跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 01:59 · 全站最近入库：2026-11-07 17:43各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 02:47 — 2026-11-08 02:47（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 01:59最近发现新增版本：2026-11-07 17:43库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 45 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 01:57（北京时间）
版本更新 · v3arXiv:2610.32057

HyScale：面向可学习稀疏注意力的长上下文训练扩展系统

HyScale: Scaling Long-Context Training for Learned Sparse Attention

Yangshen Deng, Xinjing Huang, Yulong Wang, Yunzhuo Liu, Jun Hu, Shuyong Tan, Chun-Chih Tseng, Mingji Han 等 11 位作者

AI 速读 基于摘要

HyScale 将可学习稀疏注意力中的 top-k 选择视为索引集合而非激活，通过 FlashTopK 与选择重放加速百万级 token 的长上下文训练。

cs.AI · cs.DC

arXiv ↗PDF ↗
查看原文摘要

We present HyScale, a long-context training system for learned sparse attention. Learned sparse attention is a promising architecture for million-token contexts, widely adopted in production since DeepSeek-V3.2. Selection, however, grows into the training bottleneck. For each query, it scores every previous token whereas sparse attention reads only $k$; worse, current systems materialize a full score table and repeat selection during recomputation. Our key insight is that the output of selection is not an activation, but rather a set of indices. Building on it, HyScale introduces FlashTopK and selection replay. FlashTopK finds each query's exact top-$k$ on the fly without a score table, while selection replay reuses forward-pass selection in recomputation. Together with holistic system optimizations tackling end-to-end challenges, HyScale speeds up GLM-5.1 training on 1M-token sequences by $2.07\times$ over Megatron-LM on 512 H20 GPUs. It also speeds up the CSA layers of DeepSeek-V4-Flash and the QSA layers of Qwen3.8-Flash-Next by $2.01\times$ and $1.57\times$ at 1M tokens on 32 H800 GPUs.

新论文 · v1arXiv:2611.06272

Evaluating Human-LLM Alignment on Visualization Preference

Tanmay Bakshi, Chenglong Wang, Simra Shahid

原文摘要

There are often multiple valid visualizations, spanning different chart types, visual encodings, and aesthetic choices, that can all support a user's goal of analyzing a dataset. Determining which of these candidate visualizations is most appropriate, however, remains challenging. Prior work has leveraged expert-curated taxonomies to guide visualization design and subsequent quality evaluation, a practical evaluation model must also account for human-centric factors. Latest visualization tools integrate Large Language Models (LLMs) to generate and refine visualizations, using LLM-as-a-judge to provide design feedback. Without a deeper understanding of whether, and in what ways, human and LLM perceptions of visualizations align, there is a real risk of deploying low-quality agents that do not reflect human judgment. We study this question through a pilot experiment - we formulate the problem as a preference task over curated chart pairs and compare the judgments of state-of-the-art vision models with those of a panel of human annotators. We establish a cautionary tale: such judges risk filtering out informative, compelling displays. We find that frontier models collapse human subjectivity, a rich signal that reveals contrasting design choices, into near-deterministic verdicts.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06254

HarnessFlow: MCTS-Guided Harness Optimization for LLM Agents

Zhi Hong, Qianlong Wang, Hongchen Wei, Aidan Wu, Daohong Ying, Mingze Kong, Bei Liu, Chong Luo

原文摘要

The performance of large language model (LLM) agents depends on both the underlying model and the harness that governs interaction with tools and the environment. Yet harness design remains largely manual, and automating it requires navigating an open-ended search space through costly end-to-end evaluations. We introduce HarnessFlow, a framework for optimizing complete executable harnesses under a limited candidate-evaluation budget, with the model and task environment held fixed. HarnessFlow organizes candidates and their evaluation histories in a refinement tree, using a Monte Carlo Tree Search (MCTS)-based policy to balance exploitation and exploration. A coding agent refines selected harnesses using archived code, execution feedback, and a library of reusable harness mechanisms. With 15 refinement attempts per benchmark, HarnessFlow achieves the highest mean test scores among the compared methods on six benchmarks spanning agentic tasks, coding, and web interaction. The optimized harnesses achieve an average score of 69.48%, outperforming the initial harnesses and Meta-Harness by 10.89 and 3.95 percentage points, respectively, while incurring lower average per-task execution costs than hand-engineered baselines. These results suggest that structured harness search offers a promising route toward automating the design of capable and efficient LLM agents.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04870

PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations

Travis Davies, Wentao Ma, Lihao Guo, Tengfei Ma, Xiaowen Chang, Jiafeng Xu, Shilong Wang, Yiqi Deng 等 13 位作者

原文摘要

A robot world model that serves as a simulator must do more than generate plausible videos: it must faithfully follow commanded actions, maintain consistency across camera views, and sustain coherent long-horizon rollouts. We present PrimeSim, an action-conditioned, multiview world model simulator that addresses these challenges through progressive midtraining and posttraining. Starting from a pretrained video generator, we midtrain on 30,110 hours of robot demonstrations spanning 22 platforms. To improve action following, we introduce a unified cross-embodiment action representation and frame-aligned dual-path conditioning to strengthen action-frame correspondence. To maintain multiview consistency, we develop view-aware interleaved attention with explicit camera identities, enabling cross-view information exchange while preserving view-specific representations. We further introduce a fast-video, slow-memory posttraining framework that transforms the bidirectional video generator into an efficient autoregressive simulator. By combining fast causal generation, self-rollout training, and hierarchical temporal memory, PrimeSim mitigates error accumulation from self-generated histories and supports coherent long-horizon simulation. PrimeSim runs at 10.1 FPS, remains stable over long-horizon rollouts on rigid and deformable manipulation tasks, and transfers to held-out platforms within 100 to 200 gradient steps where the pretrained backbone does not. Against five open-source action-conditioned world models it leads four of the five WorldSimProbe suites and posts the best overall EWMBench score, while fine-grained local calibration still trails the field; its rollouts are faithful enough to support GRPO-based policy optimization. We release the model weights, inference code, and training code.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.03203

MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents

Jia Yu, Zilong Wang, Xinyang Jiang, Dongsheng Li, Shuo Wang

原文摘要

Computer-use agents could automate repetitive screen-based clinical work, but their reliability in medical graphical user interfaces remains largely unvalidated. Existing benchmarks focus on general web or desktop tasks and underrepresent medical software, which requires domain knowledge, exhibits markedly different UI design from mainstream applications, lacks public testing environments, and demands safety validation beyond task completion. We introduce MedCUA-Bench, an interactive benchmark for clinical computer-use agents. It covers 18 clinical scenarios across 10 medical domains, reconstructed from real product manuals and open-source medical systems to capture authentic clinical interfaces while avoiding licensing and privacy constraints. Each task ships with paired intent- and step-level goals to disentangle clinical reasoning from UI execution, and is evaluated by a deterministic checker over task completion and five clinical safety dimensions. Across 23 agents, the best closed-source model reaches 54.2% strict success, while all models remain below 9% on the real OpenEMR. Open-source agents average only 2.5%, with the best reaching 16.2%. MedCUA-Bench exposes the gap between current agents and reliable clinical software use, providing a reproducible testbed for future research.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03240

Susceptibility optimization for wisdom of crowds: A social power reformulation and realization framework

Ye Tian, Anzhi Sheng, Angela Fontan, Long Wang, Karl H. Johansson

原文摘要

Whether social influence makes a crowd wiser or more biased hinges on who yields to others and who holds firm. Such heterogeneous susceptibilities to social influence, together with the influence network, determine the weight each agent's initial estimate carries in the collective estimate, known as social power. This paper studies susceptibility optimization for maximizing the wisdom of crowds under the Friedkin-Johnsen model. Minimizing the squared collective bias over susceptibilities leads to a nonconvex problem. To overcome this nonconvexity, we develop a social power reformulation and realization framework, which decomposes the problem into two stages: first characterizing the social power that minimizes the collective bias, then determining the susceptibilities that induce such social power. Social power reformulation yields a quadratic program over the probability simplex. Under uniform-sign biases, the optimal social power concentrates on the least biased agents and immediately determines the optimal susceptibilities; under mixed-sign biases, its geometry enables a linear-time construction algorithm. For social power realization, we introduce the notions of susceptibility realizability and establish necessary and sufficient conditions for them, under which we derive all optimal susceptibilities in closed form using the Laplacian pseudoinverse and eigenvector centrality. These results yield a unified algorithm that solves the original problem globally, with worst-case complexity cubic in the number of agents when realizability holds. Finally, we develop a fully distributed implementation with linear communication complexity, illustrating how collective intelligence can emerge from local interactions.

eess.SY · cs.SI · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02706

Hindsight Credit Assignment over Trees for Agentic RL

Penghong Zhao, Yihao Chen, Maoheng Yuan, Yunjian Zhang, Abudukelimu Wuerkaixi, Haoran Xu, Man Lv, Yaolong Wang 等 11 位作者

原文摘要

Reinforcement learning for long-horizon LLM agents faces a fundamental dilemma: successful experiences are essential for policy improvement, yet limited policy capabilities make such experiences difficult to discover. Sparse outcome rewards compound this challenge, leaving sampled trajectories with little relative feedback for learning. In this paper, we propose TriGRPO, a tree-based reinforcement learning framework that turns scarce successes into exploration and learning signals through hindsight credit assignment within and across rollout trees. TriGRPO constructs rollout trees through hindsight-guided branching: when an ongoing trajectory reaches a matched decision state, a successful action discovered during rollout initiates a sibling branch that continues autonomously, enabling further exploration and parent-sibling comparisons. Three complementary groups organize policy optimization over these trees: root groups capture within-prompt relative returns, node groups assign credit from parent-sibling outcome differences, and cross groups supplement sparse feedback with historical performance on related tasks. Experimental results demonstrate consistent gains in task performance and rollout efficiency across model scales, highlighting structured hindsight credit assignment as an effective approach to long-horizon agent learning.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.13136

From Review to Reuse: How Post-Task Workflow Can Support Human-AI Agent Interaction

Zekun Wu, Xinru Wang, Rock Yuren Pang, Chenglong Wang, Anna Maria Feit

原文摘要

AI agents can automate tasks by turning a single natural-language request into a multi-step process spanning tools, files, and applications. Users are often left to judge that process from fragmented execution information and the final output. To make the completed process easier to understand, validate, and reuse, we investigate post-task workflows: editable, graph-based representations of an agent's completed execution. We first analyzed 10,803 public workflow templates from n8n to characterize real-world automation practice, then developed Trace2Flow, a research probe that translates agent execution traces into interactive post-task workflows. In a study, participants (N = 20) reviewed agent executions with prompt or agent errors. We found that post-task workflows improved their understanding and error detection over a prompt-only condition, and that validation succeeded mainly when users cross-checked across multiple evidence sources. For follow-up tasks, adapting the workflow matched adapting the prior prompt in success, time, and difficulty, and was often preferred.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01659

HuG: Learning Humanoid Whole-Body Affordance-Aware Grasping with Active Perception

Xuanbin Peng, Lai Wei, Yuze Zhai, Qingyuan Yu, Keyi Wang, Jianglong Ye, Xiaolong Wang

原文摘要

Acquiring objects in human environments is hard for humanoids: targets are partially occluded under egocentric viewpoints, and reaching them demands coordinated whole-body motion that keeps the target visible and reachable while the base stays stable. We present HuG, a framework for whole-body affordance-aware grasping with active perception that couples perception and action through a Perceive-Align-Grasp pipeline: belief-driven active perception resolves occlusion by treating viewpoint as an explicit decision variable; a point-cloud-conditioned affordance policy proposes whole-body grasps; and an affordance-aware alignment stage repositions the body to the most executable configuration. A key insight is that, on a floating base, kinematic validity is not enough: we curate training data with controller-in-the-loop dynamics simulation, rejecting 73% of kinematically valid grasps that would destabilize the deployment controller, so the policy learns kinodynamically feasible affordances. Trained entirely in simulation with zero real demonstrations, HuG attains 87.5% real-world success on a multi-level shelf task, generalizes to novel objects, and holds at least 73% success at every tested height. Beyond generalizing within its training distribution, the policy extrapolates spatially: at scale in simulation it succeeds at table heights well below any seen during training, indicating that kinodynamically filtered synthetic data grounds affordances in object geometry and whole-body feasibility rather than in memorized configurations.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39905

Inkitiate: Initiating and Steering Agent Assistance through Ink in a Spatial Workspace

Liangwei Wang, Nan Chen, Luna K. Qiu, Zilong Wang, Fugee Tsung, Yuyu Luo, Yuqing Yang

原文摘要

Handwriting and sketching help people develop ideas around information. As this work unfolds, users may seek assistance with finding, understanding, and organizing materials. We investigate how ink can initiate and steer agent assistance in this process. An eight-participant formative study explored desired assistance and interaction expectations, informing three connected activities: bringing materials in, thinking with materials, and shaping the space. We present Inkitiate, a spatial workspace for ink-based agent assistance in knowledge work. Through ink, users retrieve external materials, build on accumulated content and results, and reorganize the canvas, while inspecting and guiding agent actions. In a study with eighteen participants, users reported favorable usability and low perceived workload, and used retained ink and materials to develop further ink queries. An ink-query vocabulary and cases reveal how users combine linguistic and graphical expressions to direct agents. These findings inform ink-based agent interaction design for expressive requests and continued work with materials.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.28070

CCFormer: Efficient Cross-Field Interaction and Hierarchical Sequence Compression for Industrial Recommendation at Tencent

Yunlong Wang, Huizhe Zhang, Haonan Hu, Yudong Li, Bing Wen, Jianchao Tu, Chengxiang Zhuo, Zang Li

原文摘要

Industrial candidate-ranking systems must combine long user behavior histories with heterogeneous user and item features under strict computational budgets. We propose CCFormer, a structured interaction architecture that separates cross-field retrieval from intra-history modeling. Feature-field-separated cross-attention allows user and target queries to read an evolving history hierarchy, while local subspace token mixing contextualizes history tokens independently of candidate targets. Hierarchical sequence compression reduces the number of history tokens and provides multi-scale historical context for subsequent interactions. Experiments on two public benchmarks show higher mean AUC than the evaluated baselines, while experiments on a large-scale industrial dataset show a favorable accuracy-compute trade-off and higher training throughput than HSTU. Online A/B tests across four recommendation and advertising scenarios report system-level improvements of up to 3.57% in click-through rate, 3.86% in page views, and 1.71% in advertising revenue relative to the corresponding production baselines. CCFormer has been fully deployed in all four scenarios, demonstrating its practical scalability and effectiveness in large-scale recommendation systems.

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.21926

IMU4D: 4D Human-Object Understanding from Wearable IMUs

Hao-Yu Hsu, Tianhang Cheng, Jing Wen, Alexander G. Schwing, Shenlong Wang

原文摘要

Understanding human activities and the objects they interact with typically relies on visual perception, yet cameras pose persistent challenges in privacy, safety, energy efficiency, and scalability. We explore an alternative: 4D perception without vision. Its goal is to recover human motion and the objects the person interacts with purely from everyday wearable sensors. For this we introduce IMU4D, a framework that repurposes large language models for non-visual spatiotemporal understanding of human-object dynamics. IMU4D uses data from a few inertial sensors from earbuds, watches, or smartphones and predicts detailed 4D human motion together with surrounding objects the person interacts with. Experiments across diverse human motion datasets and human-object datasets show that IMU4D yields more coherent and temporally stable results than SoTA cascaded pipelines, suggesting wearable motion sensors alone can support 4D understanding of human-object interactions.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.29532

GUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing

Xiaoyi Chen, Yifei Gao, Yang Xu, Zhenlong Wang, Jian Yan, Jiming An, Xingxing Song, Liqun Deng 等 12 位作者

原文摘要

Exploratory GUI testing is a particularly demanding setting for MLLM agents: without predefined test scripts, an agent must autonomously navigate an application and discover defects through its own interaction. However, current evaluation falls short on two fronts. First, existing benchmarks focus almost exclusively on interaction defects, leaving display defects outside the evaluation frame. Second, evaluation protocols are bound to predefined defect annotations, collapsing the testing process into a single end-state judgment that conflates qualitatively distinct failure modes. To address these challenges, we present GUITestScape, an interactive benchmark covering 61 real-world Android applications and 508 preset defects spanning interaction and display types, and introduce GUIJudge, an open-set evaluator that decomposes an agent's testing trajectory into independently diagnosable capabilities. Experimental results demonstrate that GUIJudge achieves reliable process-aware evaluation beyond predefined annotations, substantially outperforming all baselines. Benchmarking on GUITestScape further reveals that detection remains the critical bottleneck for existing models across both defect types, and that integrating GUIJudge's verifiers into existing agents significantly boosts their detection performance without retraining.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.35488

Benchmarking Coding Agents under Evolving Requirements

Jia Feng, Alyssa Wu, Cuiyun Gao, Yunlong Wang, Songyuanyi Lu, Zhichao Hu

原文摘要

Software development with coding agents often begins with a rough request that users refine after trying the implementation. Final correctness alone does not capture the repeated guidance this process requires. We introduce FeatureLoop, a benchmark of 61 human-reviewed tasks from 34 repositories across five primary programming languages and seven software forms. Each task follows one development goal in a persistent workspace through evolution feedback, which adds or clarifies requirements, and completion feedback, which reports failures of stated requirements. Cumulative executable checks track new behavior, repair, and preservation of earlier functionality. We evaluate 12 frontier models and find that the strongest completes 72.1% of tasks with both feedback types. Across models, however, only 15.4% of observed failed stages recover within two corrective revisions. Further analysis reveals incomplete repairs, regressions, and model-specific differences in feedback use and token efficiency, identifying obstacles to reliable, low-intervention development.

cs.SE · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39155

REALM: Identifying Minimal Task Assets for LLM Agents

Zihou Ren, Byungchul Tak, Long Wang

原文摘要

Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an opportunity to redirect execution toward unrelated resources. Applying least privilege therefore requires identifying the assets needed by a task, including assets whose identities emerge only during execution. We present REALM (Required Execution Assets Linked to a Mission), an approach to identifying and maintaining a task's required assets and their permitted uses. The approach represents required assets as Dependency Graph nodes, resolves prerequisite relationships, and admits newly discovered assets through source-scoped selection. It separates discovering an asset from authorizing its use, while preserving the agent's freedom to choose its computation. The REALM Builder maintains the selected grants and projects Asset Files; the Partial API Manager exposes resource-bound Partial APIs to the Agent inside a Task Container. Across 60 clean tasks and 560 injected cases in AgentDyn, it completes 40.0% and 36.4% of tasks and decreases ASR from 16.6% to 0.2% with qwen3.5-flash as the base model.

cs.CR · cs.AI · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38566

Co-Evolving Policy and Rubric via Capability Awareness for Open-Ended Generation

Chengsheng Zhang, Wenshen Xu, Yuchuan Wu, Zhiyuan Yu, Junfeng Fang, Tianlong Wang, Bingxue Qiu, Yongbin Li 等 9 位作者

原文摘要

Rubric-based reinforcement learning (RL) offers interpretable, fine-grained supervision for aligning large language models (LLMs) on open-ended generation tasks. However, static rubric criteria may become saturated or remain beyond the policy's exploration, rendering the reward signals insufficiently discriminative. While recent efforts seek to guide sampling exploration or evolve rubrics, they fail to explicitly factor in how rubric difficulty should track the evolving policy's capabilities, resulting in a persistent mismatch between the optimization objective and the policy's current capability frontier. In this paper, we propose \textbf{Co}-Evolving Policy and Rubric via \textbf{C}apability \textbf{A}wareness (\textbf{CoCA}), a closed-loop framework that jointly adapts the rubric and policy through criterion-level diagnosis. Specifically, CoCA contrasts query-only and rubric-guided rollouts to characterize each criterion relative to the current policy, recalibrates criteria with mismatched difficulty, and identifies guidance-revealed capability gaps for frontier-based learning. Based on this insight, CoCA either expands rubric-conditioned frontiers through guided optimization or transfers qualified gains through on-policy self-distillation. As the policy updates, CoCA improves the capability diagnosis and enables more reliable distillation, thereby completing the co-evolution loop. Extensive experiments across diverse benchmarks and LLMs demonstrate that CoCA consistently improves performance over rubric-based RL methods. Moreover, CoCA promotes the internalization of guidance-revealed capabilities into query-only behavior while mitigating capability degradation.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37434

FeatureArc: Benchmarking Coding Agents on Evolving Features

Yunlong Wang, Alyssa Wu, Cuiyun Gao, Jia Feng, Songyuanyi Lu, Zhichao Hu

原文摘要

A software feature usually evolves over time: developers extend its first version as new use cases and requirements arrive, and each extension builds on code written earlier. Most feature benchmarks evaluate a single request on a fixed codebase. Feature evolution requires evaluating successive extensions on an agent's own earlier code and checking whether the feature remains correct. We introduce FeatureArc to evaluate coding agents on evolving features, together with a pipeline that constructs its tasks from repository histories. The benchmark combines dependencies between successive stages of the same feature, explicit requirements and interface contracts, and executable checks across four programming languages. The pipeline validates fail-to-pass (F2P) tests for new behavior and pass-to-pass (P2P) tests for existing behavior on the reference code before and after each stage. We evaluated 10 coding agents on 73 manually reviewed tasks of 2 to 10 stages. Each agent works in one persistent session and workspace without external test feedback or rollback. The evaluation reveals a gap between first-stage and whole-feature success: pooled success falls from 62.7% at the first stage to 28.5% when the whole feature is tested on the final code. Trajectory analysis identifies inherited defects as a common failure mechanism, present in 72.9% of failed later stages. These earlier errors often remain undetected: in stages following a failure, agents leave the earlier error unnoticed about 95% of the time, and their self-tests rarely revisit earlier stages. Evolving a feature autonomously, without human checks between stages, therefore remains a substantial challenge for current coding agents. At Tencent, the pipeline extends internal evaluations to this setting and guides the development of Hunyuan, Tencent's family of large language models.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36859

ActiveAlign: Aligning Egocentric Manipulation via Active Perception

Ri-Zhao Qiu, Bowen Wen, Yifeng Jiang, Chen Tessler, Eric Heiden, Xue Bin Peng, Xiaolong Wang, Stan Birchfield 等 9 位作者

原文摘要

Real-to-Sim-to-Real (Real2Sim2Real) enables structured world representations for planning, interpretability, and safe execution. Most existing approaches rely on passive perception, which creates real2sim gaps due to imperfect observation. Inspired by how humans perceive actively through actions, we propose ActiveAlign, a framework that leverages active perception to align the Real2Sim2Real gap from interactions. ActiveAlign introduces two complementary modules: (i) ActiveAlign-Waving, which performs hand-eye calibration by exploiting active hand motions and differentiable rendering, and (ii) ActiveAlign-Touching, which refines object alignment through tactile feedback to achieve millimeter-level precision. Together, these capabilities enable strong real2sim alignment. We demonstrate that ActiveAlign-Waving can be used to curate simulation environments for open-sourced uncalibrated robot manipulation datasets, and demonstrate on a real Unitree G1 robot that ActiveAlign enables fine manipulation of millimeter-scale objects such as pressing buttons and moving sliders.

cs.RO · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36549

From Ripple to Boundary: Deterministic Impact Boundaries for LLM-Based Software Evolution

Jiameng Bai, Zhitao Wang, Long Wang, Keyue Qian, Sai Wu

原文摘要

The landscape of software evolution is undergoing a fundamental paradigm shift in the era of Large Language Models. As industrial software engineering increasingly transitions toward design-driven code generation, the bottleneck of evolution has shifted from writing code to maintaining deterministic consistency between multi-source design assets and the generated code. When a design asset changes, LLM agents currently lack a deterministic impact boundary to identify which code must be evolved, leading to two failure modes: hallucinating missing changes or breaking unrelated code. Probabilistic approaches, such as semantic retrieval or text-based diffing, fail to capture the structural ripple effects across highly interconnected design dependencies. We propose a paradigm shift from probabilistic semantic retrieval to deterministic structural constraints. We formalize the design assets as a Knowledge Graph and organize them into a content-addressed Merkle Directed Acyclic Graph. Our key insight reveals a topological isomorphism between the logical ripple effect of a design change and the content hash propagation within the DAG. By leveraging this, we transform ambiguous impact analysis into verifiable structural operations. Through a two-phase diffing process, we extract a precise causal chain that defines the exact modification boundary. This boundary enables deterministic context injection, providing the LLM agent with strictly scoped code and design updates, thereby fundamentally guaranteeing evolution safety. As a by-product, the KG serves as an agent-queryable knowledge base for natural language design retrieval. Early deployment on a large-scale industrial payment platform demonstrates that our mechanism successfully computes the exact impact boundary and generates incremental code modifications that meet the expected design changes.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36327

Training-Free Inference Acceleration for Video Large Language Models: Methods, Trade-offs, and Evaluation

Yuqi Li, Chuanyue Yan, Neil Rodrigues, Xianglong Wang, Xiaoqin Feng, Junming Liu, Xi Xiao, Zhongwei Cheng 等 11 位作者

原文摘要

Video Large Language Models (VLMs) have demonstrated strong capabilities in video understanding and reasoning, but processing long visual sequences incurs substantial computational, latency, and memory overhead. This survey examines training-free inference acceleration, focusing on reducing inference costs while preserving task-relevant spatiotemporal evidence. We organize existing methods by their intervention stages in the inference pipeline, covering input, visual encoding, projector, prefill, and decoding. Post-training quantization (PTQ) is discussed separately as a cross-stage extension with varying calibration requirements. We analyze how intervention position affects evidence preservation and computational savings, and why local efficiency improvements may not translate into end-to-end acceleration. We complement this analysis with quantitative evidence from prior studies and our own experiments under a shared evaluation setting to assess accuracy-latency trade-offs.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36013

OmniBrain-0: A Unified Agentic Model for Embodied Intelligence

Xiaomi Embodied Intelligence Team, Yuechen Luo, Chong He, Fang Li, Shaoqing Xu, Jingkai Wang, Menglun Su, Jiaxin Liu 等 32 位作者

原文摘要

General-purpose embodied intelligence requires robots to coordinate diverse skills over long horizons, track task progress, and recover from failures. Specialist policies alone do not ensure task-level reliability, while powerful multimodal agents rely on costly reasoning and external experience that compact models struggle to reproduce. We introduce OmniBrain-0, a lightweight unified embodied agent that coordinates manipulation and navigation through a shared high-level decision model, integrating task understanding, planning, progress tracking, and feedback-driven recovery. Our progressive training framework combines embodied pretraining, domain-specialized agent distillation, and multi-teacher on-policy distillation (MOPD). It distills powerful teachers' interaction experience into manipulation and navigation experts, then consolidates their decision capabilities into OmniBrain-0. Unification therefore occurs within the learned decision model rather than only at the tool interface. We further introduce Rubric-Guided Recursive Self-Improvement (RSI), a data flywheel in which a Meta-Agent turns execution evidence into refined rubrics, step-level reminders, and verified trajectories for domain-expert updates before their reconsolidation into OmniBrain-0 through MOPD. We evaluate OmniBrain-0 on LIBERO-Pro, LIBERO-Plus, RoboCasa365, RoboTwin 2.0, and R2R-CE Val-Unseen, as well as multiple real-world manipulation tasks. OmniBrain-0 combines strong cross-domain task performance with substantially lower inference and execution overhead than its closed-source teacher, demonstrating efficient transfer and consolidation of embodied capabilities into a compact unified agent.

cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35716

Audit Where Hacks Pay: Budgeted Strong-Verifier Audits Against Reward Hacking in GRPO

Shurun Li, Michael Hua Wang, Haibo Zeng, Long Wang

原文摘要

Reinforcement learning with verifiable rewards trains on cheap checks, such as unit tests, that a policy can learn to game, while a stronger check is too expensive to run on every rollout. We study how to spend a limited strong-verifier budget in GRPO, separating which weakly passing rollouts to audit from what reward a caught hack receives. At a fixed policy state with centered advantages, the expected update depends on a design only through each rollout's marginal audit probability and correction; reflecting a caught hack's reward about the failure reward negates the advantages of an all-hack group; and auditing whole groups with the fewest weak passes first (low-pass budgeted audits, LB) minimizes the advantage mass left on hacks among pass-count designs with a fixed correction when a label's value falls with the pass count. We tested this analysis in actual LLM training: from each run's starting state, the sign of this mass on a frozen panel predicted whether hacking would be suppressed in 33 of 39 runs, including 13 of 16 preregistered ones. In LeetCode (Wong et al., 2026) and Countdown-Code (Khalifa et al., 2026), LB drives hacking to near zero, while random audits with the same penalty and budget do not and use more labels. We also find that the randomness of the update affects training: in Countdown-Code, two unbiased corrections, per-item reward-level IPW and a group-level advantage correction, bring hacking down too but end 6.1-11.8 and 8.0-11.5 points lower in held-out accuracy than LB at the same budget. A full audit, which the group-level correction reproduces in expectation, stays within about two points of LB in three seeds, while LB uses 28% of its labels, and allocating the same correction by pass count recovers most of the loss (one seed). Training outcomes thus depend not only on the expected update but also on the randomness of its estimate.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.31142

JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models

Jianyi Hu, Hangtao Zhang, Yi Liu, Yeqi Zeng, Li Zeng, Xianlong Wang, Rui Wang, Leo Yu Zhang

原文摘要

Typed decision models (TDMs), such as Jev, answer a question about an input with a probability, an option, or an ordinal level. Web services execute these decisions automatically above a confidence threshold. An attacker who writes part of the input can change a decision that the service then executes. Current adversarial benchmarks cannot measure this risk, because they judge generated text. A TDM writes no text, and its wrong decisions have a valid format. We present JevAdvBench, to our knowledge the first unified benchmark for the adversarial robustness of TDMs. It contains 862 questions with audited answers and twelve black-box attack methods that edit the input or the options by adaptive search. Because a changed decision is not always wrong, a review keeps only 5,586 answer-preserving variants, and we attack only correct decisions. The attacks flip 46.3% of Jev's correct decisions, while identical re-runs flip only 0.17%. A flawed argument without a command flips 77.2%, close to direct prompt injection at 92.0%. The same variants flip 34.0% to 51.7% of correct decisions on eight open TDMs. At a 0.8 threshold, 23.5% of the decisions that the service still executes are wrong. On Agentgateway, the Jev guardrail rejects a jailbreak request but accepts it with an inserted argument. Web services should therefore treat TDM inputs as untrusted and should not act on confidence alone. Project website: https://JevAdvBench.github.io/JevAdvBench/

cs.CR · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2503.02296

Evaluating Harmful Memorization in LLM Code Generation

Lizhe Zhang, Wentao Chen, Li Zhong, Letian Peng, Zilong Wang, Jingbo Shang

原文摘要

Assessing memorization in LLM code generation is challenging because code reuse is not inherently harmful. Correct programs often share APIs, templates, and algorithmic idioms, so code similarity alone may reflect benign reuse rather than problematic memorization. We focus on the harmful case: a model fails to adapt when task semantics change and instead produces code that remains highly similar to the original solution. We propose \emph{code rewriting}, an automated semantic perturbation pipeline that constructs superficially similar but semantically different variants of existing coding tasks by modifying a core logic element of the reference solution and regenerating the corresponding prompt. To summarize this behavior, we introduce the \emph{Harmful Memorization Index} (HMI), an operational diagnostic that combines similarity to the original solution with performance degradation on rewritten tasks. We use harmful memorization as an operational behavioral term for this specific failure mode; HMI does not establish whether an original task or solution appeared in a model's training data. HMI is intended to complement standard accuracy metrics by capturing brittleness under small semantic changes. Across MBPP+ and BigCodeBench, we find that: (1) HMI does not monotonically increase with model scale and often decreases on simpler tasks; (2) high-HMI failures are concentrated in specific logic-edit types, especially constraint changes and data transformations; (3) supervised fine-tuning improves original-task accuracy but can substantially increase HMI on held-out tasks; and (4) across the evaluated post-training settings, PPO yields a more favorable accuracy--HMI trade-off than SFT.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34652

The CAPED Framework: Characterizing User Skills in Chart Authoring through the Lens of Tasks and Tools

Bongshin Lee, Zhicheng Liu, John Thompson, Chenglong Wang

原文摘要

In this paper, we introduce a new framework for characterizing the user skills required for chart authoring. Despite growing attention to authoring systems, we lack a conceptual framework that characterizes the diverse and multifaceted skills involved and helps identify opportunities for system design and development. Our initial investigation revealed that skill is a complex and elusive concept, and that existing theories on skills from other disciplines are too high-level to capture the importance of tasks and tools in data visualizations. To address this gap, we formulate the CAPED framework that characterizes skill as the ability to create a chart involving five dimensions pertinent to tasks and tools: input data, output chart, paradigm, abstraction, and expression. We demonstrate the framework's descriptive power by highlighting different skills involved in similar authoring situations and identifying the types of knowledge associated with chart authoring. We further present examples illustrating how the framework can be used to identify new research opportunities in supporting users with varying skills.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.17384

IndustryNav: Evaluating Spatial Reasoning and Safety of Embodied Agents in Dynamic Industrial Navigation

Yifan Li, Lichi Li, Anh Dao, Xinyu Zhou, Wenjun Huang, Tianyi Ma, Yicheng Qiao, Zheda Mai 等 18 位作者

原文摘要

Visual large language models (VLLMs) are increasingly used as embodied agents, yet industrial warehouses demand more than reaching a goal: agents must navigate safely around moving workers and vehicles. To evaluate embodied agents' goal reaching and safety, we introduce IndustryNav, a simulation environment with 24 warehouse scenes for closed-loop navigation to specified destinations. Alongside task success and efficiency, we introduce safety-aware metrics that capture collisions and near-collision warnings along each trajectory. Experiments with eleven leading open- and closed-source VLLMs and three navigation baselines show that agents can reach their goals yet collide with moving obstacles, exposing a gap between success and safe navigation. This gap matters in safety-critical settings, where a single collision can end the task. IndustryNav also supports policy learning through automated oracle trajectories and simulator interaction, with held-out scenes for generalization tests. These experiments show that policies can succeed on new routes in familiar warehouses yet fail to transfer to held-out layouts, making cross-scene generalization an open challenge.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.114ACL Anthology · ACL 2026

Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework

Ziqiang Zhang, Jing Ma, Zilong Wang, Jiayuan Chen, Yi Qiao, Yu He, Wei Zhang, Dai Cheng 等 9 位作者

原文摘要

Pricing automation in large-scale tourism is challenging because travel orders are highly unstructured, while pricing policies are complex, rapidly evolving, and inherently open-ended. Traditional rule engines are brittle and costly to maintain, whereas unconstrained LLM agents lack the reliability and auditability required for financial decisions. We present a production-grade LLM-powered pricing system with a strict decision boundary: LLMs perform structured extraction and bounded policy/path selection, while all numeric pricing, including total-price computation, is executed deterministically. Policies are compiled into interpretable condition trees, enabling open-ended support for new clauses and evolving rules without code changes, while exposing auditable artifacts for human-in-the-loop control. Periodic fine-tuning on logged traces further improves tree induction and path matching. Deployed at a municipal state-owned tourism enterprise across 7 scenic sites and 12 business categories with 1,500+ operators and 1,000+ active policies, the system processed 3,960 orders in six months, reduced the order management team from 15-20 to 3, and cut per-order handling time from 10 minutes to <2 minutes.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.129ACL Anthology · ACL 2026

RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment

Yingfeng Luo, Hongyu Liu, DingYang Lin, Kaiyan Chang, Chenglong Wang, Bei Li, Quan Du, Tong Xiao 等 9 位作者

原文摘要

Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT), but deploying them at scale remains prohibitively expensive. A widely adopted remedy is the hybrid system paradigm, which balances cost and quality by serving most requests with a small model and selectively routing a fraction to a large model. However, existing routing strategies often rely on heuristics, external predictors, or absolute quality estimation, which fail to capture whether the large model actually provides a worthwhile improvement over the small one. In this paper, we formulate routing as a budget allocation problem and identify marginal gain, i.e., the large model’s improvement over the small model, as the optimal signal for budgeted decisions. Building on this, we propose RouteLMT (routing for LLM-based MT), an efficient in-model router that predicts this expected gain by probing the small translator’s prompt-token representation, without requiring external models or hypothesis decoding. Extensive experiments demonstrate that our RouteLMT outperforms heuristics, quality/difficulty estimation baselines, achieving a superior quality–budget Pareto frontier. Furthermore, we analyze regression risks and show that a simple guarded variant can mitigate severe quality losses.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1046ACL Anthology · ACL 2026

SADA: Bridging In-Context Learning and Fine-Tuning via State-Aligned Distillation Adapters

Wenhao Gao, Tianlong Wang, Wei Jia Tencent, Linhao Zhang, Aiwei Liu Wechat AI, Miao Fan, Zhou Xiao Pattern recognition center

原文摘要

Prompt-based in-context learning (ICL) and parameter fine-tuning are two dominant paradigms for incorporating external information into large language models (LLMs), but they incur high inference costs or require expensive retraining. To bridge this gap, context-to-parameter mapping converts prompts into temporary adapter weights. However, we identify a critical failure mode in existing methods: hidden-state collapse, where the adapter-augmented model’s internal states diverge sharply from the full-context oracle in deeper layers. We trace this failure to two coupled gaps: suboptimal Input-Selection and inadequate Supervision-Signal. To address these issues, we propose SADA (State-Aligned Distillation Adapters). We establish the attention-block output as a principled feature interface to improve input selection and introduce state-alignment distillation to enforce consistency between the adapter-augmented model and the full-context oracle. Experiments on long-context language modeling (PG19) and downstream NLU and summarization benchmarks show that SADA consistently outperforms strong baselines like StreamAdapter and GenerativeAdapter, achieving performance comparable to ICL while significantly reducing memory footprint and latency. We further analyze when parameterized context compression is effective and when explicit context retention remains preferable. Our code is available at https://github.com/Taylor-Gavel/SADA.git.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1116ACL Anthology · ACL 2026

JanusMM: A Benchmark for Self-Deprecation Understanding in Real-World Multimodal Conversations

Xinyi Xu, Bingguang Hao ByteDance Inc., Yongyi Xiong, Zimo Chen University of Science and Technology of China, Xinchen Liu, Hongxin Guo, Xuelong Wang, Silin Zhou 等 9 位作者

原文摘要

Self-deprecation is a prevalent communicative strategy in human society, often using image-text interplay to express emotions and intentions. Despite self-deprecation is widespread in real-world conversations, the ability of multimodal large language models (MLLMs) to understand it remains underexplored. To fill this gap, we introduce JanusMM, the first benchmark designed to evaluate MLLMs’ understanding of self-deprecation in real-world conversations. JanusMM contains 2,016 bilingual memes from three types of social interactions and provides a dual-task evaluation framework with six new metrics. The first task assesses MLLMs’ abilities in self-deprecation recognition and reasoning, while the second task evaluates the consistency of their understanding by simulating the perspectives of the initiator and responder. We evaluate ten frontier MLLMs and find that they exhibit weak recognition and reasoning abilities, with their understanding of self-deprecation remaining inconsistent across both perspectives.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表