Explore the Frontier of Global Academia

01.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14409

Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack

Authors:

He Zhang↗Lingzhu Xiang↗Haitao Lin↗Zeyu Huang↗Minghui Wang↗Dingyan Zhong↗Yubo Dong↗Yihao Wu↗Yongming Rao↗Dongsheng Zhang↗Wanjia He↗Ling Chen↗…

arXiv:2606.14409v1 Announce Type: cross Abstract: In this report, we present Hy-Embodied-0.5-VLA, abbreviated as HyVLA-0.5, an end-to-end system that spans the full robot learning stack: data collection, model design, continued pre-training and supervised fine-tuning, RL post-training, and real-world deployment. Each component serves a distinct role in this stack.

Read & Discuss → View Source →

02.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13473

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

Authors:

Jiacheng Chen↗Xinyu Zhang↗Shunkai Zhang↗Yanmohan Wang↗Lin Li↗Tiancheng Qin↗Qin Wang↗Zhengmao Zhu↗Tianle Li↗Jingyang Li↗Zehan Li↗Binyang Jiang↗…

We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities – proof generation, proof verification, and critique-conditioned proof repair – using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.

Read & Discuss → View Source →

03.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18309

SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector

Authors:

Jingyuan Zhang↗Yucheng Bai↗Peixi Wen↗Zhehao Huang↗Zhengbao He↗Hanling Tian↗Xinwen Cheng↗Haiyin Ran↗Xiaolin Huang↗

arXiv:2606.18309v1 Announce Type: cross Abstract: Large Language Model (LLM) unlearning aims to remove undesirable knowledge or behaviors while preserving retained capabilities. Current unlearning methods all involve a trade-off between unlearning and retention. We have found that the retention activation bias can also be used to quantify the damage an unlearning method inflicts on retention, without considering the specific implementation of the unlearning process. This allows us to restore retention performance for any unlearning method using a post-hoc approach. Therefore, we propose a complementary post-hoc setting to sanitize the final update vector without rerunning the original unlearning pipeline. In this setting, we design SAGE, Spectral Activation-GEometry Sanitization, a source-agnostic correction for final unlearning updates. SAGE collects real module inputs from a small retain proxy, extracts their dominant activation geometry, and solves a source-anchored optimization objective in closed form, which suppresses update components aligned with high-energy retained directions while preserving the source method's forgetting carrier. Across multiple unlearning methods, model scales, and benchmarks, SAGE consistently relieves the retain-forget trade-off, identifying post-hoc sanitization of final vectors as a practical and underexplored axis for machine unlearning.

Read & Discuss → View Source →

04.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.03489

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs

Authors:

Wenqi Chen↗Ziyan Zhang↗Bin Wang↗Lin Liu↗Hengheng Zhang↗Zhengsu Chen↗

arXiv:2606.03489v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), typically apply coarse-grained optimization at the sequence level. This approach often fails to address the localized nature of security flaws, where a single incorrect token choice can compromise an entire program. To bridge this gap, we introduce Tree-like Self-Play (TSP), a framework that reframes secure code generation as a fine-grained sequential decision process. Unlike standard methods that blindly maximize likelihood, TSP constructs a decision tree where the model explores branching trajectories–generating both secure "golden paths" and vulnerable variants. By treating code generation as a self-play game, the model learns to strictly discriminate against its own localized errors. This provides a dense, on-policy learning signal that forces self-correction precisely at the critical decision nodes where vulnerabilities typically emerge. Our experiments demonstrate that TSP fundamentally enhances model reliability. In Python security benchmarks, TSP boosts CodeLlama-7B's pass rate (SPR@1) to 75.8%, significantly outperforming SFT (57.0%) and unstructured self-play baselines. Crucially, TSP induces robust out-of-distribution generalization: the model not only reduces vulnerabilities in unseen categories (CWEs) by 24.5% but also successfully transfers security principles learned from C/C++ to diverse languages, including Python, Go, and JavaScript. This suggests that TSP does not merely memorize patches, but internalizes abstract, language-agnostic security logic.

Read & Discuss → View Source →

05.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2602.07840

SAGE: Scalable AI Governance & Evaluation

Authors:

Benjamin Le↗Xueying Lu↗Nick Stern↗Wenqiong Liu↗Igor Lapchuk↗Xiang Li↗Baofen Zheng↗Kevin Rosenberg↗Jiewen Huang↗Zhe Zhang↗Abraham Cabangbang↗Satej Milind Wagle↗…

arXiv:2602.07840v4 Announce Type: replace-cross Abstract: Evaluating relevance in large-scale search systems is fundamentally constrained by the governance gap between nuanced, resource-constrained human oversight and the high-throughput requirements of production systems. While traditional approaches rely on engagement proxies or sparse manual review, these methods often fail to capture the full scope of high-impact relevance failures. We present SAGE (Scalable AI Governance \& Evaluation), a framework that operationalizes high-quality human product judgment as a scalable evaluation signal. At the core of SAGE is a bidirectional calibration loop where natural-language Policy, curated Precedent, and an LLM Surrogate Judge co-evolve. SAGE systematically resolves semantic ambiguities and misalignments, transforming subjective relevance judgment into an executable, multi-dimensional rubric with near human-level agreement. To bridge the gap between frontier model reasoning and industrial-scale inference, we apply teacher-student distillation to transfer high-fidelity judgments into compact student surrogates at 92$\times$ lower cost. Deployed within LinkedIn Search ecosystems, SAGE guided model iteration through simulation-driven development, distilling policy-aligned models for online serving and enabling rapid offline evaluation. In production, it powered policy oversight that measured ramped model variants and detected regressions invisible to engagement metrics. Collectively, these drove a 0.25\% lift in LinkedIn daily active users.

Read & Discuss → View Source →

06.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19755

SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling

Authors:

Haotian Xu↗Zeyang Zhang↗Linbao Li↗Huadi Zheng↗Yu Li↗Cheng Zhuo↗

arXiv:2606.19755v1 Announce Type: cross Abstract: Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees. Existing safety defenses are largely incompatible with speculative inference: they either introduce additional computation or disrupt the draft-verify mechanism, negating acceleration benefits. This reveals a fundamental incompatibility between current safety methods and speculative decoding. We propose SafeSpec, a safety-aware speculative inference framework that integrates risk estimation directly into the verification process. SafeSpec attaches a lightweight latent safety head to the target model to jointly evaluate semantic validity and safety in a single forward pass. When unsafe generations are detected, SafeSpec applies rollback and safety-guided reflective multi-sampling to recover safe continuations rather than terminating generation. We model jailbreak attacks as distributional shifts over generative trajectories, where adversarial prompts increase the probability of harmful continuations without eliminating safe ones. Under this model, SafeSpec performs risk-aware trajectory recovery within the speculative decoding process. Across multiple models and adversarial benchmarks, SafeSpec achieves a substantially improved safety-efficiency trade-off. On Qwen3-32B, SafeSpec reduces attack success rates by 15% while preserving a 2.06x inference speedup on benign workloads, demonstrating that speculative acceleration and inference-time safety can be jointly optimized.

Read & Discuss → View Source →

07.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2603.11863

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

Authors:

Zi-Han Wang↗Lam Nguyen↗Zhengyang Zhao↗Mengyue Yang↗Chengwei Qin↗Yujiu Yang↗Linyi Yang↗

The saturation of high-quality pre-training data has shifted research focus toward evolutionary systems capable of continuously generating novel artifacts, leading to the success of AlphaEvolve. However, the progress of such systems is hindered by the lack of rigorous, quantitative evaluation. To tackle this challenge, we introduce CreativeBench, a benchmark for evaluating machine creativity in code generation, grounded in a classical cognitive framework. Comprising two subsets – CreativeBench-Combo and CreativeBench-Explore – the benchmark targets combinatorial and exploratory creativity through an automated pipeline utilizing reverse engineering and self-play. By leveraging executable code, CreativeBench objectively distinguishes creativity from hallucination via a unified metric defined as the product of quality and novelty. Our analysis of state-of-the-art models reveals distinct behaviors: (1) scaling significantly improves combinatorial creativity but yields diminishing returns for exploration; (2) larger models exhibit ``convergence-by-scaling,'' becoming more correct but less divergent; and (3) reasoning capabilities primarily benefit constrained exploration rather than combination. Finally, we propose EvoRePE, a plug-and-play inference-time steering strategy that internalizes evolutionary search patterns to consistently enhance machine creativity.

Read & Discuss → View Source →

08.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11637

TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation

Authors:

Kailin Lyu↗Di Wu↗Pengwei Zhang↗Yuhang Zheng↗Yingxin Lai↗Long Xiao↗Kangyi Wu↗Pengna Li↗Chen Gao↗Lianyu Hu↗Xiaobin Hu↗Jie Hao↗…

arXiv:2606.11637v1 Announce Type: new Abstract: Touch is a key modality for embodied agents to understand the physical world. Although recent work has incorporated tactile signals into language systems for tactile commonsense reasoning, scaling such systems to realistic open-world settings remains challenging due to two key bottlenecks: (1) current tactile reasoning datasets remain limited in format and scale, providing insufficient supervision for reasoning from tactile observations to physical commonsense and hindering the learning of transferable tactile commonsense; (2) Tactile signals are inherently redundant and action-specific, yet existing methods often overlook these properties, resulting in inefficient representations with limited semantic expressiveness. To address these limitations, we propose TouchThinker, a tactile-language framework that scales tactile commonsense reasoning to the open world from both data and representation perspectives. First, we construct TouchThinker-1M, a million-scale, multi-source tactile reasoning dataset covering 415 objects, 8 scenarios, and 7 sensor types, providing a solid data foundation for open-world generalization. We further introduce TouchThinker-Bench, an open-world benchmark with more realistic and diverse tasks. Then, we propose action-aware modeling mechanism to improve tactile representation efficiency and enable efficient reasoning. Experimental results demonstrate that TouchThinker achieves competitive performance against state-of-the-art models across multiple datasets. Our code and dataset will be made available at: https://github.com/lvkailin0118/TouchThinker.

Read & Discuss → View Source →

09.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12594

Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation

Authors:

Joshua Ong Jun Leang↗Zheng Zhao↗Mihaela C\u{a}t\u{a}lina Stoian↗Qiyuan Xu↗Haonan Li↗Wenda Li↗Shay B. Cohen↗Eleonora Giunchiglia↗

arXiv:2606.12594v1 Announce Type: new Abstract: Modern Lean theorem provers achieve strong performance only with substantial training and inference compute, driven in part by scarce verified proof data and the long reasoning traces of formal proof search, making both supervised fine-tuning (SFT) and sampling expensive. We introduce Pythagoras-Prover, a compute-efficient open-source family of Lean theorem provers built for practical compute budgets. The family spans two generation paradigms: autoregressive models at 4B and 32B parameters, and a first proof-of-concept diffusion-based prover (4B) that iteratively refines Lean proofs at inference time. For training efficiency, we build a Lean-verified corpus stratified into easy, medium, and hard problems for curriculum SFT, so models acquire proof skills progressively from shorter, simpler proofs to longer, harder ones. During SFT, a dynamic proof-reasoning filtering scheme preserves informative proof traces while keeping each instance within an 8k-token context budget. We also introduce Augmented Lean Formalisation (ALF), which expands scarce verified corpora into variants of formal statements, populated via self-distillation for extra training signal without formally verifying every mutated instance. By perturbing known problems while preserving their formal character, ALF reduces reliance on any statement's surface form. Empirically, Pythagoras-Prover-4B surpasses DeepSeek-Prover-V2-671B at pass@32 on MiniF2F-Test (86.1% vs 82.4%) with ~167x fewer parameters, while Pythagoras-Prover-32B sets the open-source state of the art at 93.0% on MiniF2F-Test and solves 93 of 672 PutnamBench problems. We release MiniF2F-ALF, an ALF-mutated contamination-sensitive benchmark on which every evaluated model loses accuracy; here our 32B remains strongest and our 4B matches the prior state of the art, Goedel-Prover-V2-32B.

Read & Discuss → View Source →

10.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2604.22748

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

Authors:

Meng Chu↗Xuan Billy Zhang↗Kevin Qinghong Lin↗Lingdong Kong↗Jize Zhang↗Teng Tu↗Weijian Ma↗Ziqi Huang↗Senqiao Yang↗Wei Huang↗Yeying Jin↗Zhefan Rao↗…

arXiv:2604.22748v3 Announce Type: replace Abstract: As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that manipulate objects, navigate software, coordinate with others, or design experiments require predictive environment models, yet the term world model carries different meanings across research communities. We introduce a "levels x laws" taxonomy organized along two axes. The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence. The second identifies four governing-law regimes: physical, digital, social, and scientific. These regimes determine what constraints a world model must satisfy and where it is most likely to fail. Using this framework, we synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery. We analyze methods, failure modes, and evaluation practices across level-regime pairs, propose decision-centric evaluation principles and a minimal reproducible evaluation package, and outline architectural guidance, open problems, and governance challenges. The resulting roadmap connects previously isolated communities and charts a path from passive next-step prediction toward world models that can simulate, and ultimately reshape, the environments in which agents operate. Code and resources are available at: https://github.com/matrix-agent/awesome-agentic-world-modeling.

Read & Discuss → View Source →

11.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2602.12670

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Authors:

Xiangyi Li↗Yimin Liu↗Wenbo Chen↗Bingran You↗Zonglin Di↗Yifeng He↗Shenghan Zheng↗Kyoung Whan Choe↗Jiankai Sun↗Shuyi Wang↗Chujun Tao↗Binxu Li↗…

arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

Read & Discuss → View Source →

12.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.18089

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

Authors:

Lingjing Kong↗Xin Liu↗Guangyi Chen↗Martin Q. Ma↗Xiangchen Song↗Yuekai Sun↗Mikhail Yurochkin↗Taylor W. Killian↗Ruslan Salakhutdinov↗Kun Zhang↗Eric P. Xing↗Zhengzhong Liu↗…

arXiv:2606.18089v1 Announce Type: new Abstract: Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into robust reasoners. We argue that this combined success is driven by compositional generalization, which we formalize through a hierarchical latent selection model. In this framework, reasoning traces are generated by a cascade of discrete latent selection variables corresponding to reusable atomic modules, including both skills (local operations) and routing mechanisms (how intermediate information is selected, reused, and composed). Within this model, we theoretically show that SFT and RL play asymmetric, complementary roles: SFT supplies the raw module materials in compositional traces, and RL decomposes those traces to identify the latent atomic modules and enable compositional generalization. We design controlled experiments to validate this theory. Our results demonstrate that RL can extract atomic modules from compound traces supplied by SFT and recombine them to solve new configurations. Moreover, we find that training on compound traces yields stronger generalization than training on isolated atomic modules. Finally, we investigate the relationship between SFT and RL data and identify an effective protocol in which SFT ensures coverage of all atomic modules through compositional traces, while RL focuses on novel compositions outside the SFT support to drive exploration.

Read & Discuss → View Source →

13.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17256

Contrastive Action-Image Pre-training for Visuomotor Control

Authors:

Yuvan Sharma↗Dantong Niu↗Anirudh Pai↗Zekai Wang↗Zhuoyang Liu↗Baifeng Shi↗Stefano Saravalle↗Boning Shao↗Ruijie Zheng↗Jing Wang↗Konstantinos Kallidromitis↗Yusuke Kato↗…

Existing vision encoders for robotics face a fundamental bottleneck: robotic datasets lack the scale necessary for large-scale pre-training. Prior work circumvents this data scarcity by turning to internet-scale image and language data or egocentric human video. While these models show promise, neither paradigm learns from paired vision and action data, which downstream visuomotor control policies require. However, robot trajectories, the most direct source of this paired signal, are not available at pre-training scale, motivating us to extract action signals from abundant human video instead. To this end, we introduce CAIP (Contrastive Action-Image Pre-training), a vision encoder that treats human hand poses from large-scale egocentric video as a proxy for end-effector actions. By extracting 3D hand keypoints, a representation that aligns naturally with downstream robot action spaces, CAIP learns a unified action-image representation through a contrastive objective. Leveraging 32,041 hours of egocentric human video and only 88 hours of robotic manipulation data, CAIP outperforms state-of-the-art vision encoders including DINOv2, SigLIP, MVP, and R3M. Evaluated on a challenging real-world dexterous manipulation setup using Dexmate Vega and Sharpa Wave hands, CAIP yields performance gains of more than 30% on tasks involving folding, pouring, and fine-grained manipulation. Our results show that our method of contrastive action-centric pre-training yields a scalable path to achieving robust visual representations better suited for physical interaction.

Read & Discuss → View Source →

14.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2404.09790

NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Results

Authors:

Zheng Chen↗Zongwei Wu↗Eduard Zamfir↗Kai Zhang↗Yulun Zhang↗Radu Timofte↗Xiaokang Yang↗Hongyuan Yu↗Cheng Wan↗Yuxin Hong↗Zhijuan Huang↗Yajun Zou↗…

This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained. The challenge involves generating corresponding high-resolution (HR) images, magnified by a factor of four, from low-resolution (LR) inputs using prior information. The LR images originate from bicubic downsampling degradation. The aim of the challenge is to obtain designs/solutions with the most advanced SR performance, with no constraints on computational resources (e.g., model size and FLOPs) or training data. The track of this challenge assesses performance with the PSNR metric on the DIV2K testing dataset. The competition attracted 199 registrants, with 20 teams submitting valid entries. This collective endeavour not only pushes the boundaries of performance in single-image SR but also offers a comprehensive overview of current trends in this field.

Read & Discuss → View Source →

15.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17557

Universal Image Restoration via Internalized Chain-of-Thought Reasoning

Authors:

Yu Guo↗Zhengru Fang↗Shengfeng He↗Senkang Hu↗Yihang Tao↗Phone Lin↗Yuguang Fang↗

Image restoration seeks to recover high-quality images from degraded inputs but becomes highly ill-posed under complex, mixed degradations. While unified all-in-one models are common, their performance declines as degradation complexity increases. Recent works adopt Chain-of-Thought (CoT) reasoning for multi-round restoration using specialized modules. However, this approach faces two key limitations: (i) increased computational cost due to multi-step processing, and (ii) weak modeling of interactions between degradations during stepwise inference. We introduce CoTIR, a universal image restoration framework that internalizes CoT reasoning within a single model. Concretely, we view image restoration as a specialized subtask of image editing, which implies that a large-scale pre-trained editing model provides a more favorable optimization starting point. Building on this, we fine-tune the model for restoration and further encode structured CoT-style reasoning into the learning objective via a differentiable formulation inspired by Lagrangian optimization, enabling holistic restoration without chaining specialized restorers. To facilitate training and evaluation, we further present CoTIR-Bench, a large-scale benchmark comprising 5.2 million samples with CoT-style reasoning traces. Extensive experiments on CoTIR-Bench and broad real composite degradation scenes show that CoTIR achieves stronger perceptual quality and more competitive fidelity than both all-in-one models and multi-round restoration methods. The source code is available at https://github.com/gy65896/CoTIR.

Read & Discuss → View Source →

16.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.00288

Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture

Authors:

Hai Lin↗Hoilam Pao↗Shaoxiong Zhan↗Hai-Tao Zheng↗

arXiv:2606.00288v2 Announce Type: replace Abstract: Large language models are undergoing a transition from model technology to system technology. Engineering challenges like cache reuse, context capacity, agent scheduling, and permission control resemble classical computer systems problems. This raises a question: if we treat the LLM as a CPU, KV cache as processor cache, context window as main memory, and agent framework as an operating system, can decades of computer architecture wisdom guide next generation model native systems? This paper pursues this analogy as a visionary survey. We map computer architecture concepts onto the emerging model native stack, survey literature across LLM as OS, memory management, agent frameworks, tool protocols, multi agent coordination, cognitive architectures, and safety governance, finding that each addresses a different layer without a unifying model. We propose the Intelligent Computing Architecture (ICA): six functional layers with interface contracts and design axioms. We resolve the tension over whether the LLM resembles a CPU or OS via a dual plane architecture a probabilistic execution plane (what can be computed) and a deterministic control plane (what should be computed), with every layer passing through as a graded crossover. We propose three Amdahl style design heuristics Semantic Locality, Context Budget, and Agent Speedup as organizing back of envelope models, illustrate their parameter ranges with published data, and identify predictive validation as the principal open task. We articulate analogy boundaries, note differences between silicon and model era architectures, and propose a research roadmap. This is a conceptual and survey contribution with no new experimental results.

Read & Discuss → View Source →

17.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12736

Benchmarking AI Agents for Addressing Scientific Challenges Across Scales

Authors:

Tianyu Liu↗Allen Xin Wang↗Antonia Panescu↗Lisa Xinyi Chen↗Wenxin Long↗Xinyu Wei↗Yueqian Jing↗Ziyao Zeng↗Jihang Chen↗Sihan Jiang↗Ziqing Wang↗Siyi Gu↗…

arXiv:2606.12736v1 Announce Type: new Abstract: AI agents are increasingly being developed to accelerate scientific discovery, yet their practical capabilities in real research settings remain poorly understood. Existing benchmarks for AI agents rarely capture the complexity, heterogeneity, and extended reasoning required by scientific work, whereas benchmarks for scientific tasks often reduce research to static, direct problems and provide limited support for interactive evaluation. Here, we introduce SciAgentArena, a systematic benchmark for evaluating AI agents in real-world scientific research scenarios drawn from emerging needs across multiple domains. SciAgentArena comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents. Using this benchmark, we find that current agents can contribute effectively to well-specified data-analysis workflows, particularly when the task structure and evaluation criteria are clear. However, their performance remains uneven across scientific contexts: agents struggle to generate genuinely novel insights, sustain self-directed exploration, and formulate robust solutions for open-ended research questions. We further characterize common failure modes across agents and identify opportunities for improving their reliability, autonomy, and scientific reasoning. Together, SciAgentArena provides a practical framework for measuring progress in AI agents for science and for guiding the design of future agents capable of addressing complex scientific challenges. Full codes, tasks, and datasets can be accessed via this link: https://sciagentarena.github.io/.

Read & Discuss → View Source →

18.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2511.15645

FDIO: Frequency Decomposed Inertial Odometry

Authors:

Shanshan Zhang↗Liqin Wu↗Wenying Cao↗Lingxiang Zheng↗Yu Yang↗

Pedestrian inertial odometry (PIO) estimates autonomous pedestrian motion using only acceleration and angular velocity measurements collected by an inertial measurement unit (IMU), making it highly valuable for consumer level localization applications. However, under a dual device acquisition setting, IMU signals collected by a freely carried mobile device are inherently composite signals in which the global motion of the human torso is coupled with perturbations induced by local limb motion. This coupling makes accurate human motion modeling more challenging. To address this issue, this paper proposes frequency decomposed inertial odometry (FDIO). The proposed method first decomposes input IMU signals into low frequency and high frequency components using a Laplacian pyramid. It then adopts a Mamba module to model long range motion information from the low frequency component and uses a multi scale convolution module to extract fine grained local dynamic features from the high frequency component. Experiments on five public PIO datasets show that FDIO achieves an average absolute trajectory error of 3.221~m and an average relative trajectory error of 2.550~m, reducing the errors by 33.3\% and 16.7\% compared with the RoNIN ResNet baseline, respectively. These results validate the effectiveness of the proposed frequency decomposition strategy. To the best of our knowledge, this work is among the first efforts to introduce Mamba and a frequency decomposition architecture into inertial odometry.

Read & Discuss → View Source →

19.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11042

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

Authors:

Liya Zhu↗Jingzhe Ding↗Jian Zhang↗Jianbo Xue↗Shihao Liang↗Ge Zhang↗Yi Zhu↗Duju Zeng↗Xiang Gao↗Qingshui Gu↗Mailun Gao↗Huimin Che↗…

arXiv:2606.11042v2 Announce Type: replace Abstract: Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. Current GUI benchmarks still predominantly focus on general-purpose software, relatively simple applications, and short-horizon tasks, leaving it largely unknown whether modern agents can follow user instructions to autonomously operate domain-specific professional software and accomplish economically valuable work in an end-to-end manner. To bridge this gap, we introduce Workflow-GYM, a benchmark for long-horizon GUI tasks centered on professional domains and specialized software environments. Through extensive experiments on state-of-the-art models, we find that even the strongest models achieve only slightly above 30% success rates, highlighting that professional long-horizon GUI workflows remain highly challenging for current GUI agents. Further analysis reveals that current agents struggle to maintain long-horizon workflow consistency, frequently exhibiting workflow stage omission, error propagation, objective drift, and insufficient understanding of professional software environments. Our findings provide important insights into the limitations of current agent systems and suggest key directions for the next generation of GUI-agent research.

Read & Discuss → View Source →

20.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2510.06647

Q-Learning with Fine-Grained Gap-Dependent Regret

Authors:

Haochen Zhang↗Zhong Zheng↗Lingzhou Xue↗

arXiv:2510.06647v2 Announce Type: replace-cross Abstract: We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minimax worst-case regret, but their gap-dependent bounds remain coarse and fail to fully capture the structure of suboptimality gaps. We address this limitation by establishing fine-grained gap-dependent regret bounds for both UCB-based and non-UCB-based algorithms. In the UCB-based setting, we develop a novel analytical framework that explicitly separates the analysis of optimal and suboptimal state-action pairs, yielding the first fine-grained regret upper bound for UCB-Hoeffding (Jin et al., 2018). To highlight the generality of this framework, we introduce ULCB-Hoeffding, a new UCB-based algorithm inspired by AMB (Xu et al.,2021) but with a simplified structure, which enjoys fine-grained regret guarantees and empirically outperforms AMB. In the non-UCB-based setting, we revisit the only known algorithm AMB, and identify two key issues in its algorithm design and analysis: improper truncation in the $Q$-updates and violation of the martingale difference condition in its concentration argument. We propose a refined version of AMB that addresses these issues, establishing the first rigorous fine-grained gap-dependent regret for a non-UCB-based method, with experiments demonstrating improved performance over AMB.

Read & Discuss → View Source →

21.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11806

External Experience Serving in Production LLM Systems: A Deployment-Oriented Study of Quality-Cost Trade-offs

Authors:

Lin Sun↗Heming Zhang↗Xiangzheng Zhang↗

Production LLM systems accumulate reusable operational experience, but the practical deployment issue is not merely whether such experience can help. It is how different serving strategies trade off quality against online cost under realistic constraints. Injecting external experience can improve task quality, yet it also increases prompt burden, latency, and serving pressure. We study external experience serving as a deployment-oriented quality-cost trade-off problem. We evaluate this question in a real production moderation setting, with tool-use and GPQA as supporting contrast tasks that expose different output-cost regimes. We compare no-experience baselines, random experience controls, global prompt injection, and retrieval-based selective injection, and analyze both task quality and serving cost. The results show that, once experience becomes case-dependent, selective retrieval provides a stronger operating point than unconditional global injection. They further show that retrieval quality matters more than simply increasing Top-$K$, and that the same serving policy can exhibit substantially different cost-benefit profiles across short-output and decode-heavy regimes. These findings suggest that external experience is best treated as a selective, cost-aware serving decision rather than as a universal add-on. Overall, in the settings studied here, external experience pays off only when both the serving interface and the task-specific cost structure make its quality gains worth the online cost.

Read & Discuss → View Source →

22.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18697

Stealthy World Model Manipulation via Data Poisoning

Authors:

Yibin Hu↗Xiaolin Sun↗Zizhan Zheng↗

arXiv:2606.18697v1 Announce Type: new Abstract: Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments. However, the process of updating world models from collected experience creates a training-time attack surface: adversarially poisoned fine-tuning trajectories can manipulate the learned dynamics and thereby corrupt downstream planning. In this paper, we propose SWAAP, the first two-stage data poisoning framework for learned world models. In the first stage, SWAAP identifies a harmful target world model that induces low-return behavior under planning while remaining close to clean dynamics, using first-order bilevel optimization enabled by a transition-gradient theorem. In the second stage, SWAAP realizes this target through stealth-constrained gradient matching, modifying only a limited fraction of fine-tuning transition targets so that the induced training gradients steer the victim model toward the adversarial target, while a prediction-error regularizer encourages the poisoned targets to remain close to the world model's natural approximation error. To assess attack stealthiness, we evaluate defenses and detectability across three stages of the poisoning pipeline: pre-training detection of poisoned transitions, robust training during fine-tuning, and test-time monitoring of the resulting world model. Across diverse continuous-control tasks, SWAAP causes substantial performance degradation while keeping poisoned transitions close to clean data and evading the evaluated non-adaptive residual/CUSUM/TRIM-style defenses. These results reveal a practical vulnerability in world-model adaptation pipelines and highlight the need for robustness methods that protect both world-model training data and learned dynamics.

Read & Discuss → View Source →

23.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15079

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Authors:

Ang Li↗Ben Liu↗Bin Han↗Bin Hu↗Bin Jing↗Binbin Hu↗Bing Li↗Cai Chen↗Caizhi Tang↗Changxin Tian↗Chao Huang↗Chao Zhang↗…

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

Read & Discuss → View Source →

24.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11520

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

Authors:

Siyuan Luo↗Nairong Zheng↗Lin Zhou↗Tiankuo Yao↗Shengyou Yuan↗Haojia Yu↗Cong Pang↗Jiapeng Luo↗Lewei Lu↗

Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution–properties absent from existing datasets. We propose ISE (Intent -> Simulate -> Execute), a three-stage synthesis paradigm that addresses these gaps jointly. Stage 1 constructs roughly 50000 structured intents via a 4D framework (Persona x Domain x Task x Complexity); after deduplication the pool contains 43956 unique intents and attains a Vendi Score of 61.57 over the entire pool on mpnet-base-v2 embeddings (cosine kernel, q=1). Stage 2 drives multi-turn user-agent interaction through a role-locked user simulator that grounds each user turn in actual execution outcomes, producing 23132 complete trajectories averaging 8.12 user turns and 68.24 total dialogue turns. Stage 3 runs every tool call inside a live, isolated OS workspace, generating authentic failure-recovery dynamics instead of simulated responses. Fine-tuning on ISETrace improves ClawEval pass@1 from 19.3 to 37.7 using Qwen3-8B on agent tool-use tasks with a standard protocol. This result outperforms zero-shot GPT-4o and the larger Qwen3-32B base model which is four times bigger. An ablation on Stage 2 proves multi-turn simulation brings a large portion of the performance gain. We release all source code and dataset at https://github.com/Valiere01/ISE-Trace.

Read & Discuss → View Source →

25.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2512.22560

RollArt: Disaggregated Multi-Task Agentic RL Training at Scale

Authors:

Wei Gao↗Yuheng Zhao↗Tianyuan Wu↗Shaopan Xiong↗Weixun Wang↗Dakai An↗Lunxi Cao↗Dilxat Muhtar↗Zichen Liu↗Haizhou Zhao↗Ju Huang↗Siran Yang↗…

arXiv:2512.22560v2 Announce Type: replace-cross Abstract: Agentic Reinforcement Learning (RL) trains LLMs through multi-turn interactions with environments, producing workloads that mix compute-bound prefill, bandwidth-bound decoding, CPU-heavy environment execution, and bursty reward evaluation. Existing systems either colocate all stages on a single GPU cluster or decouple them only at a coarse granularity, overlooking hardware heterogeneity and incurring substantial synchronization overhead across stages. We present ROLLART, a system for multi-task agentic RL on disaggregated infrastructure. ROLLART maps each pipeline stage to best-fit hardware, routing prefill-heavy tasks to compute-optimized GPUs, decode-heavy tasks to bandwidth-optimized GPUs, and environments to CPU clusters. It decouples rollout at the trajectory level, allowing generation, environment interaction, and reward scoring to proceed independently, so that slow or failed environments never block the others. ROLLART offloads stateless reward computation to serverless infrastructure and overlaps rollout with training via staleness-bounded asynchronous weight synchronization. Our results demonstrate that ROLLART effectively improves training throughput and achieves 1.31–2.05 \(\times\) training time reduction compared to various RL systems. We also evaluated ROLLART by training a hundreds-of-billions-parameter MoE model for Qoder product on an Alibaba cluster with above 3,000 GPUs, demonstrating its stability and scalability.

Read & Discuss → View Source →