show that removing any credit signal degrades the evolution.</p> - https://arxiv.org/abs/2605.06130 - Thu, 07 May 2026 00:00:00 +0000 + SEIF: Self-Evolving Reinforcement Learning for Instruction Following + https://arxiv.org/abs/2605.07465 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07465.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyu Ren, Qianyu He, Jiajie Zhu, Xingzhou Chen, Jingwen Chang, Zeye Sun, Han Xia, Fei Yu, Jiaqing Liang, Yanghua Xiao</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Instruction following is a fundamental capability of large language models (LLMs), yet continuously improving this capability remains challenging. Existing methods typically rely either on costly external supervision from humans or strong teacher models, or on self-play training with static-difficulty instructions that cannot evolve as the model's capabilities improve. To address these limitations, we propose SEIF (Self-Evolving Reinforcement Learning for Instruction Following), a self-evolving framework for enhancing the instruction-following ability of LLMs. SEIF forms a closed self-evolution loop that improves the model's instruction-following ability, where instruction difficulty evolution and model capability evolution reinforce each other. SEIF consists of four roles: an Instructor that generates increasingly challenging instructions, a Filter that removes conflicting or invalid instructions to ensure data quality, a Follower that learns to follow evolved instructions, and a Judger that provides reward signals for reinforcement learning. The Instructor and Follower are alternately trained and co-evolve throughout the process. Experiments across multiple model scales and architectures show that SEIF consistently improves instruction-following performance, suggesting strong generality. Further analyses reveal the sources of improvement and identify an effective training strategy for self-evolution on open-ended tasks: sufficient early-stage training to build a solid foundation, followed by moderate late-stage training to mitigate overfitting and achieve better final performance. The code and data are publicly available at https://github.com/Rainier-rq1/SEIF.</p> + https://arxiv.org/abs/2605.07465 + Fri, 08 May 2026 00:00:00 +0000 + + + Rubric-based On-policy Distillation + https://arxiv.org/abs/2605.07396 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07396.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junfeng Fang, Zhepei Hong, Mao Zheng, Mingyang Song, Gengsheng Li, Houcheng Jiang, Dan Zhang, Haiyun Guo, Xiang Wang, Tat-Seng Chua</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that structured semantic rubrics can serve as a scalable alternative to teacher logits, enabling OPD using only teacher-generated responses. To prove it, we introduce ROPD, a simple yet foundational framework for rubric-based OPD. Specifically, ROPD induces prompt-specific rubrics from teacher-student contrasts, and then utilizes these rubrics to score the student rollouts for on-policy optimization. Empirically, ROPD outperforms the advanced logit-based OPD methods across most scenarios, and achieving up to a 10x gain in sample efficiency. These results position rubric-based OPD as a flexible, black-box-compatible alternative to the prevailing logit-based OPD, offering a simple yet strong baseline for scalable distillation across proprietary and open-source LLMs. Code is available at https://github.com/Peregrine123/ROPD_official.</p> + https://arxiv.org/abs/2605.07396 + Fri, 08 May 2026 00:00:00 +0000 + + + HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents + https://arxiv.org/abs/2605.07177 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07177.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guankai Li, Jiabin Chen, Yi Xu, Xichen Zhang, Yuan Lu</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds whenever a query decomposes into independent sub-retrievals. We argue that effective multimodal agents should search wider rather than longer: dispatching multiple grounded queries concurrently within a round. To this end, we present HyperEyes, a parallel multimodal search agent that fuses visual grounding and retrieval into a single atomic action, enabling concurrent search across multiple entities while treating inference efficiency as a first-class training objective. HyperEyes is trained in two stages. For cold-start supervision, we develop a Parallel-Amenable Data Synthesis Pipeline covering visual multi-entity and textual multi-constraint queries, curating efficiency-oriented trajectories via Progressive Rejection Sampling. Building on this, our central contribution, a Dual-Grained Efficiency-Aware Reinforcement Learning framework, operates at two levels. At the macro level, we propose TRACE (Tool-use Reference-Adaptive Cost Efficiency), a trajectory-level reward whose reference is monotonically tightened during training to suppress superfluous tool calls without restricting genuine multi-hop search. At the micro level, we adapt On-Policy Distillation to inject dense token-level corrective signals from an external teacher on failed rollouts, mitigating the credit-assignment deficiency of sparse outcome rewards. Since existing benchmarks evaluate accuracy as the sole metric, omitting inference cost, we introduce IMEB, a human-curated benchmark of 300 instances that jointly evaluates search capability and efficiency. Across six benchmarks, HyperEyes-30B surpasses the strongest comparable open-source agent by 9.9% in accuracy with 5.3x fewer tool-call rounds on average.</p> + https://arxiv.org/abs/2605.07177 + Fri, 08 May 2026 00:00:00 +0000 + + + LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling + https://arxiv.org/abs/2605.08083 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.08083.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tong Zheng, Haolin Liu, Chengsong Huang, Huiwen Bao, Sheng Zhang, Rui Liu, Runpeng Dai, Ruibo Chen, Chenxi Liu, Tianyi Xiong, Xidong Wu, Hongming Zhang, Heng Huang</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually design reasoning patterns and tune heuristics by intuition, leaving much of the computation-allocation space unexplored. We propose an environment-driven framework, AutoTTS, that changes what researchers design: from individual TTS heuristics to environments where TTS strategies can be discovered automatically. The key to AutoTTS lies in environment construction: the discovery environment must make the control space tractable and provide cheap, frequent feedback for TTS search. As a concrete instantiation, we formulate width--depth TTS as controller synthesis over pre-collected reasoning trajectories and probe signals, where controllers decide when to branch, continue, probe, prune, or stop and can be evaluated cheaply without repeated LLM calls. We further introduce beta parameterization to make the search tractable and fine-grained execution trace feedback to improve discovery efficiency by helping the agent diagnose why a TTS program fails. Experiments on mathematical reasoning benchmarks show that the discovered strategies improve the overall accuracy--cost tradeoff over strong manually designed baselines. The discovered strategies generalize to held-out benchmarks and model scales, while the entire discovery costs only $39.9 and 160 minutes. Our data, and code will be open-source at https://github.com/zhengkid/AutoTTS.</p> + https://arxiv.org/abs/2605.08083 + Fri, 08 May 2026 00:00:00 +0000 + + + Flow-OPD: On-Policy Distillation for Flow Matching Models + https://arxiv.org/abs/2605.08063 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.08063.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhen Fang, Wenxuan Huang, Yu Zeng, Yiming Zhao, Shuang Chen, Kaituo Feng, Yunlong Lin, Lin Chen, Zehui Chen, Shaosheng Cao, Feng Zhao</p><p><b>Upvotes:</b> 94</p><p><b>Summary:</b> Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly optimizing heterogeneous objectives, which together give rise to a 'seesaw effect' of competing metrics and pervasive reward hacking. Inspired by the success of On-Policy Distillation (OPD) in the large language model community, we propose Flow-OPD, the first unified post-training framework that integrates on-policy distillation into Flow Matching models. Flow-OPD adopts a two-stage alignment strategy: it first cultivates domain-specialized teacher models via single-reward GRPO fine-tuning, allowing each expert to reach its performance ceiling in isolation; it then establishes a robust initial policy through a Flow-based Cold-Start scheme and seamlessly consolidates heterogeneous expertise into a single student via a three-step orchestration of on-policy sampling, task-routing labeling, and dense trajectory-level supervision. We further introduce Manifold Anchor Regularization (MAR), which leverages a task-agnostic teacher to provide full-data supervision that anchors generation to a high-quality manifold, effectively mitigating the aesthetic degradation commonly observed in purely RL-driven alignment. Built upon Stable Diffusion 3.5 Medium, Flow-OPD raises the GenEval score from 63 to 92 and the OCR accuracy from 59 to 94, yielding an overall improvement of roughly 10 points over vanilla GRPO, while preserving image fidelity and human-preference alignment and exhibiting an emergent 'teacher-surpassing' effect. These results establish Flow-OPD as a scalable alignment paradigm for building generalist text-to-image models.</p> + https://arxiv.org/abs/2605.08063 + Fri, 08 May 2026 00:00:00 +0000 + + + SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training + https://arxiv.org/abs/2605.08738 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.08738.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengkun Tang, Zekun Wang, Bo Zheng, Liangyu Wang, Rui Men, Siqi Zhang, Xiulong Yuan, Zihan Qiu, Zhiqiang Shen, Dayiheng Liu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Structured pruning and knowledge distillation (KD) are typical techniques for compressing large language models, but it remains unclear how they should be applied at pretraining scale, especially to recent mixture-of-experts (MoE) models. In this work, we systematically study MoE compression in large-scale pretraining, focusing on three key questions: whether pruning provides a better initialization than training from scratch, how expert compression choices affect the final model after continued training, and which training strategy is most effective. We have the following findings: First, across depth, width, and expert compression, pruning a pretrained MoE consistently outperforms training the target architecture from scratch under the same training budget. Second, different one-shot expert compression methods converge to similar final performance after large-scale continual pretraining. Motivated by this, we introduce a simple partial-preservation expert merging strategy that improves downstream performance across most benchmarks. Third, combining KD with the language modeling loss outperforms KD alone, particularly on knowledge-intensive tasks. We further propose multi-token prediction (MTP) distillation, which yields consistent gains. Finally, given the same training tokens, progressive pruning schedules outperform one-shot compression, suggesting that gradual architecture transitions lead to better optimization trajectories. Putting it all together, we compress Qwen3-Next-80A3B to a 23A2B model that retains competitive performance. These results offer practical guidance for efficient MoE compression at scale.</p> + https://arxiv.org/abs/2605.08738 + Sat, 09 May 2026 00:00:00 +0000 + + + RigidFormer: Learning Rigid Dynamics using Transformers + https://arxiv.org/abs/2605.09196 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09196.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyang Dou, Minghao Guo, Haixu Wu, Doug Roble, Tuur Stuyck, Wojciech Matusik</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Learning-based simulation of multi-object rigid-body dynamics remains difficult because contact is discontinuous and errors compound over long horizons. Most existing methods remain tied to mesh connectivity and vertex-level message passing, which limits their applicability to mesh-free inputs such as point clouds and leads to high computational cost. Efficiently modeling high-fidelity rigid-body dynamics from mesh-free representations, therefore, remains challenging. We introduce RigidFormer, an object-centric Transformer-based model that learns mesh-free rigid-body dynamics with controllable integration step sizes. RigidFormer reasons at the object level and advances each object through compact anchors; Anchor-Vertex Pooling enriches these anchors with local vertex features, retaining contact-relevant geometry without dense vertex-level interaction. We propose Anchor-based RoPE to inject anchor geometry into attention while respecting the unordered nature of objects and anchors: object-token processing is permutation-equivariant, and the mean-pooled anchor descriptor is invariant to anchor reindexing while preserving shape extent. RigidFormer further enforces rigidity by projecting updates onto the rigid-body manifold using differentiable Kabsch alignment. On standard benchmarks, RigidFormer outperforms or matches mesh-based baselines using point inputs, runs faster, generalizes to unseen point resolutions and across datasets, and scales to 200+ objects; we also show a preliminary extension to command-conditioned articulated bodies by treating body parts as interacting object-level components.</p> + https://arxiv.org/abs/2605.09196 + Sat, 09 May 2026 00:00:00 +0000 + + + LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs? + https://arxiv.org/abs/2605.08985 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.08985.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kechen Fang, Yihua Qin, Chongyi Wang, Wenshuo Ma, Tianyu Yu, Yuan Yao</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. The prevailing practice typically adopts global encoding followed by post-ViT compression. Global encoding produces massive token sequences, while post-ViT compression incurs the full quadratic attention cost of the ViT before any token reduction takes place. In this work, we revisit this convention along two dimensions: the encoding strategy and visual token compression. First, controlled experiments show that slice-based encoding outperforms global encoding across benchmarks, suggesting that preserving local details through sliced views can be more beneficial than applying global attention for fine-grained perception. Second, we introduce intra-ViT early compression, which reduces tokens in shallow ViT layers and substantially lowers visual-encoding FLOPs while preserving downstream performance. By integrating intra-ViT compression into the slice-based encoding framework, we present LLaVA-UHD v4, an efficient and compute-controllable visual encoding scheme tailored for high-resolution inputs. Across a diverse set of benchmarks covering document understanding, OCR, and general VQA, LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% while matching or even surpassing baseline performance. These results suggest that visual-encoding efficiency can be substantially improved without sacrificing downstream performance, providing a practical design direction for efficient high-resolution MLLMs. All model weights and code will be publicly released to support further research.</p> + https://arxiv.org/abs/2605.08985 + Sat, 09 May 2026 00:00:00 +0000 + + + MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments + https://arxiv.org/abs/2605.09131 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09131.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Giridhar Ganapavarapu, Dhaval Patel</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> The Model Context Protocol (MCP) has unified the interface between Large Language Models (LLMs) and external tools, yet a fundamental gap remains in how agents conceptualize the environments within which they operate. Current paradigms are bifurcated: Task-level planning often ignores execution-time dynamics, while reactive execution lacks long-horizon foresight. We present MCP-Cosmos, a framework that infuses generative World Models (WM) into the MCP ecosystem to enable predictive task automation. By unifying three disparate technologies, namely MCP, World Model, and Agent, we demonstrate that a "Bring Your Own World Model" (BYOWM) strategy allows agents to simulate state transitions and refine plans in a latent space before execution. We conducted experiments using two strategies, namely ReAct and SPIRAL with 2 planning models and 3 representative world models over 20+ MCP-Bench tasks. We observed improvements in Agent's environment interaction KPI such as tool success rate and tool parameter accuracy. The framework also offers new metrics such as Execution Quality to generate new insights about the effectiveness of world models compared to baseline.</p> + https://arxiv.org/abs/2605.09131 + Sat, 09 May 2026 00:00:00 +0000 + + + CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models + https://arxiv.org/abs/2605.08735 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.08735.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Joowon Kim, Seungho Shin, Joonhyung Park, Eunho Yang</p><p><b>Upvotes:</b> 67</p><p><b>Summary:</b> Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on goal-directed tasks: long-horizon drift on multi-step tasks and mid-clip simulation errors that compound. Both stem from the absence of explicit reasoning built upon the VGM's short-horizon visual prior, a role naturally filled by Vision-Language Models (VLMs), but where to place the VLM is non-trivial: upfront plans commit before any frame is generated and post-hoc critiques over whole videos intervene too late. We propose VLM-VGM Collaborative Video Reasoning (CollabVR), a closed-loop framework that couples the VLM with the VGM at step-level granularity: the VLM plans the immediate next action, inspects the clip the VGM generates, and folds the verifier's diagnosis directly into the next action prompt to repair detected failures. On Gen-ViRe and VBVR-Bench, CollabVR improves both open-source and closed-source VGMs over single-inference, Pass@k, and prior test-time scaling baselines at matched compute, with the largest gains on the hardest tasks. It also yields further improvements on top of a reasoning-fine-tuned VGM, indicating that step-level VLM supervision is orthogonal to and stackable with reasoning-oriented fine-tuning. We provide video samples and additional qualitative results at our project page: https://joow0n-kim.github.io/collabvr-project-page.</p> + https://arxiv.org/abs/2605.08735 + Sat, 09 May 2026 00:00:00 +0000 + + + Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs + https://arxiv.org/abs/2605.09063 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09063.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guijin Son, Seungone Kim, Catherine Arnett, Hyunwoo Ko, Hyein Lee, Hyeonah Kang, Jiang Longxi, Jin Yun, JungYup Lee, Kyungmin Lee, Sam Yoosuk Kim, Sang Park, Seunghyeok Hong, SeungJae Lee, Seungyeop Yi, Shinae Shin, SunHye Bok, Sunyoung Shin, Yonghoon Ji, Youngtaek Kim, Hanearl Jung, Akari Asai, Graham Neubig, Sean Welleck, Youngjae Yu, Akshelin R, Alexander B. Ivanov, Boboev Muhammadjon, Chaeyoung Han, Christian Stump, Dmitrii Karp, Dohyun Kwon, DoYong Kwon, Duk-Soon Oh, Giovanni Resta, Greta Panova, Huiyun Noh, Hyungryul Baik, Hyungsun Bae, Inomov Mashrafdzhon, Jeewon Kim, Ji Eun Lee, Jiaqi Liu, Jieui Kang, Jimin Kim, Jon-Lark Kim, Junseo Yoon, Junwoo Jo, Kibeom Kim, Kiwoon Kwon, Mario Kummer, Max Mercer, Minjun Kim, Nahyun Lee, Ng Ze-An, Rafał Marcin Łochowski, Raphaël Lachièze-Rey, Ruichen Zhang, Sejin Park, Seonguk Seo, Shin Jaehoon, Sunatullo, Taewoong Eom, Yeachan Park, Yongseok Jang, Youchan Oh, Zhaoyang Wang, Zoltán Kovács</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> Following the recent achievement of gold-medal performance on the IMO by frontier LLMs, the community is searching for the next meaningful and challenging target for measuring LLM reasoning. Whereas olympiad-style problems measure step-by-step reasoning alone, research-level problems use such reasoning to advance the frontier of mathematical knowledge itself, emerging as a compelling alternative. Yet research-level math benchmarks remain scarce because such problems are difficult to source (e.g., Riemann Bench and FrontierMath-Tier 4 contain 25 and 50 problems, respectively). To support reliable evaluation of next-generation frontier models, we introduce Soohak, a 439-problem benchmark newly authored from scratch by 64 mathematicians. Soohak comprises two subsets. On the Challenge subset, frontier models including Gemini-3-Pro, GPT-5, and Claude-Opus-4.5 reach 30.4%, 26.4%, and 10.4% respectively, leaving substantial headroom, while leading open-weight models such as Qwen3-235B, GPT-OSS-120B, and Kimi-2.5 remain below 15%. Notably, beyond standard problem solving, Soohak introduces a refusal subset that probes a capability intrinsic to research mathematics: recognizing ill-posed problems and pausing rather than producing confident but unjustified answers. On this subset, no model exceeds 50%, identifying refusal as a new optimization target that current models do not directly address. To prevent contamination, the dataset will be publicly released in late 2026, with model evaluations available upon request in the interim.</p> + https://arxiv.org/abs/2605.09063 + Sat, 09 May 2026 00:00:00 +0000 + + + Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control + https://arxiv.org/abs/2604.26326 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.26326.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bolian Li, Yifan Wang, Yi Ding, Anamika Lochab, Ananth Grama, Ruqi Zhang</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Reinforcement learning (RL) has enabled complex reasoning abilities in large language models (LLMs). However, most RL algorithms suffer from performance saturation, preventing continued gains as RL training scales. This problem can be characterized by the collapse of entropy, a key diagnostic for exploration in RL. Existing attempts focus on preventing entropy collapse through regularization or clipping. However, their resulting entropy curves often exhibit instability in the long term, which hinders performance gains. In this paper, we introduce Entrocraft, a simple rejection-sampling approach that realizes user-customized entropy schedule by biasing the advantage distributions. Entrocraft requires no objective regularization and is advantage-estimator-agnostic. Theoretically, we relate per-step entropy change to the advantage distribution under minimal assumptions. This explains the behavior of existing RL and entropy-preserving methods. Entrocraft also enables a systematic study of entropy schedules, which reveals that linear annealing, which starts high and decays to a slightly lower target, performs best. Empirically, Entrocraft addresses performance saturation, significantly improving generalization, output diversity, and long-term training. It enables a 4B model to outperform an 8B baseline, sustains improvement for up to 4x longer before plateauing, and raises pass@K by 50% over the baseline.</p> + https://arxiv.org/abs/2604.26326 + Sun, 10 May 2026 00:00:00 +0000 + + + SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning + https://arxiv.org/abs/2605.09266 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09266.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kun Xiang, Terry Jingchen Zhang, Zirong Liu, Bokai Zhou, Yueling Tang, Junjie Yu, Jiacong Lu, Shangrui Huang, Heng Li, Likui Zhang, Kunkun Liu, Changzheng Zhang, Yangle Fang, Boqiang Guo, Hui-Ling Zhen, Dandan Tu, Yinya Huang, Xiaodan Liang</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> We introduce SeePhys Pro, a fine-grained modality transfer benchmark that studies whether models preserve the same reasoning capability when critical information is progressively transferred from text to image. Unlike standard vision-essential benchmarks that evaluate a single input form, SeePhys Pro features four semantically aligned variants for each problem with progressively increasing visual elements. Our evaluation shows that current frontier models are far from representation-invariant reasoners: performance degrades on average as information moves from language to diagrams, with visual variable grounding as the most critical bottleneck. Motivated by this inference-time fragility, we further develop large training corpora for multimodal RLVR and use blind training as a diagnostic control, finding that RL with all training images masked can still improve performance on unmasked validation sets. To analyze this effect, text-deletion, image-mask-rate, and format-saturation controls suggest that such gains can arise from residual textual and distributional cues rather than valid visual evidence. Our results highlight the need to evaluate multimodal reasoning not only by final-answer accuracy, but also by robustness under modality transfer and by diagnostics that test whether improvements rely on task-critical visual evidence.</p> + https://arxiv.org/abs/2605.09266 + Sun, 10 May 2026 00:00:00 +0000 + + + Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training + https://arxiv.org/abs/2605.09608 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09608.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanyi Wang, Yifan Yang, Su Lu, Yanggan Gu, Pengkai Wang, Wenjun Wang, Zhaoyi Yan, Congkai Xie, Jianmin Wu, Jialun Cao, Shing-Chi Cheung, Hongxia Yang</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Continual post-training aims to extend large language models (LLMs) with new knowledge, skills, and behaviors, yet it remains unclear when sequential updates enable capability transfer and when they cause catastrophic forgetting. Existing methods mitigate forgetting through sequential fine-tuning, replay, regularization, or model merging, but offer limited criteria for determining when incorporating new updates is beneficial or harmful. In this work, we study LLM continual post-training through three questions: What drives forgetting? When do sequentially acquired capabilities transfer or interfere? How can compatibility be used to control update integration? We address these questions through task geometry: we represent each post-training task by its parameter update and study the covariance geometry induced by the update. Our central finding is that: forgetting can be considered as a state-relative update-integration failure, it arises when the covariance geometries induced by tasks misalign with the geometry of the evolving model state. Sequential updates transfer when they remain compatible with the model state shaped by previous updates, and interfere when state-relative geometry conflict becomes high. Motivated by this finding, we propose Geometry-Conflict Wasserstein Merging (GCWM), a data-free update-integration method that constructs a shared Wasserstein metric via Gaussian Wasserstein barycenters and uses geometry conflict to gate geometry-aware correction. Across Qwen3 0.6B--14B on domain-continual and capability-continual settings, GCWM consistently outperforms data-free baselines, improving retention and final performance without replay data. These results identify geometry conflict as both an explanatory signal for forgetting and a practical control signal for LLM continual post-training.</p> + https://arxiv.org/abs/2605.09608 + Sun, 10 May 2026 00:00:00 +0000 + + + MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents + https://arxiv.org/abs/2605.09530 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09530.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yining Chen, Jihao Zhao, Bo Tang, Haofen Wang, Feiyu Xiong, Zhiyu Li</p><p><b>Upvotes:</b> 141</p><p><b>Summary:</b> As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. However, cloud-assisted memory management exposes sensitive user information, while existing privacy protection methods typically rely on aggressive masking that removes task-relevant semantics and consequently degrades memory utility and personalization quality. To address this challenge, We propose MemPrivacy, which identifies privacy-sensitive spans on edge devices, replaces them with semantically structured type-aware placeholders for cloud-side memory processing, and restores the original values locally when needed. By decoupling privacy protection from semantic destruction, MemPrivacy minimizes sensitive data exposure while retaining the information required for effective memory formation and retrieval. We also construct MemPrivacy-Bench for systematic evaluation, a dataset covering 200 users and over 52k privacy instances, and introduce a four-level privacy taxonomy for configurable protection policies. Experiments show that MemPrivacy achieves strong performance in privacy information extraction, substantially surpassing strong general-purpose models such as GPT-5.2 and Gemini-3.1-Pro, while also reducing inference latency. Across multiple widely used memory systems, MemPrivacy limits utility loss to within 1.6%, outperforming baseline masking strategies. Overall, MemPrivacy offers an effective balance between privacy protection and personalized memory utility for edge-cloud agents, enabling secure, practical, and user-transparent deployment.</p> + https://arxiv.org/abs/2605.09530 + Sun, 10 May 2026 00:00:00 +0000 + + + Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning + https://arxiv.org/abs/2605.10923 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10923.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junhao Shen, Teng Zhang, Xiaoyan Zhao, Hong Cheng</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Large language model agents increasingly rely on external skills to solve complex tasks, where skills act as modular units that extend their capabilities beyond what parametric memory alone supports. Existing methods assume external skills either accumulate as persistent guidance or internalized into the policy, eventually leading to zero-skill inference. We argue this assumption is overly restrictive, since with limited parametric capacity and uneven marginal contribution across skills, the optimal active skill set is non-monotonic, task- and stage-dependent. In this work, we propose SLIM, a framework of dynamic Skill LIfecycle Management for agentic reinforcement learning (RL), which treats the active external skill set as a dynamic optimization variable jointly updated with policy learning. Specifically, SLIM estimates each active skill's marginal external contribution through leave-one-skill-out validation, then applies three lifecycle operations: retaining high-value skills, retiring skills whose contribution becomes negligible after sufficient exposure, and expanding the skill bank when persistent failures reveal missing capability coverage. Experiments show that SLIM outperforms the best baselines by an average of 7.1% points across ALFWorld and SearchQA. Results further indicate that policy learning and external skill retention are not mutually exclusive: some skills are absorbed into the policy, while others continue to provide external value, supporting SLIM as a more general paradigm for skill-based agentic RL.</p> + https://arxiv.org/abs/2605.10923 + Mon, 11 May 2026 00:00:00 +0000 + + + ELF: Embedded Language Flows + https://arxiv.org/abs/2605.10938 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10938.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keya Hu, Linlu Qiu, Yiyang Lu, Hanhong Zhao, Tianhong Li, Yoon Kim, Jacob Andreas, Kaiming He</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Diffusion and flow-based models have become the de facto approaches for generating continuous data, e.g., in domains such as images and videos. Their success has attracted growing interest in applying them to language modeling. Unlike their image-domain counterparts, today's leading diffusion language models (DLMs) primarily operate over discrete tokens. In this paper, we show that continuous DLMs can be made effective with minimal adaptation to the discrete domain. We propose Embedded Language Flows (ELF), a class of diffusion models in continuous embedding space based on continuous-time Flow Matching. Unlike existing DLMs, ELF predominantly stays within the continuous embedding space until the final time step, where it maps to discrete tokens using a shared-weight network. This formulation makes it straightforward to adapt established techniques from image-domain diffusion models, e.g., classifier-free guidance (CFG). Experiments show that ELF substantially outperforms leading discrete and continuous DLMs, achieving better generation quality with fewer sampling steps. These results suggest that ELF offers a promising path toward effective continuous DLMs.</p> + https://arxiv.org/abs/2605.10938 + Mon, 11 May 2026 00:00:00 +0000 + + + Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR + https://arxiv.org/abs/2605.10781 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10781.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jeonghye Kim, Jiwon Jeon, Dongsheng Li, Yuqing Yang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Self-distillation has emerged as a powerful framework for post-training LLMs, where a teacher conditioned on extra information guides a student without it, both from the same model. While this guidance is useful when the student has failed, on successful rollouts, the same mechanism instead overwrites the student's choices and suppresses it's own reasoning. Therefore, we propose reading the original self-distillation signal in reverse: when the student succeeds along a path the teacher would not have predicted, these tokens reflect its self-driven reasoning. Building on this, we propose RLRT (RLVR with Reversed Teacher), which augments GRPO by reinforcing these tokens on correct rollouts. We interpret this as a new form of exploration in RLVR: not uniform diversity, but valuable exploration grounded in the student's own success. Across base, instruction-tuned, and thinking-tuned Qwen3 checkpoints, RLRT substantially outperforms self-distillation and exploration-based baselines, establishing information asymmetry as a new, principled design axis for RLVR.</p> + https://arxiv.org/abs/2605.10781 + Mon, 11 May 2026 00:00:00 +0000 + + + HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution + https://arxiv.org/abs/2605.09942 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09942.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongming Jiang, Yi Li, Guanpeng Li, Qiannan Li, Bingzhe Li</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binary relational graphs. However, fixed graph structures cannot capture the varying strength, confidence, and query-dependent relevance of relationships between events. In this paper, we propose HAGE, a weighted multi-relational memory framework that reconceptualizes retrieval as sequential, query-conditioned traversal over a unified relational memory graph. Memory is organized as relation-specific graph views over shared memory nodes, where each edge is associated with a trainable relation feature vector encoding multiple relational signals. Given a query, an LLM-based classifier identifies the relational intent, and a routing network dynamically modulates the corresponding dimensions of the edge embedding. Traversal scores are computed via a learned combination of semantic similarity and these query-conditioned edge representations. This allows memory traversal to prioritize high-utility relational paths while softly suppressing noisy or weakly relevant connections. Beyond adaptive traversal, HAGE further introduces a reinforcement learning-based training framework that jointly optimizes routing behavior and edge representations using downstream tasks. Finally, empirical results demonstrate improved long-horizon reasoning accuracy and a favorable accuracy-efficiency trade-off compared to state-of-the-art agentic memory systems. Our code is available at https://github.com/FredJiang0324/HAGE_MVPReview.</p> + https://arxiv.org/abs/2605.09942 + Mon, 11 May 2026 00:00:00 +0000 + + + G-Zero: Self-Play for Open-Ended Generation from Zero Data + https://arxiv.org/abs/2605.09959 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09959.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengsong Huang, Haolin Liu, Tong Zheng, Runpeng Dai, Langlin Huang, Jinyuan Li, Zongxia Li, Zhepei Wei, Yu Meng, Jiaxin Huang</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Self-evolving LLMs excel in verifiable domains but struggle in open-ended tasks, where reliance on proxy LLM judges introduces capability bottlenecks and reward hacking. To overcome this, we introduce G-Zero, a verifier-free, co-evolutionary framework for autonomous self-improvement. Our core innovation is Hint-δ, an intrinsic reward that quantifies the predictive shift between a Generator model's unassisted response and its response conditioned on a self-generated hint. Using this signal, a Proposer model is trained via GRPO to continuously target the Generator's blind spots by synthesizing challenging queries and informative hints. The Generator is concurrently optimized via DPO to internalize these hint-guided improvements. Theoretically, we prove a best-iterate suboptimality guarantee for an idealized standard-DPO version of G-Zero, provided that the Proposer induces sufficient exploration coverage and the data filteration keeps pseudo-label score noise low. By deriving supervision entirely from internal distributional dynamics, G-Zero bypasses the capability ceilings of external judges, providing a scalable, robust pathway for continuous LLM self-evolution across unverifiable domains.</p> + https://arxiv.org/abs/2605.09959 + Mon, 11 May 2026 00:00:00 +0000 + + + Continual Harness: Online Adaptation for Self-Improving Foundation Agents + https://arxiv.org/abs/2605.09998 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09998.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seth Karten, Joel Zhang, Tersoo Upaa Jr, Ruirong Feng, Wenzhe Li, Chengshuai Shi, Chi Jin, Kiran Vodrahalli</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agents' long-horizon partial-observability decision-making. We first report our Gemini Plays Pokemon (GPP) experiments. With iterative human-in-the-loop harness refinement, GPP became the first AI system to complete Pokemon Blue, Yellow Legacy on hard mode, and Crystal without a lost battle. In the hardest stages, the agent itself began iterating on its strategy through long-context memory, surfacing emergent self-improvement signals alongside human-in-the-loop refinement. Continual Harness removes the human fully from this loop: a reset-free self-improving harness for embodied agents that formalizes and automates what we observed. Starting from only a minimal environment interface, the agent alternates between acting and refining its own prompt, sub-agents, skills, and memory, drawing on any past trajectory data. Prompt-optimization methods require episode resets; Continual Harness adapts online within a single run. On Pokemon Red and Emerald across frontier models, Continual Harness starting from scratch substantially reduces button-press cost relative to the minimalist baseline and recovers a majority of the gap to a hand-engineered expert harness, with capability-dependent gains, despite starting from the same raw interface with no curated knowledge, no hand-crafted tools, and no domain scaffolding. We then close the loop with the model itself: an online process-reward co-learning loop, in which an open-source agent's rollouts through the refining harness are relabeled by a frontier teacher and used to update the model, drives sustained in-game milestone progress on Pokemon Red without resetting the environment between training iterations.</p> + https://arxiv.org/abs/2605.09998 + Mon, 11 May 2026 00:00:00 +0000 + + + Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents + https://arxiv.org/abs/2605.10832 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10832.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijue Huang, Hangyu Guo, Chenxin Li, Junting Lu, Xinyu Geng, Zhaochen Su, Zhenyu Li, Shuang Chen, Hongru Wang, Yi R. Fung</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Multimodal deep search requires an agent to solve open-world problems by chaining search, tool use, and visual reasoning over evolving textual and visual context. Two bottlenecks limit current systems. First, existing tool-use harnesses treat images returned by search, browsing, or transformation as transient outputs, so intermediate visual evidence cannot be re-consumed by later tools. Second, training data is usually built by fixed curation recipes that cannot track the target agent's evolving capability. To address these challenges, we first introduce a visual-native agent harness centered on an image bank reference protocol, which registers every tool-returned image as an addressable reference and makes intermediate visual evidence reusable by later tools. On top of this harness, On-policy Data Evolution (ODE) runs a closed-loop data generator that refines itself across rounds from rollouts of the policy being trained. This per-round refinement makes each round's data target what the current policy still needs to learn. The same framework supports both diverse supervised fine-tuning data and policy-aware reinforcement learning data curation, covering the full training lifecycle of the target agent. Across 8 multimodal deep search benchmarks, ODE improves the Qwen3-VL-8B agent from 24.9% to 39.0% on average, surpassing Gemini-2.5 Pro in standard agent-workflow setting (37.9%). At 30B, ODE raises the average score from 30.6% to 41.5%. Further analyses validate the effectiveness of image-bank reuse, especially on complex tasks requiring iterative visual refinement, while rollout-feedback evolution yields more grounded SFT traces and better policy-matched RL tasks than static synthesis.</p> + https://arxiv.org/abs/2605.10832 + Mon, 11 May 2026 00:00:00 +0000 + + + Key-Value Means + https://arxiv.org/abs/2605.09877 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09877.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniel Goldstein, Eugene Cheah</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> We present Key-Value Means ("KVM"), a novel block-recurrence for attention that can accommodate either fixed-size or growing state. Equipping a strong transformer baseline with fixed-size KVM attention layers yields a strong O(N) chunked RNN, while adding only an insignificant number of new parameters. We train a transformer with a growable KVM cache and show it performs competitively on long-context tests with only subquadratic prefill time and sublinear state growth. KVM is implementable with standard operations and without custom kernels, and supports chunk-wise parallelizable training and prefill. It provides many of the benefits of both traditional transformers (expandable context memory, chunk-wise parallelizable training and prefill) and linear RNNs in a single unified package. It can be used on every layer, saving KV-cache memory, and allowing a continuous range of choices of prefill time complexity between O(N) and O(N^2). It can also be implemented in a hybrid solution in tandem with LRNN layers in place of traditional attention, to supplement the LRNN with improved sublinear memory growth context length usage and long context decoding. We release our code at https://github.com/recursal/KVM-paper and trained models at https://huggingface.co/collections/recursal/key-value-means under the Apache 2.0 license.</p> + https://arxiv.org/abs/2605.09877 + Mon, 11 May 2026 00:00:00 +0000 + + + PREPING: Building Agent Memory without Tasks + https://arxiv.org/abs/2605.13880 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yumin Choi, Sangwoo Park, Minki Kang, Jinheon Baek, Sung Ju Hwang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an agent faces a cold-start gap when first introduced to a new environment without any task-specific experience available. In this paper, we study pre-task memory construction: whether an agent can build procedural memory before observing any target-environment tasks, using only self-generated synthetic practice. Yet, synthetic interaction alone is insufficient, as without controlling what to practice and what to store, synthetic tasks become redundant, infeasible, and ultimately uninformative, and memory further degrades quickly due to unfiltered trajectories. To overcome this, we present Preping, a proposer-guided memory construction framework. At its core is proposer memory, a structured control state that shapes future practice. A Proposer generates synthetic tasks conditioned on this state, a Solver executes them, and a Validator determines which trajectories are eligible for memory insertion while also providing feedback to guide future proposals. Experiments on AppWorld, BFCL v3, and MCP-Universe show that Preping substantially improves over a no-memory baseline and achieves performance competitive with strong playbook-based methods built from offline or online experience, with deployment cost 2.99times lower on AppWorld and 2.23times lower on BFCL v3 than online memory construction. Further analyses reveal that the main benefit does not come from synthetic volume alone, but from proposer-side control over feasibility, redundancy, and coverage, combined with selective memory updates.</p> + https://arxiv.org/abs/2605.13880 + Mon, 11 May 2026 00:00:00 +0000 + + + Teaching Language Models to Think in Code + https://arxiv.org/abs/2605.07237 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07237.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyeon Hwang, Jiwoo Lee, Jaewoo Kang</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Tool-integrated reasoning (TIR) has emerged as a dominant paradigm for mathematical problem solving in language models, combining natural language (NL) reasoning with code execution. However, this interleaved setup has three key limitations: code often acts as a post-hoc verifier, intermediate NL computations are error-prone, and NL and code play overlapping rather than clearly distinct roles. We propose ThinC (Thinking in Code), a framework in which code itself serves as the reasoner rather than as a tool invoked by NL. A ThinC trajectory begins with a brief NL planning step, after which all reasoning unfolds through code blocks connected only by their execution outputs. We distill 12.2k code-centric trajectories from a teacher model and train ThinC-1.7B and ThinC-4B with supervised fine-tuning followed by reinforcement learning. ThinC-4B consistently outperforms every TIR baseline on five competition-level math benchmarks and even surpasses the much larger Qwen3-235B-A22B-Thinking. Further analysis shows that ThinC reasons through code: 99.2% of its final answers are grounded in interpreter output, and the model recovers reliably from code execution failures without intermediate NL reasoning. Our code and models will be released soon.</p> + https://arxiv.org/abs/2605.07237 + Mon, 11 May 2026 00:00:00 +0000 + + + Pixal3D: Pixel-Aligned 3D Generation from Images + https://arxiv.org/abs/2605.10922 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10922.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dong-Yang Li, Wang Zhao, Yuxin Chen, Wenbo Hu, Meng-Hao Guo, Fang-Lue Zhang, Ying Shan, Shi-Min Hu</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Recent advances in 3D generative models have rapidly improved image-to-3D synthesis quality, enabling higher-resolution geometry and more realistic appearance. Yet fidelity, which measures pixel-level faithfulness of the generated 3D asset to the input image, still remains a central bottleneck. We argue this stems from an implicit 2D-3D correspondence issue: most 3D-native generators synthesize shape in canonical space and inject image cues via attention, leaving pixel-to-3D associations ambiguous. To tackle this issue, we draw inspiration from 3D reconstruction and propose Pixal3D, a pixel-aligned 3D generation paradigm for high-fidelity 3D asset creation from images. Instead of generating in a canonical pose, Pixal3D directly generates 3D in a pixel-aligned way, consistent with the input view. To enable this, we introduce a pixel back-projection conditioning scheme that explicitly lifts multi-scale image features into a 3D feature volume, establishing direct pixel-to-3D correspondence without ambiguity. We show that Pixal3D is not only scalable and capable of producing high-quality 3D assets, but also substantially improves fidelity, approaching the fidelity level of reconstruction. Furthermore, Pixal3D naturally extends to multi-view generation by aggregating back-projected feature volumes across views. Finally, we show pixel-aligned generation benefits scene synthesis, and present a modular pipeline that produces high-fidelity, object-separated 3D scenes from images. Pixal3D for the first time demonstrates 3D-native pixel-aligned generation at scale, and provides a new inspiring way towards high-fidelity 3D generation of object or scene from single or multi-view images. Project page: https://ldyang694.github.io/projects/pixal3d/</p> + https://arxiv.org/abs/2605.10922 + Mon, 11 May 2026 00:00:00 +0000 + + + WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors + https://arxiv.org/abs/2605.10434 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10434.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keming Wu, Yijing Cui, Wenhan Xue, Qijie Wang, Xuan Luo, Zhiyuan Feng, Zuhao Yang, Sudong Wang, Sicong Jiang, Haowei Zhu, Zihan Wang, Ping Nie, Wenhu Chen, Bin Wang</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet the community still lacks a benchmark that directly tests whether a model can reason about how an observed world should evolve over time. We introduce WorldReasonBench, which reframes video generation evaluation as world-state prediction: given an initial state and an action, can a model generate a future video whose state evolution remains physically, socially, logically, and informationally consistent? WorldReasonBench contains 436 curated test cases with structured ground-truth QA annotations spanning four reasoning dimensions and 22 subcategories. We evaluate generated videos with a human-aligned two-part methodology: Process-aware Reasoning Verification uses structured QA and reasoning-phase diagnostics to detect temporal and causal failures, while Multi-dimensional Quality Assessment scores reasoning quality, temporal consistency, and visual aesthetics for ranking and reward modeling. We further introduce WorldRewardBench, a preference benchmark with approximately 6K expert-annotated pairs over 1.4K videos, supporting pair-wise and point-wise reward-model evaluation. Across modern video generators, our results expose a persistent gap between visual plausibility and world reasoning: videos can look convincing while failing dynamics, causality, or information preservation. We will release our benchmarks and evaluation toolkit to support community research on genuinely world-aware video generation at https://github.com/UniX-AI-Lab/WorldReasonBench/.</p> + https://arxiv.org/abs/2605.10434 + Mon, 11 May 2026 00:00:00 +0000 + + + PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents + https://arxiv.org/abs/2605.10341 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10341.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bihui Yu, Xinglong Xu, Junjie Jiang, Jiabei Cheng, Caijun Jia, Siyuan Li, Conghui He, Jingxuan Wei, Cheng Tan</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> A LaTeX manuscript that compiles without error is not necessarily publication-ready. The resulting PDFs frequently suffer from misplaced floats, overflowing equations, inconsistent table scaling, widow and orphan lines, and poor page balance, forcing authors into repetitive compile-inspect-edit cycles. Rule-based tools are blind to rendered visuals, operating only on source code and log files. Text-only LLMs perform open-loop text editing, unable to predict or verify the two-dimensional layout consequences of their changes. Reliable typesetting optimization therefore requires a visual closed loop with verification after every edit. We formalize this problem as Visual Typesetting Optimization (VTO), the task of transforming a compilable LaTeX paper into a visually polished, page-budget-compliant PDF through iterative visual verification and source-level revision, and introduce a five-category taxonomy of typesetting defects to guide diagnosis. We present PaperFit, a vision-in-the-loop agent that iteratively renders pages, diagnoses defects, and applies constrained repairs. To benchmark VTO, we construct PaperFit-Bench with 200 papers across 10 venue templates and 13 defect types at different difficulty. Extensive experiments show that PaperFit outperforms all baselines by a large margin, establishing that bridging the gap from compilable source to publication-ready PDF requires vision-in-the-loop optimization and that VTO constitutes a critical missing stage in the document automation pipeline.</p> + https://arxiv.org/abs/2605.10341 + Mon, 11 May 2026 00:00:00 +0000 + + + WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation + https://arxiv.org/abs/2605.10912 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10912.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuangrui Ding, Xuanlang Dai, Long Xing, Shengyuan Ding, Ziyu Liu, Yang JingYi, Penghui Yang, Zhixiong Zhang, Xilin Wei, Xinyu Fang, Yubo Ma, Haodong Duan, Jing Shao, Jiaqi Wang, Dahua Lin, Kai Chen, Yuhang Zang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks, mock-service APIs, and final-answer checks, leaving open whether agents can complete realistic long-horizon work in the runtimes where they are deployed. This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories. Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls, and runs inside a reproducible Docker container hosting an actual CLI agent harness (OpenClaw, Claude Code, Codex, or Hermes Agent) with access to real tools rather than mock services. Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification. Across 19 frontier models, the best, Claude Opus 4.7, reaches only 62.2% overall under OpenClaw, while every other model stays below 60%, and switching harness alone shifts a single model by up to 18 points. These results show that long-horizon, native-runtime agent evaluation remains a far-from-resolved task for current frontier models. We release the tasks, code, and containerized tooling to support reproducible evaluation.</p> + https://arxiv.org/abs/2605.10912 + Mon, 11 May 2026 00:00:00 +0000 + + + Model Merging Scaling Laws in Large Language Models + https://arxiv.org/abs/2509.24244 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24244.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanyi Wang, Yanggan Gu, Yiming Zhang, Qi Zhou, Zhaoyi Yan, Congkai Xie, Xinyao Wang, Jianbo Yuan, Hongxia Yang</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> We study empirical scaling laws for language model merging measured by cross-entropy. Despite its wide practical use, merging lacks a quantitative rule that predicts returns as we add experts or scale the model size. We identify a compact power law that links model size and expert number: the size-dependent floor decreases with model capacity, while the merging tail exhibits clear diminishing returns in the number of experts. The law holds in-domain and cross-domain, tightly fits measured curves across diverse architectures and methods (Average, TA, TIES, DARE), and explains two robust regularities: most gains arrive early, and variability shrinks as more experts are included. Building on this, we present a simple theory that explains why gains fall roughly as 1/k and links the floor and tail to properties of the base model and the diversity across domains. This law enables predictive planning: estimate how many experts are needed to reach a target loss, decide when to stop adding experts, and trade off scaling the base model versus adding experts under a fixed budget--turning merging from heuristic practice into a computationally efficient, planable alternative to multitask training. This suggests a scaling principle for distributed generative AI: predictable gains can be achieved by composing specialists, offering a complementary path toward AGI-level systems.</p> + https://arxiv.org/abs/2509.24244 + Mon, 11 May 2026 00:00:00 +0000 + + + TMAS: Scaling Test-Time Compute via Multi-Agent Synergy + https://arxiv.org/abs/2605.10344 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10344.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> George Wu, Nan Jing, Qing Yi, Chuan Hao, Ming Yang, Feng Chang, Yuan Wei, Jian Yang, Ran Tao, Bryan Dai</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Test-time scaling has become an effective paradigm for improving the reasoning ability of large language models by allocating additional computation during inference. Recent structured approaches have further advanced this paradigm by organizing inference across multiple trajectories, refinement rounds, and verification-based feedback. However, existing structured test-time scaling methods either weakly coordinate parallel reasoning trajectories or rely on noisy historical information without explicitly deciding what should be retained and reused, limiting their ability to balance exploration and exploitation. In this work, we propose TMAS, a framework for scaling test-time compute via multi-agent synergy. TMAS organizes inference as a collaborative process among specialized agents, enabling structured information flow across agents, trajectories, and refinement iterations. To support effective cross-trajectory collaboration, TMAS introduces hierarchical memories: the experience bank reuses low-level reliable intermediate conclusions and local feedback, while the guideline bank records previously explored high-level strategies to steer subsequent rollouts away from redundant reasoning patterns. Furthermore, we design a hybrid reward reinforcement learning scheme tailored to TMAS, which jointly preserves basic reasoning capability, enhances experience utilization, and encourages exploration beyond previously attempted solution strategies. Extensive experiments on challenging reasoning benchmarks demonstrate that TMAS achieves stronger iterative scaling than existing test-time scaling baselines, while hybrid reward training further improves scaling effectiveness and stability across iterations. Code and data are available at https://github.com/george-QF/TMAS-code.</p> + https://arxiv.org/abs/2605.10344 + Mon, 11 May 2026 00:00:00 +0000 + + + RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards + https://arxiv.org/abs/2605.10899 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10899.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang, Jun Yan, Yanfei Chen, Chun-Liang Li, Long T. Le, Rujun Han, George Lee, Hanghang Tong, Chen-Yu Lee, Tomas Pfister</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> Training deep research agents, namely systems that plan, search, evaluate evidence, and synthesize long-form reports, pushes reinforcement learning beyond the regime of verifiable rewards. Their outputs lack ground-truth answers, their trajectories span many tool-augmented decisions, and standard post-training offers little mechanism for turning past attempts into reusable experience. In this work, we argue that rubrics should serve not merely as final-answer evaluators, but as the shared interface that structures policy execution, judge feedback, and agent memory. Based on this view, we introduce RubricEM, a rubric-guided reinforcement learning framework that combines stagewise policy decomposition with reflection-based meta-policy evolution. RubricEM first makes research trajectories stage-aware by conditioning planning, evidence gathering, review, and synthesis on self-generated rubrics. It then assigns credit with Stage-Structured GRPO, which uses stagewise rubric judgments to provide denser semantic feedback for long-horizon optimization. In parallel, RubricEM trains a shared-backbone reflection meta-policy that distills judged trajectories into reusable rubric-grounded guidance for future attempts. The resulting RubricEM-8B achieves strong performance across four long-form research benchmarks, outperforming comparable open models and approaching proprietary deep-research systems. Beyond final performance, we perform thorough analyses to understand the key ingredients of RubricEM.</p> + https://arxiv.org/abs/2605.10899 + Mon, 11 May 2026 00:00:00 +0000 + + + Qwen-Image-2.0 Technical Report + https://arxiv.org/abs/2605.10730 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10730.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bing Zhao, Chenfei Wu, Deqing Li, Hao Meng, Jiahao Li, Jie Zhang, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kuan Cao, Kun Yan, Liang Peng, Lihan Jiang, Niantong Li, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiao Xu, Xiaoyue Chen, Xihua Wang, Yan Shu, Yanran Zhang, Yi Wang, Yilei Chen, Ying Ba, Yixian Xu, Yujia Wu, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhendong Wang, Zihao Liu, Zikai Zhou, An Yang, Chen Cheng, Chenxu Lv, Dayiheng Liu, Fan Zhou, Hantian Xiong, Hongzhu Shi, Hu Wei, Huihong Zhao, Ivy Liu, Jianwei Zhang, Jiawei Zhang, Kai Chen, Kang He, Levon Xue, Lin Qu, Linhan Tang, Luwen Feng, Minggang Wu, Minmin Sun, Na Ni, Rui Men, Shuai Bai, Sishou Zheng, Tao Lan, Tianqi Zhang, Tingkun Wen, Wei Wang, Weixu Qiao, Weiyi Lu, Wenmeng Zhou, Xiaodong Deng, Xiaoxiao Xu, Xinlei Fang, Xionghui Chen, Yanan Wang, Yang Fan, Yichang Zhang, Yixuan Xu, Yu Wu, Zhiyuan Ma, Zhizhi Cai</p><p><b>Upvotes:</b> 104</p><p><b>Summary:</b> We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite recent progress, existing models still struggle with ultra-long text rendering, multilingual typography, high-resolution photorealism, robust instruction following, and efficient deployment, especially in text-rich and compositionally complex scenarios. Qwen-Image-2.0 addresses these challenges by coupling Qwen3-VL as the condition encoder with a Multimodal Diffusion Transformer for joint condition-target modeling, supported by large-scale data curation and a customized multi-stage training pipeline. This enables strong multimodal understanding while preserving flexible generation and editing capabilities. The model supports instructions of up to 1K tokens for generating text-rich content such as slides, posters, infographics, and comics, while significantly improving multilingual text fidelity and typography. It also enhances photorealistic generation with richer details, more realistic textures, and coherent lighting, and follows complex prompts more reliably across diverse styles. Extensive human evaluations show that Qwen-Image-2.0 substantially outperforms previous Qwen-Image models in both generation and editing, marking a step toward more general, reliable, and practical image generation foundation models.</p> + https://arxiv.org/abs/2605.10730 + Mon, 11 May 2026 00:00:00 +0000 + + + MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image + https://arxiv.org/abs/2605.10616 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10616.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alan Arazi, Eilam Shapira, Shoham Grunblat, Mor Ventura, Elad Hoffer, Gioia Blayer, David Holzmüller, Lennart Purucker, Gaël Varoquaux, Frank Hutter, Roi Reichart</p><p><b>Upvotes:</b> 134</p><p><b>Summary:</b> Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack native support for unstructured modalities such as text and image, and rely on frozen, pretrained embeddings to process them. On established Multimodal Tabular Learning benchmarks, we show that tuning the embeddings to the task improves performance. Existing benchmarks, however, often focus on the mere co-occurrence of modalities; this leads to high variance across datasets and masks the benefits of task-specific tuning. To address this gap, we introduce MulTaBench, a benchmark of 40 datasets, split equally between image-tabular and text-tabular tasks. We focus on predictive tasks where the modalities provide complementary predictive signal, and where generic embeddings lose critical information, necessitating Target-Aware Representations that are aligned with the task. Our experimental results demonstrate that the gains from target-aware representation tuning generalize across both text and image modalities, several tabular learners, encoder scales, and embedding dimensions. MulTaBench constitutes the largest image-tabular benchmarking effort to date, spanning high-impact domains such as healthcare and e-commerce. It is designed to enable the research of novel architectures which incorporate joint modeling and target-aware representations, paving the way for the development of novel Multimodal Tabular Foundation Models.</p> + https://arxiv.org/abs/2605.10616 + Mon, 11 May 2026 00:00:00 +0000 + + + Covering Human Action Space for Computer Use: Data Synthesis and Benchmark + https://arxiv.org/abs/2605.12501 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12501.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Miaosen Zhang, Xiaohan Zhao, Zhihong Tan, Zhou Huoshen, Yijia Fan, Yifan Yang, Kai Qiu, Bei Liu, Justin Wagle, Chenzhong Yin, Mingxi Cheng, Ji Li, Qi Dai, Chong Luo, Xu Yang, Xin Geng, Baining Guo</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user trust. Our analysis of failure cases from advanced models suggests a long-tail pattern in GUI operations, where a relatively small fraction of complex and diverse interactions accounts for a disproportionate share of task failures. We hypothesize that this issue largely stems from the scarcity of data for complex interactions. To address this problem, we propose a new benchmark CUActSpot for evaluating models' capabilities on complex interactions across five modalities: GUI, text, table, canvas, and natural image, as well as a variety of actions (click, drag, draw, etc.), covering a broader range of interaction types than prior click-centric benchmarks that focus mainly on GUI widgets. We also design a renderer-based data-synthesis pipeline: scenes are automatically generated for each modality, screenshots and element coordinates are recorded, and an LLM produces matching instructions and action traces. After training on this corpus, our Phi-Ground-Any-4B outperforms open-source models with fewer than 32B parameters. We will release our benchmark, data, code, and models at https://github.com/microsoft/Phi-Ground.git</p> + https://arxiv.org/abs/2605.12501 + Tue, 12 May 2026 00:00:00 +0000 + + + From Web to Pixels: Bringing Agentic Search into Visual Perception + https://arxiv.org/abs/2605.12497 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12497.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bokang Yang, Xinyi Sun, Kaituo Feng, Xingping Dong, Dongming Wu, Xiangyu Yue</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Visual perception connects high-level semantic understanding to pixel-level perception, but most existing settings assume that the decisive evidence for identifying a target is already in the image or frozen model knowledge. We study a more practical yet harder open-world case where a visible object must first be resolved from external facts, recent events, long-tail entities, or multi-hop relations before it can be localized. We formalize this challenge as Perception Deep Research and introduce WebEye, an object-anchored benchmark with verifiable evidence, knowledge-intensive queries, precise box/mask annotations, and three task views: Search-based Grounding, Search-based Segmentation, and Search-based VQA. WebEyes contains 120 images, 473 annotated object instances, 645 unique QA pairs, and 1,927 task samples. We further propose Pixel-Searcher, an agentic search-to-pixel workflow that resolves hidden target identities and binds them to boxes, masks, or grounded answers. Experiments show that Pixel-Searcher achieves the strongest open-source performance across all three task views, while failures mainly arise from evidence acquisition, identity resolution, and visual instance binding.</p> + https://arxiv.org/abs/2605.12497 + Tue, 12 May 2026 00:00:00 +0000 + + + On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment + https://arxiv.org/abs/2605.11882 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.11882.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bo Yin, Qi Li, Xinchao Wang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Tool-using LLM agents fail through trajectories rather than only final responses, as they may execute unsafe tool calls, follow injected instructions, comply with harmful requests, or over-refuse benign tasks despite producing a seemingly safe answer. Existing safety-alignment signals are largely response-level or off-policy, and often incur a safety-utility trade-off: improving agent safety comes at the cost of degraded task performance. Such sparse and single-objective rewards severely limit real-world usability. To bridge this gap, we propose FATE, an on-policy self-evolving framework that transforms verifier-scored failures into repair supervision without expert demonstrations. For each failure, the same policy proposes repair candidates, which are then re-scored by verifiers and filtered across security, utility, over-refusal control, and trajectory validity. This dense trajectory-level information is then used as a supervision signal for agent self-evolution. During this process, we further introduce Pareto-Front Policy Optimization (PFPO), combining supervised warmup with Pareto-aware policy optimization to preserve safety-utility trade-offs. Experiments on AgentDojo, AgentHarm, and ATBench show that FATE improves safety across different models and scales while preserving useful behavior. Compared with strong baselines, FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%. These results suggest that failed trajectories can provide structured repair supervision for safer self-evolving agents.</p> + https://arxiv.org/abs/2605.11882 + Tue, 12 May 2026 00:00:00 +0000 + + + Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction + https://arxiv.org/abs/2605.12070 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12070.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhong Guan, Yongjian Guo, Haoran Sun, Wen Huang, Shuai Di, Xiong Jun Wu, Likang Wu, Hongke Zhao</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it also introduces a critical failure mode for PPO-style off-policy correction. In heterogeneous training systems, the total importance ratio should ideally be decomposed into two semantically distinct factors: a training--inference discrepancy term that aligns inference-side and training-side distributions at the same behavior-policy version, and a policy-staleness term that constrains the update from the historical policy to the current policy. We show that practical asynchronous pipelines with delayed updates and partial rollouts often lose the required historical training-side logits, or old logits. This missing-old-logit problem entangles discrepancy repair with staleness correction, breaks the intended semantics of decoupled correction, and makes clipping and masking thresholds interact undesirably. To address this issue, we study both exact and approximate correction routes. We propose three exact old-logit acquisition strategies: snapshot-based version tracking, a dedicated old-logit model, and synchronization via partial rollout interruption, and compare their system trade-offs. From the perspective of approximate correction, we focus on preserving the benefits of decoupled correction through a more appropriate approximate policy when exact old logits cannot be recovered at low cost, without incurring extra system overhead. Following this analysis, we adopt a revised PPO-EWMA method, which achieves significant gains in both training speed and optimization performance. Code at https://github.com/millioniron/ROLL.</p> + https://arxiv.org/abs/2605.12070 + Tue, 12 May 2026 00:00:00 +0000 + + + Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs + https://arxiv.org/abs/2605.12460 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12460.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guinan Su, Yanwu Yang, Xueyan Li, Jonas Geiping</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or computer use applications. However, the core of these systems has not changed much since early instruction-tuned models like ChatGPT. Even advanced AI agents function on message exchange formats, successively exchanging messages with users, systems, with itself (i.e. chain-of-thought) and tools in a single stream of computation. This bottleneck to a single stream in chat models leads to a number of limitations: the agent cannot act (generate output) while reading, and in reverse, cannot react to new information while writing. Similarly, the agent cannot act while thinking and cannot think while reading or acting on information. In this work, we show that models can be unblocked by switching from instruction-tuning for sequential message formats to instruction-tuning for multiple, parallel streams of computation, splitting each role into a separate stream. Every forward pass of the language model then simultaneously reads from multiple input streams and generates tokens in multiple output streams, all of which causally depend on earlier timesteps. We argue that this data-driven change remedies a number of usability limitations as outlined above, improves model efficiency through parallelization, improves model security through better separation of concerns and can further improve model monitorability.</p> + https://arxiv.org/abs/2605.12460 + Tue, 12 May 2026 00:00:00 +0000 + + + Learning, Fast and Slow: Towards LLMs That Adapt Continually + https://arxiv.org/abs/2605.12484 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12484.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rishabh Tiwari, Kusha Sareen, Lakshya A Agrawal, Joseph E. Gonzalez, Matei Zaharia, Kurt Keutzer, Inderjit S Dhillon, Rishabh Agarwal, Devvrit Khatri</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of plasticity. In contrast, in-context learning with fixed LLM parameters can cheaply and rapidly adapt to task-specific requirements (e.g., prompt optimization), but cannot by itself typically match the performance gains available through updating LLM parameters. There is no good reason for restricting learning to being in-context or in-weights. Moreover, humans also likely learn at different time scales (e.g., System 1 vs 2). To this end, we introduce a fast-slow learning framework for LLMs, with model parameters as "slow" weights and optimized context as "fast" weights. These fast "weights" can learn from textual feedback to absorb the task-specific information, while allowing slow weights to stay closer to the base model and persist general reasoning behaviors. Fast-Slow Training (FST) is up to 3x more sample-efficient than only slow learning (RL) across reasoning tasks, while consistently reaching a higher performance asymptote. Moreover, FST-trained models remain closer to the base LLM (up to 70% less KL divergence), resulting in less catastrophic forgetting than RL-training. This reduced drift also preserves plasticity: after training on one task, FST trained models adapt more effectively to a subsequent task than parameter-only trained models. In continual learning scenarios, where task domains change on the fly, FST continues to acquire each new task while parameter-only RL stalls.</p> + https://arxiv.org/abs/2605.12484 + Tue, 12 May 2026 00:00:00 +0000 + + + Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding + https://arxiv.org/abs/2605.07637 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07637.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Valeriy Vyaltsev, Alsu Sagirova, Anton Andreychuk, Oleg Bulichev, Yuri Kuratov, Konstantin Yakovlev, Aleksandr Panov, Alexey Skrynnik</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Multi-agent pathfinding (MAPF) is a widely used abstraction for multi-robot trajectory planning problems, where multiple homogeneous agents move simultaneously within a shared environment. Although solving MAPF optimally is NP-hard, scalable and efficient solvers are critical for real-world applications such as logistics and search-and-rescue. To this end, the research community has proposed various decentralized suboptimal MAPF solvers that leverage machine learning. Such methods frame MAPF (from a single agent perspective) as a Dec-POMDP where at each time step an agent has to decide an action based on the local observation and typically solve the problem via reinforcement learning or imitation learning. We follow the same approach but additionally introduce a learnable communication module tailored to enhance cooperation between agents via efficient feature sharing. We present the Local Communication for Multi-agent Pathfinding (LC-MAPF), a generalizable pre-trained model that applies multi-round communication between neighboring agents to exchange information and improve their coordination. Our experiments show that the introduced method outperforms the existing learning-based MAPF solvers, including IL and RL-based approaches, across diverse metrics in a diverse range of (unseen) test scenarios. Remarkably, the introduced communication mechanism does not compromise LC-MAPF's scalability, a common bottleneck for communication-based MAPF solvers.</p> + https://arxiv.org/abs/2605.07637 + Tue, 12 May 2026 00:00:00 +0000 + + + The DAWN of World-Action Interactive Models + https://arxiv.org/abs/2605.11550 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.11550.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongbo Lu, Liang Yao, Chenghao He, Haoyu Wang, Xiang Gu, Xianfei Li, Wenlong Liao, Tao He, Pai Peng</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. Existing World Action Models (WAMs) largely miss this reciprocity, treating world prediction and action generation as either isolated parallel branches or rigid predict-then-plan pipelines. We formalize this perspective as World-Action Interactive Models (WAIMs), and instantiate it in autonomous driving with DAWN (Denoising Actions and World iNteractive model), a simple yet strong latent generative baseline. DAWN operates in a compact semantic latent space and couples a World Predictor with a World-Conditioned Action Denoiser: the predicted world hypothesis conditions action denoising, while the denoised action hypothesis is fed back to update the world prediction, so that both are recursively refined during inference. Rather than eliminating test-time world evolution altogether or rolling out the full future in pixel space, DAWN performs a short explicit latent rollout that is sufficient to support long-horizon trajectory generation in complex interactive scenes. Experiments show that DAWN achieves strong planning performance and favorable safety-related results across multiple autonomous driving benchmarks. More broadly, our results suggest that interactive world-action generation is a principled path toward truly actionable world models.</p> + https://arxiv.org/abs/2605.11550 + Tue, 12 May 2026 00:00:00 +0000 + + + ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents + https://arxiv.org/abs/2605.12481 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12481.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuhao Hu, Xi Zhang, Haiyang Xu, Kyle Qiao, Jingyi Yang, Xuanjing Huang, Jing Shao, Ming Yan, Jieping Ye</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Computer Use Agents (CUAs) can act through both atomic GUI actions, such as click and type, and high-level tool calls, such as API-based file operations, but this hybrid action space often leaves them uncertain about when to continue with GUI actions or switch to tools, leading to suboptimal execution paths. This difficulty stems from the scarcity of high-quality interleaved GUI-Tool trajectories, the cost and brittleness of collecting real tool trajectories, and the lack of trajectory-level supervision for GUI-Tool path selection. In this paper, we propose ToolCUA, an end-to-end agent designed to learn optimal GUI-Tool path selection through a staged training paradigm. We first introduce an Interleaved GUI-Tool Trajectory Scaling Pipeline that repurposes abundant static GUI trajectories and synthesizes a grounded tool library, enabling diverse GUI-Tool trajectories without manual engineering or real tool-trajectory collection. We then perform Tool-Bootstrapped GUI RFT, combining warmup SFT with single-turn RL to improve decisions at critical GUI-Tool switching points. Finally, we optimize ToolCUA with Online Agentic RL in a high-fidelity GUI-Tool environment, guided by a Tool-Efficient Path Reward that encourages appropriate tool use and shorter execution paths. Experiments on OSWorld-MCP show that ToolCUA achieves 46.85% accuracy, a relative improvement of approximately 66% over the baseline, establishing a new state of the art among models of comparable scale. It also improves by 3.9% over GUI-only settings, demonstrating effective GUI-Tool orchestration. The results further suggest that training in a hybrid action space is a promising paradigm for real-world digital agents. Open-sourced here: https://x-plug.github.io/ToolCUA/</p> + https://arxiv.org/abs/2605.12481 + Tue, 12 May 2026 00:00:00 +0000 + + + CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives + https://arxiv.org/abs/2605.12496 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12496.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihao Meng, Zichen Liu, Hao Ouyang, Qiuyu Wang, Ka Leong Cheng, Yue Yu, Hanlin Wang, Haobo Li, Jiapeng Zhu, Yanhong Zeng, Xing Zhu, Yujun Shen, Qifeng Chen, Huamin Qu</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Autoregressive video generation aims at real-time, open-ended synthesis. Yet, cinematic storytelling is not merely the endless extension of a single scene; it requires progressing through evolving events, viewpoint shifts, and discrete shot boundaries. Existing autoregressive models often struggle in this setting. Trained primarily for short-horizon continuation, they treat long sequences as extended single shots, inevitably suffering from motion stagnation and semantic drift during long rollouts. To bridge this gap, we introduce CausalCine, an interactive autoregressive framework that transforms multi-shot video generation into an online directing process. CausalCine generates causally across shot changes, accepts dynamic prompts on the fly, and reuses context without regenerating previous shots. To achieve this, we first train a causal base model on native multi-shot sequences to learn complex shot transitions prior to acceleration. We then propose Content-Aware Memory Routing (CAMR), which dynamically retrieves historical KV entries according to attention-based relevance scores rather than temporal proximity, preserving cross-shot coherence under bounded active memory. Finally, we distill the causal base model into a few-step generator for real-time interactive generation. Extensive experiments demonstrate that CausalCine significantly outperforms autoregressive baselines and approaches the capability of bidirectional models while unlocking the streaming interactivity of causal generation. Demo available at https://yihao-meng.github.io/CausalCine/</p> + https://arxiv.org/abs/2605.12496 + Tue, 12 May 2026 00:00:00 +0000 + + + L2P: Unlocking Latent Potential for Pixel Generation + https://arxiv.org/abs/2605.12013 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12013.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhennan Chen, Junwei Zhu, Xu Chen, Jiangning Zhang, Jiawei Chen, Zhuoqi Zeng, Wei Zhang, Chengjie Wang, Jian Yang, Ying Tai</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Pixel diffusion models have recently regained attention for visual generation. However, training advanced pixel-space models from scratch demands prohibitive computational and data resources. To address this, we propose the Latent-to-Pixel (L2P) transfer paradigm, an efficient framework that directly harnesses the rich knowledge of pre-trained LDMs to build powerful pixel-space models. Specifically, L2P discards the VAE in favor of large-patch tokenization and freezes the source LDM's intermediate layers, exclusively training shallow layers to learn the latent-to-pixel transformation. By utilizing LDM-generated synthetic images as the sole training corpus, L2P fits an already smooth data manifold, enabling rapid convergence with zero real-data collection. This strategy allows L2P to seamlessly migrate massive latent priors to the pixel space using only 8 GPUs. Furthermore, eliminating the VAE memory bottleneck unlocks native 4K ultra-high resolution generation. Extensive experiments across mainstream LDM architectures show that L2P incurs negligible training overhead, yet performs on par with the source LDM on DPG-Bench and reaches 93% performance on GenEval.</p> + https://arxiv.org/abs/2605.12013 + Tue, 12 May 2026 00:00:00 +0000 + + + Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization + https://arxiv.org/abs/2605.10780 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10780.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuanyu Zhu, Yan Bai, Yang Shi, Yihang Lou, Yuanxing Zhang, Jing Jin, Yuan Zhou</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quality. However, existing methods universally extract features from only the last encoder layer, discarding the rich hierarchical information distributed across intermediate layers. We show that low-level visual details survive in the last layer merely as attenuated residuals after multiple layers of semantic abstraction, and that explicitly fusing multi-layer features can substantially recover this lost information. We propose DRoRAE (Depth-Routed Representation AutoEncoder), a lightweight fusion module that adaptively aggregates all encoder layers via energy-constrained routing and incremental correction, producing an enriched latent compatible with a frozen pretrained decoder. A three-phase decoupled training strategy first learns the fusion under the implicit distributional constraint of the frozen decoder, then fine-tunes the decoder to fully exploit the enriched representation. On ImageNet-256, DRoRAE reduces rFID from 0.57 to 0.29 and improves generation FID from 1.74 to 1.65 (with AutoGuidance), with gains also transferring to text-to-image synthesis. Furthermore, we uncover a log-linear scaling law (R^2{=}0.86) between fusion capacity and reconstruction quality, identifying representation richness as a new, predictably scalable dimension for visual tokenizers analogous to vocabulary size in NLP.</p> + https://arxiv.org/abs/2605.10780 + Tue, 12 May 2026 00:00:00 +0000 + + + AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward + https://arxiv.org/abs/2605.12495 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12495.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runhui Huang, Jie Wu, Rui Yang, Zhe Liu, Hengshuang Zhao</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal generation capabilities without an additional cold-start stage. Our approach unlocks the model's intrinsic potential to perform advanced reasoning tasks: Reasoning Text-to-Image Generation, where the model actively infers implicit user intents, and Self-Reflective Refinement, where it autonomously diagnoses and corrects misalignments in generated outputs. To address the challenge of providing stable supervision for real-world multimodal generation, we introduce the Decompositional Verifiable Reward (DVReward). Unlike holistic scalar rewards, DVReward utilizes an LLM to decompose complex user requests into atomic, verifiable semantic and quality questions, which are then evaluated by a general MLLM to provide reliable and interpretable feedback. Extensive experiments demonstrate that AlphaGRPO yields robust improvements across multimodal generation benchmarks, including GenEval, TIIF-Bench, DPG-Bench and WISE, while also achieving significant gains in editing tasks on GEdit without training on editing tasks. These results validate that our self-reflective reinforcement approach effectively leverages inherent understanding to guide high-fidelity generation. Project page: https://huangrh99.github.io/AlphaGRPO/</p> + https://arxiv.org/abs/2605.12495 + Tue, 12 May 2026 00:00:00 +0000 + + + TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking + https://arxiv.org/abs/2605.12587 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12587.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jisu Nam, Jahyeok Koo, Soowon Son, Jaewoo Jung, Honggyu An, Junhwa Hur, Seungryong Kim</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from strong motion priors learned from real-world videos. Existing 3D trackers either follow iterative paradigms trained from scratch on synthetic data or fine-tune 3D reconstruction models learned from static multi-view images, both lacking real-world motion priors. Pre-trained video diffusion transformers (video DiTs) offer rich spatio-temporal priors from internet-scale videos, making them a promising foundation for 3D tracking. However, their frame-anchored formulation, which generates each frame's content, is fundamentally mismatched with reference-anchored dense 3D tracking, which must follow the same physical points from a reference frame across time. We present TrackCraft3R, the first method to repurpose a video DiT as a feed-forward dense 3D tracker. Given a monocular video and its frame-anchored reconstruction pointmap, TrackCraft3R predicts a reference-anchored tracking pointmap that follows every pixel of the first frame across time in a single forward pass, along with its visibility. We achieve this through two designs: (i) a dual-latent representation that uses per-frame geometry latents and reference-anchored track latents as dense queries, and (ii) temporal RoPE alignment, which specifies the target timestamp of each track latent. Together, these designs convert the per-frame generative paradigm of video DiTs into a reference-anchored tracking formulation with LoRA fine-tuning. TrackCraft3R achieves state-of-the-art performance on standard sparse and dense 3D tracking benchmarks, while running 1.3x faster and using 4.6x less peak memory than the strongest prior method. We further demonstrate robustness to large motions and long videos.</p> + https://arxiv.org/abs/2605.12587 + Tue, 12 May 2026 00:00:00 +0000 + + + Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling + https://arxiv.org/abs/2605.12411 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12411.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Eilam Shapira, Moshe Tennenholtz, Roi Reichart</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> AI agents negotiate and transact in natural language with unfamiliar counterparts: a buyer bot facing an unknown seller, or a procurement assistant negotiating with a supplier. In such interactions, the counterpart's LLM, prompts, control logic, and rule-based fallbacks are hidden, while each decision can have monetary consequences. We ask whether an agent can predict an unfamiliar counterpart's next decision from a few interactions. To avoid real-world logging confounds, we study this problem in controlled bargaining and negotiation games, formulating it as target-adaptive text-tabular prediction: each decision point is a table row combining structured game state, offer history, and dialogue, while K previous games of the same target agent, i.e., the counterpart being modeled, are provided in the prompt as labeled adaptation examples. Our model is built on a tabular foundation model that represents rows using game-state features and LLM-based text representations, and adds LLM-as-Observer as an additional representation: a small frozen LLM reads the decision-time state and dialogue; its answer is discarded, and its hidden state becomes a decision-oriented feature, making the LLM an encoder rather than a direct few-shot predictor. Training on 13 frontier-LLM agents and testing on 91 held-out scaffolded agents, the full model outperforms direct LLM-as-Predictor prompting and game+text features baselines. Within this tabular model, Observer features contribute beyond the other feature schemes: at K=16, they improve response-prediction AUC by about 4 points across both tasks and reduce bargaining offer-prediction error by 14%. These results show that formulating counterpart prediction as a target-adaptive text-tabular task enables effective adaptation, and that hidden LLM representations expose decision-relevant signals that direct prompting does not surface.</p> + https://arxiv.org/abs/2605.12411 + Tue, 12 May 2026 00:00:00 +0000 + + + Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics + https://arxiv.org/abs/2605.12178 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12178.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jishnu Sethumadhavan Nair, Patrice Bechard, Rishabh Maheshwary, Surajit Dasgupta, Sravan Ramachandran, Aakash Bhagat, Shruthan Radhakrishna, Pulkit Pattnaik, Johan Obando-Ceron, Shiva Krishna Reddy Malay, Sagar Davasam, Seganrasan Subramanian, Vipul Mittal, Sridhar Krishna Nemala, Christopher Pal, Srinivas Sunkara, Sai Rajeswar</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> World models enable agents to anticipate the effects of their actions by internalizing environment dynamics. In enterprise systems, however, these dynamics are often defined by tenant-specific business logic that varies across deployments and evolves over time, making models trained on historical transitions brittle under deployment shift. We ask a question the world-models literature has not addressed: when the rules can be read at inference time, does an agent still need to learn them? We argue, and demonstrate empirically, that in settings where transition dynamics are configurable and readable, runtime discovery complements offline training by grounding predictions in the active system instance. We propose enterprise discovery agents, which recover relevant transition dynamics at runtime by reading the system's configuration rather than relying solely on internalized representations. We introduce CascadeBench, a reasoning-focused benchmark for enterprise cascade prediction that adopts the evaluation methodology of World of Workflows on diverse synthetic environments, and use it together with deployment-shift evaluation to show that offline-trained world models can perform well in-distribution but degrade as dynamics change, whereas discovery-based agents are more robust under shift by grounding their predictions in the current instance. Our findings suggest that, in configurable enterprise environments, agents should not rely solely on fixed internalized dynamics, but should incorporate mechanisms for discovering relevant transition logic at runtime.</p> + https://arxiv.org/abs/2605.12178 + Tue, 12 May 2026 00:00:00 +0000 + + + World Action Models: The Next Frontier in Embodied AI + https://arxiv.org/abs/2605.12090 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12090.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyin Wang, Junhao Shi, Zhaoyang Fu, Xinzhe He, Feihong Liu, Chenchen Yang, Yikang Zhou, Zhaoye Fei, Jingjing Gong, Jinlan Fu, Mike Zheng Shou, Xuanjing Huang, Xipeng Qiu, Yu-Gang Jiang</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention. A growing body of work addresses this limitation by integrating world models, predictive models of environment dynamics, into the action generation pipeline. We term this emerging paradigm World Action Models (WAMs): embodied foundation models that unify predictive state modeling with action generation, targeting a joint distribution over future states and actions rather than actions alone. However, the literature remains fragmented across architectures, learning objectives, and application scenarios, lacking a unified conceptual framework. We formally define WAMs and disambiguate them from related concepts, and trace the foundations and early integration of VLA and world model research that gave rise to this paradigm. We organize existing methods into a structured taxonomy of Cascaded and Joint WAMs, with further subdivision by generation modality, conditioning mechanism, and action decoding strategy. We systematically analyze the data ecosystem fueling WAMs development, spanning robot teleoperation, portable human demonstrations, simulation, and internet-scale egocentric video, and synthesize emerging evaluation protocols organized around visual fidelity, physical commonsense, and action plausibility. Overall, this survey provides the first systematic account of the WAMs landscape, clarifies key architectural paradigms and their trade-offs, and identifies open challenges and future opportunities for this rapidly evolving field.</p> + https://arxiv.org/abs/2605.12090 + Tue, 12 May 2026 00:00:00 +0000 + + + δ-mem: Efficient Online Memory for Large Language Models + https://arxiv.org/abs/2605.12357 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12357.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingdi Lei, Di Zhang, Junxian Li, Weida Wang, Kaixuan Fan, Xiang Liu, Qihan Liu, Xiaoteng Ma, Baian Chen, Soujanya Poria</p><p><b>Upvotes:</b> 112</p><p><b>Summary:</b> Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and often fails to ensure effective context utilization. We propose δ-mem, a lightweight memory mechanism that augments a frozen full-attention backbone with a compact online state of associative memory. δ-mem compresses past information into a fixed-size state matrix updated by delta-rule learning, and uses its readout to generate low-rank corrections to the backbone's attention computation during generation. With only an 8times8 online memory state, δ-mem improves the average score to 1.10times that of the frozen backbone and 1.15times that of the strongest non-δ-mem memory baseline. It achieves larger gains on memory-heavy benchmarks, reaching 1.31times on MemoryAgentBench and 1.20times on LoCoMo, while largely preserving general capabilities. These results show that effective memory can be realized through a compact online state directly coupled with attention computation, without full fine-tuning, backbone replacement, or explicit context extension.</p> + https://arxiv.org/abs/2605.12357 + Tue, 12 May 2026 00:00:00 +0000 + + + SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture + https://arxiv.org/abs/2605.12500 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiwen Diao, Penghao Wu, Hanming Deng, Jiahao Wang, Shihao Bai, Silei Wu, Weichen Fan, Wenjie Ye, Wenwen Tong, Xiangyu Fan, Yan Li, Yubo Wang, Zhijie Cao, Zhiqian Lin, Zhitao Yang, Zhongang Cai, Yuwei Niu, Yue Zhu, Bo Liu, Chengguang Lv, Haojia Yu, Haozhe Xie, Hongli Wang, Jianan Fan, Jiaqi Li, Jiefan Lu, Jingcheng Ni, Junxiang Xu, Kaihuan Liang, Lianqiang Shi, Linjun Dai, Linyan Wang, Oscar Qian, Peng Gao, Pengfei Liu, Qingping Sun, Rui Shen, Ruisi Wang, Shengnan Ma, Shuang Yang, Siyi Xie, Siying Li, Tianbo Zhong, Xiangli Kong, Xuanke Shi, Yang Gao, Yongqiang Yao, Yves Wang, Zhengqi Bai, Zhengyu Lin, Zixin Yin, Wenxiu Sun, Ruihao Gong, Quan Wang, Lewei Lu, Lei Yang, Ziwei Liu, Dahua Lin</p><p><b>Upvotes:</b> 171</p><p><b>Summary:</b> Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fragmented architectures, cascaded pipelines, and misaligned representation spaces. We argue that this divide is not merely an engineering artifact, but a structural limitation that hinders the emergence of native multimodal intelligence. Hence, we introduce SenseNova-U1, a native unified multimodal paradigm built upon NEO-unify, in which understanding and generation evolve as synergistic views of a single underlying process. We launch two native unified variants, SenseNova-U1-8B-MoT and SenseNova-U1-A3B-MoT, built on dense (8B) and mixture-of-experts (30B-A3B) understanding baselines, respectively. Designed from first principles, they rival top-tier understanding-only VLMs across text understanding, vision-language perception, knowledge reasoning, agentic decision-making, and spatial intelligence. Meanwhile, they deliver strong semantic consistency and visual fidelity, excelling in conventional or knowledge-intensive any-to-image (X2I) synthesis, complex text-rich infographic generation, and interleaved vision-language generation, with or without think patterns. Beyond performance, we show detailed model design, data preprocessing, pre-/post-training, and inference strategies to support community research. Last but not least, preliminary evidence demonstrates that our models extend beyond perception and generation, performing strongly in vision-language-action (VLA) and world model (WM) scenarios. This points toward a broader roadmap where models do not translate between modalities, but think and act across them in a native manner. Multimodal AI is no longer about connecting separate systems, but about building a unified one and trusting the necessary capabilities to emerge from within.</p> + https://arxiv.org/abs/2605.12500 + Tue, 12 May 2026 00:00:00 +0000 + + + PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World + https://arxiv.org/abs/2605.13169 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13169.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Changpeng Wang, Xin Lin, Junhan Liu, Yuheng Liu, Zhen Wang, Donglian Qi, Yunfeng Yan, Xi Chen</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Multimodal large laboratory models (MLLMs) still struggle with spatial understanding under the dominant perspective-image paradigm, which inherits the narrow field of view of human-like perception. For navigation, robotic search, and 3D scene understanding, 360-degree panoramic sensing offers a form of supersensing by capturing the entire surrounding environment at once. However, existing MLLM pipelines typically decompose panoramas into multiple perspective views, leaving the spherical structure of equirectangular projection (ERP) largely implicit. In this paper, we study pano-native understanding, which requires an MLLM to reason over an ERP panorama as a continuous, observer-centered space. To this end, we first define the key abilities for pano-native understanding, including semantic anchoring, spherical localization, reference-frame transformation, and depth-aware 3D spatial reasoning. We then build a large-scale metadata construction pipeline that converts mixed-source ERP panoramas into geometry-aware, language-grounded, and depth-aware supervision, and instantiate these signals as capability-aligned instruction tuning data. On the model side, we introduce PanoWorld with Spherical Spatial Cross-Attention, which injects spherical geometry into the visual stream. We further construct PanoSpace-Bench, a diagnostic benchmark for evaluating ERP-native spatial reasoning. Experiments show that PanoWorld substantially outperforms both proprietary and open-source baselines on PanoSpace-Bench, H* Bench, and R2R-CE Val-Unseen benchmarks. These results demonstrate that robust panoramic reasoning requires dedicated pano-native supervision and geometry-aware model adaptation. All source code and proposed data will be publicly released.</p> + https://arxiv.org/abs/2605.13169 + Wed, 13 May 2026 00:00:00 +0000 + + + Useful Memories Become Faulty When Continuously Updated by LLMs + https://arxiv.org/abs/2605.12978 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12978.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dylan Zhang, Yanshan Lin, Zhengkun Wu, Yihang Sun, Bingxuan Li, Dianqi Li, Hao Peng</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolidated abstractions distilled across many episodes into reusable, schema-like lessons. Recent agentic-memory systems pursue the consolidated form: an LLM rewrites past trajectories into a textual memory bank that it continuously updates with new interactions, promising self-improving agents without parameter updates. Yet we find that such consolidated memories produced by today's LLMs are often faulty even when derived from useful experiences. As consolidation proceeds, memory utility first rises, then degrades, and can fall below the no-memory baseline. More surprisingly, even when consolidating from ground-truth solutions, GPT-5.4 fails on 54% of a set of ARC-AGI problems it had previously solved without memory. We trace the regression to the consolidation step rather than the underlying experience: the same trajectories yield qualitatively different memories under different update schedules, and an episodic-only control that simply retains those trajectories remains competitive with the consolidators we test. In a controlled ARC-AGI Stream environment that exposes Retain, Delete, and Consolidate actions, agents preserve raw episodes by default and double the accuracy of their forced-consolidation counterparts; disabling consolidation entirely (episodic management only) matches this auto regime. Practically, robust agent memory should treat raw episodes as first-class evidence and gate consolidation explicitly rather than firing it after every interaction. Looking forward, reliable agentic memory will require LLMs that can consolidate without overwriting the evidence they depend on.</p> + https://arxiv.org/abs/2605.12978 + Wed, 13 May 2026 00:00:00 +0000 + + + Asymmetric Flow Models + https://arxiv.org/abs/2605.12964 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12964.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hansheng Chen, Jan Ackermann, Minseo Kim, Gordon Wetzstein, Leonidas Guibas</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Flow-based generation in high-dimensional spaces is difficult because velocity prediction requires modeling high-dimensional noise, even when data has strong low-rank structure. We present Asymmetric Flow Modeling (AsymFlow), a rank-asymmetric velocity parameterization that restricts noise prediction to a low-rank subspace while keeping data prediction full-dimensional. From this asymmetric prediction, AsymFlow analytically recovers the full-dimensional velocity without changing the network architecture or training/sampling procedures. On ImageNet 256times256, AsymFlow achieves a leading 1.57 FID, outperforming prior DiT/JiT-like pixel diffusion models by a large margin. AsymFlow also provides the first-ever route for finetuning pretrained latent flow models into pixel-space models: aligning the low-rank pixel subspace to the latent space gives a seamless initialization that preserves the latent model's high-level semantics and structure, so finetuning mainly improves low-level mismatches rather than relearning pixel generation. We show that the pixel AsymFlow model finetuned from FLUX.2 klein 9B establishes a new state of the art for pixel-space text-to-image generation, beating its latent base on HPSv3, DPG-Bench, and GenEval while qualitatively showing substantially improved visual realism.</p> + https://arxiv.org/abs/2605.12964 + Wed, 13 May 2026 00:00:00 +0000 + + + FrameSkip: Learning from Fewer but More Informative Frames in VLA Training + https://arxiv.org/abs/2605.13757 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13757.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Yu, Shijie Lian, Xiaopeng Lin, Zhaolong Shen, Yuliang Wei, Changti Wu, Hang Yuan, Haishan Liu, Bailing Wang, Cong Huang, Kai Chen</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Vision-Language-Action (VLA) policies are commonly trained from dense robot demonstration trajectories, often collected through teleoperation, by sampling every recorded frame as if it provided equally useful supervision. We argue that this convention creates a temporal supervision imbalance: long low-change segments dominate the training stream, while manipulation-critical transitions such as alignment, contact, grasping, and release appear only sparsely. We introduce FrameSkip, a data-layer frame selection framework that scores trajectory frames using action variation, visual-action coherence, task-progress priors, and gripper-transition preservation, then remaps training samples toward high-importance frames under a target retention ratio. Because FrameSkip operates only in the dataloader, it leaves the VLA architecture, action head, training objective, and inference procedure unchanged. Across RoboCasa-GR1, SimplerEnv, and LIBERO, FrameSkip improves the success-retention trade-off over full-frame training and simpler frame selection variants, achieving a macro-average success rate of 76.15% across the three benchmarks compared with 66.50% for full-frame training while using a compressed trajectory view that retains 20% of unique frames in the main setting.</p> + https://arxiv.org/abs/2605.13757 + Wed, 13 May 2026 00:00:00 +0000 + + + EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents + https://arxiv.org/abs/2605.13941 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Liu, Xinyu Ye, Peng Xia, Zeyu Zheng, Cihang Xie, Mingyu Ding, Huaxiu Yao</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and answer-generation policies remain frozen at deployment. We argue that truly adaptive memory requires co-evolution at two levels: the stored knowledge and the retrieval mechanism that queries it. We present EvolveMem, a self-evolving memory architecture that exposes its full retrieval configuration as a structured action space optimized by an LLM-powered diagnosis module. In each evolution round, the module reads per-question failure logs, identifies root causes, and proposes targeted configuration adjustments; a guarded meta-analyzer applies them with automatic revert-on-regression and explore-on-stagnation safeguards. This closed-loop self-evolution realizes an AutoResearch process: the system autonomously conducts iterative research cycles on its own architecture, replacing manual configuration tuning. Starting from a minimal baseline, the process converges autonomously, discovering effective retrieval strategies including entirely new configuration dimensions not present in the original action space. On LoCoMo, EvolveMem outperforms the strongest baseline by 25.7% relative and achieves a 78.0% relative improvement over the minimal baseline. On MemBench, EvolveMem exceeds the strongest baseline by 18.9% relative. Evolved configurations transfer across benchmarks with positive rather than catastrophic transfer, indicating that the self-evolution process captures universal retrieval principles rather than benchmark-specific heuristics. Code is available at https://github.com/aiming-lab/SimpleMem.</p> + https://arxiv.org/abs/2605.13941 + Wed, 13 May 2026 00:00:00 +0000 + + + Many-Shot CoT-ICL: Making In-Context Learning Truly Learn + https://arxiv.org/abs/2605.13511 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13511.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tsz Ting Chung, Lemao Liu, Mo Yu, Dit-Yan Yeung</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> In-context learning (ICL) adapts large language models (LLMs) to new tasks by conditioning on demonstrations in the prompt without parameter updates. With long-context models, many-shot ICL can use dozens to hundreds of examples and achieve performance comparable to fine-tuning, yet current understanding of its scaling behavior is largely derived from non-reasoning tasks. We study many-shot chain-of-thought in-context learning (CoT-ICL) for reasoning and show that standard many-shot rules do not transfer. Across non-reasoning and reasoning-oriented LLMs and across non-reasoning and reasoning tasks, we find: (i) a setting-dependent scaling effect, where increasing the number of CoT demonstrations is unstable for non-reasoning LLMs and benefits mainly reasoning-oriented LLMs; (ii) similarity-based retrieval helps on non-reasoning tasks but fails on reasoning, since semantic similarity poorly predicts procedural (i.e., CoT) compatibility; and (iii) an order-scaling effect, where performance variance grows with more CoT demonstrations. We interpret these behaviors by viewing many-shot CoT-ICL as in-context test-time learning rather than scaled pattern matching, and suggests two principles: (i) demonstrations should be easy for the target model to understand, and (ii) they should be ordered to support a smooth conceptual progression. Guided by the principle, we propose Curvilinear Demonstration Selection (CDS), a simple ordering method that yields up to a 5.42 percentage-point gain on geometry with 64 demonstrations. Overall, our results reframe the long context window from a retrieval buffer into a structured curriculum for in-context test-time learning.</p> + https://arxiv.org/abs/2605.13511 + Wed, 13 May 2026 00:00:00 +0000 + + + Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling + https://arxiv.org/abs/2605.13062 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13062.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuehai Bai, Yang Shi, Yi-Fan Zhang, Xuanyu Zhu, Yuran Wang, Yifan Dai, Xinyu Liu, Yiyan Ji, Xiaoling Gu, Yuanxing Zhang</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Recent image editing models have achieved remarkable progress in instruction following, multimodal understanding, and complex visual editing. However, existing benchmarks often fail to faithfully reflect human judgment, especially for strong frontier models, due to limited task difficulty and coarse-grained evaluation protocols. In parallel, reward models have become increasingly important for RL-based image editing optimization, yet existing reward model benchmarks still rely on unrealistic evaluation settings that deviate from practical RL scenarios. These limitations hinder reliable assessment of both image editing models and reward models. To address these challenges, we introduce Edit-Compass and EditReward-Compass, a unified evaluation suite for image editing and reward modeling. Edit-Compass contains 2,388 carefully annotated instances spanning six progressively challenging task categories, covering capabilities such as world knowledge reasoning, visual reasoning, and multi-image editing. Beyond broad task coverage, Edit-Compass adopts a fine-grained multidimensional evaluation framework based on structured reasoning and carefully designed scoring rubrics. In parallel, EditReward-Compass contains 2,251 preference pairs that simulate realistic reward modeling scenarios during RL optimization.</p> + https://arxiv.org/abs/2605.13062 + Wed, 13 May 2026 00:00:00 +0000 + + + Qwen-Image-VAE-2.0 Technical Report + https://arxiv.org/abs/2605.13565 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13565.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zekai Zhang, Deqing Li, Kuan Cao, Yujia Wu, Chenfei Wu, Yu Wu, Liang Peng, Hao Meng, Jiahao Li, Jie Zhang, Kaiyuan Gao, Kun Yan, Lihan Jiang, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiao Xu, Xiaoyue Chen, Yan Shu, Yanran Zhang, Yilei Chen, Yixian Xu, Yuxiang Chen, Zhendong Wang, Zihao Liu, Zikai Zhou, Yiliang Gu, Yi Wang, Xiaoxiao Xu, Lin Qu</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> We present Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability. To address the reconstruction bottlenecks of high compression, we adopt an improved architecture featuring Global Skip Connections (GSC) and expanded latent channels. Moreover, we scale training to billions of images and incorporate a synthetic rendering engine to improve performance in text-rich scenarios. To tackle the convergence challenges of high-dimensional latent space, we implement an enhanced semantic alignment strategy to make the latent space highly amenable to diffusion modeling. To optimize computational efficiency, we leverage an asymmetric and attention-free encoder-decoder backbone to minimize encoding overhead. We present a comprehensive evaluation of Qwen-Image-VAE-2.0 on public reconstruction benchmarks. To evaluate performance in text-rich scenarios, we propose OmniDoc-TokenBench, a new benchmark comprising a diverse collection of real-world documents coupled with specialized OCR-based evaluation metrics. Qwen-Image-VAE-2.0 achieves state-of-the-art reconstruction performance, demonstrating exceptional capabilities in both general domains and text-rich scenarios at high compression ratio. Furthermore, downstream DiT experiments reveal our models possess superior diffusability, significantly accelerating convergence compared to existing high-compression baselines. These establish Qwen-Image-VAE-2.0 as a leading model with high compression, superior reconstruction, and exceptional diffusability.</p> + https://arxiv.org/abs/2605.13565 + Wed, 13 May 2026 00:00:00 +0000 + + + EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents + https://arxiv.org/abs/2605.13841 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13841.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tara Bogavelli, Gabrielle Gauthier Melançon, Katrina Stankiewicz, Oluwanifemi Bamgbose, Fanny Riols, Hoang H. Nguyen, Raghav Mehndiratta, Lindsay Devon Brin, Joseph Marinier, Hari Subramani, Anil Madamala, Sridhar Krishna Nemala, Srinivas Sunkara</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Voice agents, artificial intelligence systems that conduct spoken conversations to complete tasks, are increasingly deployed across enterprise applications. However, no existing benchmark jointly addresses two core evaluation challenges: generating realistic simulated conversations, and measuring quality across the full scope of voice-specific failure modes. We present EVA-Bench, an end-to-end evaluation framework that addresses both. On the simulation side, EVA-Bench orchestrates bot-to-bot audio conversations over dynamic multi-turn dialogues, with automatic simulation validation that detects user simulator error and appropriately regenerates conversations before scoring. On the measurement side, EVA-Bench introduces two composite metrics: EVA-A (Accuracy), capturing task completion, faithfulness, and audio-level speech fidelity; and EVA-X (Experience), capturing conversation progression, spoken conciseness, and turn-taking timing. Both metrics apply to different agent architectures, enabling direct cross-architecture comparison. EVA-Bench includes 213 scenarios across three enterprise domains, a controlled perturbation suite for accent and noise robustness, and pass@1, pass@k, pass^k measurements that distinguish peak from reliable capability. Across 12 systems spanning all three architectures, we find: (1) no system simultaneously exceeds 0.5 on both EVA-A pass@1 and EVA-X pass@1; (2) peak and reliable performance diverge substantially (median pass@k - pass^k gap of 0.44 on EVA-A); and (3) accent and noise perturbations expose substantial robustness gaps, with effects varying across architectures, systems, and metrics (mean up to 0.314). We release the full framework, evaluation suite, and benchmark data under an open-source license.</p> + https://arxiv.org/abs/2605.13841 + Wed, 13 May 2026 00:00:00 +0000 + + + Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context + https://arxiv.org/abs/2605.13831 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13831.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaowei Wang, Lishu Luo, Haodong Duan, Weiwei Liu, Sijin Wu, Ji Luo, Shen Yan, Shuai Peng, Sihang Yuan, Chaoyi Huang, Yi Lin, Yangqiu Song</p><p><b>Upvotes:</b> 82</p><p><b>Summary:</b> Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video analysis, and multi-turn tool use in agentic workflows. Yet practical training recipes remain insufficiently explored, particularly for designing and balancing long-context data mixtures. In this work, we present a systematic study of long-context continued pre-training for LVLMs, extending a 7B model from 32K to 128K context with extensive ablations on long-document data. We first show that long-document VQA is substantially more effective than OCR transcription. Building on this observation, our ablations further yield three key findings: i) for sequence-length distribution, balanced data outperforms target-length-focused data (e.g., 128K), suggesting that long-context ability requires generalizable key-information retrieval across various lengths and positions; ii) retrieval remains the primary bottleneck, favoring retrieval-heavy mixtures with modest reasoning data for task diversity; and iii) pure long-document VQA largely preserves short-context capabilities, suggesting that instruction-formatted long data reduces the need for short-data mixing. Based on these findings, we introduce MMProLong, obtained by long-context continued pre-training from Qwen2.5-VL-7B with only a 5B-token budget. MMProLong improves long-document VQA scores by 7.1% and maintains strong performance at 256K and 512K contexts beyond its 128K training window, without additional training. It further generalizes to webpage-based multimodal needle retrieval, long-context vision-text compression, and long-video understanding without task-specific supervision. Overall, our study establishes a practical LongPT recipe and an empirical foundation for advancing long-context vision-language models.</p> + https://arxiv.org/abs/2605.13831 + Wed, 13 May 2026 00:00:00 +0000 + + + AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation + https://arxiv.org/abs/2605.13724 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13724.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchao Gu, Guian Fang, Yuxin Jiang, Weijia Mao, Song Han, Han Cai, Mike Zheng Shou</p><p><b>Upvotes:</b> 89</p><p><b>Summary:</b> Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling steps are allocated at test time, limiting their effectiveness for any-step video diffusion. This limitation arises because consistency distillation replaces the original probability-flow ODE trajectory with a consistency-sampling trajectory, weakening the desirable test-time scaling behavior of ODE sampling. To address this limitation, we introduce AnyFlow, the first any-step video diffusion distillation framework based on flow maps. Instead of distilling a model for only a few fixed sampling steps, AnyFlow optimizes the full ODE sampling trajectory. To this end, we shift the distillation target from endpoint consistency mapping (z_{t}rightarrow z_{0}) to flow-map transition learning (z_{t}rightarrow z_{r}) over arbitrary time intervals. We further propose Flow Map Backward Simulation, which decomposes a full Euler rollout into shortcut flow-map transitions, enabling efficient on-policy distillation that reduces test-time errors (i.e., discretization error in few-step sampling and exposure bias in causal generation). Extensive experiments across both bidirectional and causal architectures, at scales ranging from 1.3B to 14B parameters, demonstrate that AnyFlow achieves performance matches or surpasses consistency-based counterparts in the few-step regime, while scaling with sampling step budgets.</p> + https://arxiv.org/abs/2605.13724 + Wed, 13 May 2026 00:00:00 +0000 + + + Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling + https://arxiv.org/abs/2605.13301 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13301.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yafu Li, Runzhe Zhan, Haoran Zhang, Shunkai Zhang, Yizhuo Li, Zhilin Wang, Jiacheng Chen, Futing Wang, Xuyang Hu, Yuchen Fan, Bangjie Xu, Yucheng Su, Xinmiao Han, Chenxi Li, Haodi Lei, Yufeng Zhao, Zejin Lin, Qianjia Cheng, Tong Zhu, Xiaoye Qu, Ganqu Cui, Peng Ye, Yun Luo, Zhouchen Lin, Yu Qiao, Bowen Zhou, Ning Ding, Yu Cheng</p><p><b>Upvotes:</b> 140</p><p><b>Summary:</b> Recent progress in reasoning models has substantially advanced long-horizon mathematical and scientific problem solving, with several systems now reaching gold-medal-level performance on International Mathematical Olympiad (IMO) and International Physics Olympiad (IPhO) problems. In this paper, we introduce a simple and unified recipe for converting a post-trained reasoning backbone into a rigorous olympiad-level solver. The recipe first uses a reverse-perplexity curriculum for SFT to instill rigorous proof-search and self-checking behaviors, then scales these behaviors through a two-stage RL pipeline that progresses from RL with verifiable rewards to more delicate proof-level RL, and finally boosts solving performance with test-time scaling. Applying this recipe, we train a 30B-A3B backbone with SFT on around 340K sub-8K-token trajectories followed by 200 RL steps. The resulting model, SU-01, supports stable reasoning on difficult problems with trajectories exceeding 100K tokens, while achieving gold-medal-level performance on mathematical and physical olympiad competitions, including IMO 2025/USAMO 2026 and IPhO 2024/2025. It also demonstrates strong generalization of scientific reasoning to domains beyond mathematics and physics.</p> + https://arxiv.org/abs/2605.13301 + Wed, 13 May 2026 00:00:00 +0000 + + + MinT: Managed Infrastructure for Training and Serving Millions of LLMs + https://arxiv.org/abs/2605.13779 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13779.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mind Lab, Song Cao, Vic Cao, Andrew Chen, Kaijie Chen, Cleon Cheng, Steven Chiang, Kaixuan Fan, Hera Feng, Huan Feng, Arthur Fu, Jun Gao, Hongquan Gu, Aaron Guan, Nolan Ho, Mutian Hong, Hailee Hou, Peixuan Hua, Charles Huang, Miles Jiang, Nora Jiang, Yuyi Jiang, Qiuyu Jin, Fancy Kong, Andrew Lei, Kyrie Lei, Alexy Li, Lucian Li, Ray Li, Theo Li, Zhihui Li, Jiayi Lin, Kairus Liu, Kieran Liu, Logan Liu, Xiang Liu, Irvine Lu, Maeve Luo, Runze Lv, Pony Ma, Verity Niu, Anson Qiu, Vincent Wang, Rio Yang, Maxwell Yao, Carrie Ye, Regis Ye, Wenlin Ye, Josh Ying, Danney Zeng, Yuhan Zhan, Anya Zhang, Di Zhang, Ruijia Zhang, Sueky Zhang, Ya Zhang, Wei Zhao, Ada Zhou, Changhai Zhou, Yuhua Zhou, Xinyue Zhu, Murphy Zhuang</p><p><b>Upvotes:</b> 209</p><p><b>Summary:</b> We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained policies are produced over a small number of expensive base-model deployments. Instead of materializing each policy as a merged full checkpoint, MinT keeps the base model resident and moves exported LoRA adapter revisions through rollout, update, export, evaluation, serving, and rollback, hiding distributed training, serving, scheduling, and data movement behind a service interface. MinT scales this path along three axes. Scale Up extends LoRA RL to frontier-scale dense and MoE architectures, including MLA and DSA attention paths, with training and serving validated beyond 1T total parameters. Scale Down moves only the exported LoRA adapter, which can be under 1% of base-model size in rank-1 settings; adapter-only handoff reduces the measured step by 18.3x on a 4B dense model and 2.85x on a 30B MoE, while concurrent multi-policy GRPO shortens wall time by 1.77x and 1.45x without raising peak memory. Scale Out separates durable policy addressability from CPU/GPU working sets: a tensor-parallel deployment supports 10^6-scale addressable catalogs (measured single-engine sweeps through 100K) and thousand-adapter active waves at cluster scale, with cold loading treated as scheduled service work and packed MoE LoRA tensors improving live engine loading by 8.5-8.7x. MinT thus manages million-scale LoRA policy catalogs while training and serving selected adapter revisions over shared 1T-class base models.</p> + https://arxiv.org/abs/2605.13779 + Wed, 13 May 2026 00:00:00 +0000 + + + IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation + https://arxiv.org/abs/2605.14712 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14712.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijie Lian, Bin Yu, Xiaopeng Lin, Zhaolong Shen, Laurence Tianruo Yang, Yurun Jin, Haishan Liu, Changti Wu, Hang Yuan, Cong Huang, Kai Chen</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing frame-conditioned VLA policies infer each chunk from the current observation and instruction alone, so under partial observability they may resample different intents across adjacent replanning steps, leading to inter-chunk conflict and unstable execution. We introduce IntentVLA, a history-conditioned VLA framework that encodes recent visual observations into a compact short-horizon intent representation and uses it to condition chunk generation. We further introduce AliasBench, a 12-task ambiguity-aware benchmark on RoboTwin2 with matched training data and evaluation environments that isolate short-horizon observation aliasing. Across AliasBench, SimplerEnv, LIBERO, and RoboCasa, IntentVLA improves rollout stability and outperforms strong VLA baselines</p> + https://arxiv.org/abs/2605.14712 + Thu, 14 May 2026 00:00:00 +0000 + + + Orchard: An Open-Source Agentic Modeling Framework + https://arxiv.org/abs/2605.15040 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15040.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baolin Peng, Wenlin Yao, Qianhui Wu, Hao Cheng, Xiao Yu, Rui Yang, Tao Ge, Alessandrio Sordoni, Xingdi Yuan, Yelong Shen, Pengcheng He, Tong Zhang, Zhou Yu, Jianfeng Gao</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Agentic modeling aims to transform LLMs into autonomous agents capable of solving complex tasks through planning, reasoning, tool use, and multi-turn interaction with environments. Despite major investment, open research remains constrained by infrastructure and training gaps. Many high-performing systems rely on proprietary codebases, models, or services, while most open-source frameworks focus on orchestration and evaluation rather than scalable agent training. We present Orchard, an open-source framework for scalable agentic modeling. At its core is Orchard Env, a lightweight environment service providing reusable primitives for sandbox lifecycle management across task domains, agent harnesses, and pipeline stages. On top of Orchard Env, we build three agentic modeling recipes. Orchard-SWE targets coding agents. We distill 107K trajectories from MiniMax-M2.5 and Qwen3.5-397B, introduce credit-assignment SFT to learn from productive segments of unresolved trajectories, and apply Balanced Adaptive Rollout for RL. Starting from Qwen3-30B-A3B-Thinking, Orchard-SWE achieves 64.3% on SWE-bench Verified after SFT and 67.5% after SFT+RL, setting a new state of the art among open-source models of comparable size. Orchard-GUI trains a 4B vision-language computer-use agent using only 0.4K distilled trajectories and 2.2K open-ended tasks. It achieves 74.1%, 67.0%, and 64.0% success rates on WebVoyager, Online-Mind2Web, and DeepShop, respectively, making it the strongest open-source model while remaining competitive with proprietary systems. Orchard-Claw targets personal assistant agents. Trained with only 0.2K synthetic tasks, it achieves 59.6% pass@3 on Claw-Eval and 73.9% when paired with a stronger ZeroClaw harness. Collectively, these results show that a lightweight, open, harness-agnostic environment layer enables reusable agentic data, training recipes, and evaluations across domains.</p> + https://arxiv.org/abs/2605.15040 + Thu, 14 May 2026 00:00:00 +0000 + + + DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models + https://arxiv.org/abs/2605.15055 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quanhao Li, Junqiu Yu, Kaixun Jiang, Yujie Wei, Zhen Xing, Pandeng Li, Ruihang Chu, Shiwei Zhang, Yu Liu, Zuxuan Wu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint optimization suffers from cross-task interference and imbalance, while cascade RL is cumbersome and prone to catastrophic forgetting. We propose DiffusionOPD, a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD). DiffusionOPD first trains task-specific teachers independently, then distills their capabilities into a unified student along the student own rollout trajectories. This decouples single-task exploration from multi-task integration and avoids the optimization burden of solving all tasks jointly from scratch. Theoretically, we lift the OPD framework from discrete tokens to continuous-state Markov processes, deriving a closed-form per-step KL objective that unifies both stochastic SDE and deterministic ODE refinement via mean-matching. We formally and empirically demonstrate that this analytic gradient provides lower variance and better generality compared to conventional PPO-style policy gradients. Extensive experiments show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance, while achieving state-of-the-art results on all evaluated benchmarks.</p> + https://arxiv.org/abs/2605.15055 + Thu, 14 May 2026 00:00:00 +0000 + + + FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale + https://arxiv.org/abs/2605.14445 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14445.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runyuan He, Qiuyang Mang, Shang Zhou, Kaiyuan Liu, Hanchen Li, Huanzhi Mao, Qizheng Zhang, Zerui Li, Bo Peng, Lufeng Cheng, Tianfu Fu, Yichuan Wang, Wenhao Chai, Jingbo Shang, Alex Dimakis, Joseph E. Gonzalez, Alvin Cheung</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Many real-world coding challenges are open-ended and admit no known optimal solution. Yet, recent progress in LLM coding has focused on well-defined tasks such as feature implementation, bug fixing, and competitive programming. Open-ended coding remains a weak spot for LLMs, largely because open-ended training problems are scarce and expensive to construct. Our goal is to synthesize open-ended coding problems at scale to train stronger LLM coders. We introduce FrontierSmith, an automated system for iteratively evolving open-ended problems from existing closed-ended coding tasks. Starting from competitive programming problems, FrontierSmith generates candidate open-ended variants by changing the problems'goals, restricting outputs, and generalizing inputs. It then uses a quantitative idea divergence metric to select problems that elicit genuinely diverse approaches from different solvers. Agents then generate test cases and verifiers for the surviving candidates. On two open-ended coding benchmarks, training on our synthesized data yields substantial gains over the base models: Qwen3.5-9B improves by +8.82 score on FrontierCS and +306.36 (Elo-rating-based performance) on ALE-bench; Qwen3.5-27B improves by +12.12 and +309.12, respectively. The synthesized problems also make agents take more turns and use more tokens, similar to human-curated ones, suggesting that closed-ended seeds can be a practical starting point for long-horizon coding data.</p> + https://arxiv.org/abs/2605.14445 + Thu, 14 May 2026 00:00:00 +0000 + + + ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both + https://arxiv.org/abs/2605.15198 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15198.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyu Guo, Rain Liu, Xinyan Chen, Pheng-Ann Heng</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. A straightforward approach is to directly generate images via unified models during reasoning, but this is computationally expensive and architecturally non-trivial. Recent alternatives include agentic reasoning through code or tool calls, and latent reasoning with learnable hidden embeddings. However, agentic methods incur context-switching latency from external execution, while latent methods lack task generalization and are difficult to train with autoregressive parallelization. To combine their strengths while mitigating their limitations, we propose ATLAS, a framework in which a single discrete 'word', termed as a functional token, serves both as an agentic operation and a latent visual reasoning unit. Each functional token is associated with an internalized visual operation, yet requires no visual supervision and remains a standard token in the tokenizer vocabulary, which can be generated via next-token prediction. This design avoids verbose intermediate visual content generation, while preserving compatibility with the vanilla scalable SFT and RL training, without architectural or methodological modifications. To further address the sparsity of functional tokens during RL, we introduce Latent-Anchored GRPO (LA-GRPO), which stabilizes the training by anchoring functional tokens with a statically weighted auxiliary objective, providing stronger gradient updates. Extensive experiments and analyses demonstrate that ATLAS achieves superior performance on challenging benchmarks while maintaining clear interpretability. We hope ATLAS offers a new paradigm inspiring future visual reasoning research.</p> + https://arxiv.org/abs/2605.15198 + Thu, 14 May 2026 00:00:00 +0000 + + + VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction + https://arxiv.org/abs/2605.15186 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15186.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaixin Zhu, Yiwen Tang, Yifan Yang, Renrui Zhang, Bohan Zeng, Ziyu Guo, Ruichuan An, Zhou Liu, Qizhi Chen, Delin Qu, Jaehong Yoon, Wentao Zhang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> High-quality 3D scene reconstruction has recently advanced toward generalizable feed-forward architectures, enabling the generation of complex environments in a single forward pass. However, despite their strong performance in static scene perception, these models remain limited in responding to dynamic human instructions, which restricts their use in interactive applications. Existing editing methods typically rely on a 2D-lifting strategy, where individual views are edited independently and then lifted back into 3D space. This indirect pipeline often leads to blurry textures and inconsistent geometry, as 2D editors lack the spatial awareness required to preserve structure across viewpoints. To address these limitations, we propose VGGT-Edit, a feed-forward framework for text-conditioned native 3D scene editing. VGGT-Edit introduces depth-synchronized text injection to align semantic guidance with the backbone's spatial poses, ensuring stable instruction grounding. This semantic signal is then processed by a residual transformation head, which directly predicts 3D geometric displacements to deform the scene while preserving background stability. To ensure high-fidelity results, we supervise the framework with a multi-term objective function that enforces geometric accuracy and cross-view consistency. We also construct the DeltaScene Dataset, a large-scale dataset generated through an automated pipeline with 3D agreement filtering to ensure ground-truth quality. Experiments show that VGGT-Edit substantially outperforms 2D-lifting baselines, producing sharper object details, stronger multi-view consistency, and near-instant inference speed.</p> + https://arxiv.org/abs/2605.15186 + Thu, 14 May 2026 00:00:00 +0000 + + + Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video + https://arxiv.org/abs/2605.15182 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15182.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Wang, Tong He</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Camera-controlled video generation has made substantial progress, enabling generated videos to follow prescribed viewpoint trajectories. However, existing methods usually learn camera-specific conditioning through camera encoders, control branches, or attention and positional-encoding modifications, which often require post-training on large-scale camera-annotated videos. Training-free alternatives avoid such post-training, but often shift the cost to test-time optimization or extra denoising-time guidance. We propose Warp-as-History, a simple interface that turns camera-induced warps into camera-warped pseudo-history with target-frame positional alignment and visible-token selection. Given a target camera trajectory, we construct camera-warped pseudo-history from past observations and feed it through the model's visual-history pathway. Crucially, we align its positional encoding with the target frames being denoised and remove warped-history tokens without valid source observations. Without any training, architectural modification, or test-time optimization, this interface reveals a non-trivial zero-shot capability of a frozen video generation model to follow camera trajectories. Moreover, lightweight offline LoRA finetuning on only one camera-annotated video further improves this capability and generalizes to unseen videos, improving camera adherence, visual quality, and motion dynamics without test-time optimization or target-video adaptation. Extensive experiments on diverse datasets confirm the effectiveness of our method.</p> + https://arxiv.org/abs/2605.15182 + Thu, 14 May 2026 00:00:00 +0000 + + + Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems + https://arxiv.org/abs/2605.14892 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14892.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shihao Qi, Jie Ma, Rui Xing, Wei Guo, Xiao Huang, Zhitao Gao, Jianhao Deng, Jun Liu, Lingling Zhang, Bifan Wei, Boqian Yang, Pinghui Wang, Jianwen Sun, Jing Tao, Yaqiang Wu, Hui Liu, Yu Yao, Tongliang Liu</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> LLM-based autonomous agents have demonstrated strong capabilities in reasoning, planning, and tool use, yet remain limited when tasks require sustained coordination across roles, tools, and environments. Multi-agent systems address this through structured collaboration among specialized agents, but tighter coordination also amplifies a less explored risk: errors can propagate across agents and interaction rounds, producing failures that are difficult to diagnose and rarely translate into structural self-improvement. Existing surveys cover individual agent capabilities, multi-agent collaboration, or agent self-evolution separately, leaving the causal dependencies among them unexamined. This survey provides a unified review organized around four causally linked stages, which we term the LIFE progression: Lay the capability foundation, Integrate agents through collaboration, Find faults through attribution, and Evolve through autonomous self-improvement. For each stage, we provide systematic taxonomies and formally characterize the dependencies between adjacent stages, revealing how each stage both depends on and constrains the next. Beyond synthesizing existing work, we identify open challenges at stage boundaries and propose a cross-stage research agenda for closed-loop multi-agent systems capable of continuously diagnosing failures, reorganizing structures, and refining agent behaviors, extending current coordination frameworks toward more self-organizing forms of collective intelligence. By bridging these previously fragmented research threads, this survey aims to offer both a systematic reference and a conceptual roadmap toward autonomous, self-improving multi-agent intelligence.</p> + https://arxiv.org/abs/2605.14892 + Thu, 14 May 2026 00:00:00 +0000 + + + Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning + https://arxiv.org/abs/2605.14386 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14386.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taebong Kim, Youngsik Hong, Minsik Kim, Sunyoung Choi, Jaewon Jang, Junghoon Shin, Minseo Kim</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> We present Darwin Family, a framework for training-free evolutionary merging of large language models via gradient-free weight-space recombination. We ask whether frontier-level reasoning performance can be improved without additional training, by reorganizing latent capabilities already encoded in existing checkpoints. Darwin introduces three key ideas: (i) a 14-dimensional adaptive merge genome enabling fine-grained component- and block-level recombination; (ii) MRI-Trust Fusion, which adaptively balances diagnostic layer-importance signals with evolutionary search through a learnable trust parameter; and (iii) an Architecture Mapper that enables cross-architecture breeding between heterogeneous model families. Empirically, the flagship Darwin-27B-Opus achieves 86.9% on GPQA Diamond, ranking #6 among 1,252 evaluated models, and outperforming its fully trained foundation model without any gradient-based training. Across scales from 4B to 35B parameters, Darwin models consistently improve over their parents, support recursive multi-generation evolution, and enable a training-free evolutionary merge that combines Transformer- and Mamba-based components. Together, the Darwin Family demonstrates that diagnostic-guided evolutionary merging is a practical and reproducible alternative to costly post-training pipelines for reasoning-centric language models.</p> + https://arxiv.org/abs/2605.14386 + Thu, 14 May 2026 00:00:00 +0000 + + + MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory + https://arxiv.org/abs/2605.15128 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15128.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minghao Guo, Qingyue Jiao, Zeru Shi, Yihao Quan, Boxuan Zhang, Danrui Li, Liwei Che, Wujiang Xu, Shilong Liu, Zirui Liu, Mubbasir Kapadia, Vladimir Pavlovic, Jiang Liu, Mengdi Wang, Yiyu Shi, Dimitris N. Metaxas, Ruixiang Tang</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only captions or textual traces, allowing answers to be inferred without preserving the fine-grained visual evidence. Meanwhile, harder cases that require reasoning over changing visual states are largely absent. Therefore, we introduce MemEye, a framework that evaluates memory capabilities from two dimensions: one measures the granularity of decisive visual evidence (from scene-level to pixel-level evidence), and the other measures how retrieved evidence must be used (from single evidence to evolutionary synthesis). Under this framework, we construct a new benchmark across 8 life-scenario tasks, with ablation-driven validation gates for assessing answerability, shortcut resistance, visual necessity, and reasoning structure. By evaluating 13 memory methods across 4 VLM backbones, we show that current architectures still struggle to preserve fine-grained visual details and reason about state changes over time. Our findings show that long-term multimodal memory depends on evidence routing, temporal tracking, and detail extraction.</p> + https://arxiv.org/abs/2605.15128 + Thu, 14 May 2026 00:00:00 +0000 + + + SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer + https://arxiv.org/abs/2605.15178 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15178.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyi Zhu, Haozhe Liu, Yuyang Zhao, Tian Ye, Junsong Chen, Jincheng Yu, Tong He, Song Han, Enze Xie</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> We introduce SANA-WM, an efficient 2.6B-parameter open-source world model natively trained for one-minute generation, synthesizing high-fidelity, 720p, minute-scale videos with precise camera control. SANA-WM achieves visual quality comparable to large-scale industrial baselines such as LingBot-World and HY-WorldPlay, while significantly improving efficiency. Four core designs drive our architecture: (1) Hybrid Linear Attention combines frame-wise Gated DeltaNet (GDN) with softmax attention for memory-efficient long-context modeling. (2) Dual-Branch Camera Control ensures precise 6-DoF trajectory adherence. (3) Two-Stage Generation Pipeline applies a long-video refiner to stage-1 outputs, improving quality and consistency across sequences. (4) Robust Annotation Pipeline extracts accurate metric-scale 6-DoF camera poses from public videos to yield high-quality, spatiotemporally consistent action labels. Driven by these designs, SANA-WMdemonstrates remarkable efficiency across data, training compute, and inference hardware: it uses only sim213K public video clips with metric-scale pose supervision, completes training in 15 days on 64 H100s, and generates each 60s clip on a single GPU; its distilled variant can be deployed on a single RTX 5090 with NVFP4 quantization to denoise a 60s 720p clip in 34s. On our one-minute world-model benchmark, SANA-WM demonstrates stronger action-following accuracy than prior open-source baselines and achieves comparable visual quality at 36times higher throughput for scalable world modeling.</p> + https://arxiv.org/abs/2605.15178 + Thu, 14 May 2026 00:00:00 +0000 + + + MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models + https://arxiv.org/abs/2605.14906 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14906.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiyu Ren, Zhaowei Wang, Yiming Du, Zhongwei Xie, Chi Liu, Xinlin Yang, Haoyue Feng, Wenjun Pan, Tianshi Zheng, Baixuan Xu, Zhengnan Li, Yangqiu Song, Ginny Wong, Simon See</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capability: long-context LVLMs and memory-augmented agents. However, no existing benchmark conducts a systematic comparison of the two on questions that genuinely require multimodal evidence. To close this gap, we introduce MEMLENS, a comprehensive benchmark for memory in multimodal multi-session conversations, comprising 789 questions across five memory abilities (information extraction, multi-session reasoning, temporal reasoning, knowledge update, and answer refusal) at four standard context lengths (32K-256K tokens) under a cross-modal token-counting scheme. An image-ablation study confirms that solving MEMLENS requires visual evidence: removing evidence images drops two frontier LVLMs below 2% accuracy on the 80.4% of questions whose evidence includes images. Evaluating 27 LVLMs and 7 memory-augmented agents, we find that long-context LVLMs achieve high short-context accuracy through direct visual grounding but degrade as conversations grow, whereas memory agents are length-stable but lose visual fidelity under storage-time compression. Multi-session reasoning caps most systems below 30%, and neither approach alone solves the task. These results motivate hybrid architectures that combine long-context attention with structured multimodal retrieval. Our code is available at https://github.com/xrenaf/MEMLENS.</p> + https://arxiv.org/abs/2605.14906 + Thu, 14 May 2026 00:00:00 +0000 + + + Self-Distilled Agentic Reinforcement Learning + https://arxiv.org/abs/2605.15155 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15155.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxi Lu, Zhiyuan Yao, Zhuowen Han, Zi-Han Wang, Jinyang Wu, Qi Gu, Xunliang Cai, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements RL by introducing dense token-level guidance from a teacher branch augmented with privileged context. However, transferring OPSD to multi-turn agents proves problematic: compounding multi-turn instability destabilizes supervision, while skill-conditioned privileged guidance requires asymmetric treatment for negative teacher rejections may arise from imperfect skills retrieval or utilization. We introduce SDAR (Self-Distilled Agentic Reinforcement Learning), which treats OPSD as a gated auxiliary objective while keeping RL as the primary optimization backbone. SDAR maps detached token-level signals into a sigmoid gate, strengthening distillation on teacher-endorsed positive-gap tokens and softly attenuating negative teacher rejections. Across the Qwen2.5 and Qwen3 families on ALFWorld, WebShop, and Search-QA, SDAR substantially improves over GRPO (+9.4% on ALFWorld, +7.0% on Search-QA, +10.2% on WebShop-Acc), avoids the instability of naive GRPO+OPSD, and consistently outperforms hybrid RL--OPSD baselines across model scales.</p> + https://arxiv.org/abs/2605.15155 + Thu, 14 May 2026 00:00:00 +0000 + + + Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation + https://arxiv.org/abs/2605.15141 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15141.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Min Zhao, Hongzhou Zhu, Kaiwen Zheng, Zihan Zhou, Bokai Yan, Xinyuan Li, Xiao Yang, Chongxuan Li, Jun Zhu</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong results in the chunk-wise 4-step regime by distilling bidirectional base models into few-step AR students, but they remain limited by coarse response granularity and non-negligible sampling latency. In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps. In this regime, we identify the initialization of a few-step AR student as the key bottleneck: existing strategies are either target-misaligned, incapable of few-step generation, or too costly to scale. We propose Causal Forcing++, a principled and scalable pipeline that uses causal consistency distillation (causal CD) for few-step AR initialization. The core idea is that causal CD learns the same AR-conditional flow map as causal ODE distillation, but obtains supervision from a single online teacher ODE step between adjacent timesteps, avoiding the need to precompute and store full PF-ODE trajectories. This makes the initialization both more efficient and easier to optimize. The resulting pipeline, \ours, surpasses the SOTA 4-step chunk-wise Causal Forcing under the \textbf{frame-wise 2-step setting} by 0.1 in VBench Total, 0.3 in VBench Quality, and 0.335 in VisionReward, while reducing first-frame latency by 50\% and Stage 2 training cost by sim4times. We further extend the pipeline to action-conditioned world model generation in the spirit of Genie3. Project Page: https://github.com/thu-ml/Causal-Forcing and https://github.com/shengshu-ai/minWM .</p> + https://arxiv.org/abs/2605.15141 + Thu, 14 May 2026 00:00:00 +0000