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

+788新增论文
+627其中 AI 相关
+81已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 11:20 · 全站最近入库：2026-11-09 11:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 12:32 — 2026-11-09 12:32（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：2026-11-09 11:20最近发现新增版本：2026-11-09 11:19库内论文最新更新时间：2026-11-06 21:58

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。

17,888 已收录论文15,288 AI 相关4,419 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 3,570 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 11:19（北京时间）
版本更新 · v2arXiv:2610.35560

Multi-Fidelity Training Reshapes Uncertainty Decomposition in Atomistic Models

Matteo Tolloso, Davide Bacciu, Luigi Bonati

原文摘要

Multi-fidelity training, which combines abundant low-fidelity data with scarce high-fidelity labels, is increasingly common in atomistic modeling, but its effect on predictive uncertainty remains largely unexplored. We investigate this question using deep ensembles of mean-variance MACE models trained on ANI-1x, contrasting high-fidelity training from scratch with low-fidelity pretraining followed by fine-tuning. We characterize aleatoric, epistemic, and total uncertainty throughout training and under two distribution shifts: unseen molecular systems and higher-energy configurations. We find that pretraining reduces prediction error and improves uncertainty-based ranking across all test sets, but does not yield well-calibrated predictive variances; calibration deteriorates more severely under energy extrapolation. Training-dynamics analysis localizes most of this calibration degradation to high-fidelity optimization, during which the learned aleatoric variance becomes overconfident on held-out data. Moreover, multi-fidelity fine-tuning produces a more effective uncertainty-based acquisition function than high-fidelity training from scratch. These findings show that uncertainty ranking and calibration capture distinct properties and must be assessed separately in multi-fidelity atomistic models, especially under extrapolation.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36900

Natural Hard-Negative Mining from Positives for Instruction-Following Retrieval

Chaolang Li, Jingyu Li, Zhaocheng Du, Xuyang Xie, Gang Wang, Pengwen Dai

原文摘要

Instruction-following information retrieval (IFIR) requires retrievers to rank documents by both a query and its instance-specific instructions, yet instruction-conditioned contrastive supervision remains scarce. Existing synthetic methods typically fix a positive passage and generate additional negatives, overlooking the hard-negative potential of the original positive. We propose Natural Hard-Negative Mining (NHNM), which promotes convertible negatives under query-compatible instructions and repurposes original positives as natural instruction hard negatives. Its automated Candidate Cleaning, Reversal Construction, and Geometry Filtering pipeline produces compact, high-contrast supervision aligned with the pretrained retrieval space. Applied to MSMARCO, NHNM yields NHNM-MARCO, an IFIR training set of nearly 7K instances. On InstructIR and FollowIR, models with 568M to 4B parameters fine-tuned on NHNM-MARCO achieve strong instruction-following performance and match or surpass substantially larger retrievers in several settings. Controlled analyses and ablations attribute these gains to natural hard-negative supervision rather than model scale or training-data volume.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36878

RubricAtlas: Mining Type-Level Rubrics from Expert Reports to Evaluate Deep Research Agents

Delin Wang, Sinuo Wang, Rui Sun, Beidi Luan, Qiming Shi, Jing Li, Daxin Jiang, Zuo Bai

原文摘要

Deep research agents conduct multi-step Web searches and synthesise retrieved information into analytical reports. Evaluating these outputs requires checking which analyses they deliver, beyond the presence of relevant facts. Query-specific binary rubrics make individual requirements explicit, but task-level checklists may leave the overall analytical structure underexamined. We introduce RubricAtlas, which derives type-level analytical requirements from expert reports on different objects within the same research type and organises detailed checks around recurring analytical questions. The requirements give related tasks a shared standard for what to analyse, without prescribing their answers. Our framework links binary checkpoints to report passages and evaluates completeness separately from argument validity. Built from 3,079 Chinese financial research reports, RubricAtlas covers 99 research types. Reference-report selection experiments show that individual reports cover only about half of their type's analytical questions, and that selecting requirements from different reports changes evaluation scores and agent rankings. Across ten agents, two judge pipelines achieve checkpoint agreement of $κ$ = 0.71 and agent-ranking agreement of Kendall $τ$ = 0.87. Controlled deletions reduce scores on the affected analyses, while padding produces no detectable increase. These findings support type-level rubrics for comparing the analytical completeness of Web deep research outputs, with individual decisions traceable to report evidence.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36877

GUI-JEPA: Candidate-Conditioned JEPA Latents as a Fast Action Policy for Mobile GUI Agents

Bingchao Wang, Yongcheng Jing, Shunyu Liu, Chengyu Wang, Jun Huang, Jie Yang, Wei Liu, Dacheng Tao

原文摘要

Mobile GUI agents are typically fine-tuned 7B-scale vision-language models (VLMs) that generate each action as text. However, these VLMs decode every action token by token, and even agents that score candidate actions keep a large language model or VLM in the loop, making them slow and memory-hungry. To address these issues, we propose GUI-JEPA, to our knowledge the first decoder-free GUI agent policy built on a Joint-Embedding Predictive Architecture (JEPA), which selects actions in the latent space of a JEPA encoder pretrained on unlabelled GUI screenshots. Its action- and region-conditioned latent predictor turns the screen latent into one latent per candidate action, letting lightweight heads score all candidates against the instruction in a single batched pass, without decoding a token. We further show that the scorer relies on this latent pathway and that the predictor is trained for the decision itself: a randomly initialised predictor does just as well as one pretrained on screen dynamics. On AndroidControl, GUI-JEPA is 2.8-4.0x faster on the same GPU than a Qwen2.5-VL-7B agent we fine-tune with the same inputs, while reaching 86-92% of its in-distribution accuracy with 6% of its parameters. Code is available at https://github.com/bcwang-sjtu/GUI-JEPA

cs.AI · cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36874

AdaGround: Token-Normalized Adaptive Zooming with Verifier-in-the-Loop Refinement for GUI Grounding

Bingchao Wang, Yongcheng Jing, Chengyu Wang, Jun Huang, Jie Yang, Wei Liu, Dacheng Tao

原文摘要

GUI grounding on high-resolution screens fails mostly on small targets, and zooming in is a common training-free remedy. However, most existing zooming pipelines do not match the zoom to the target's size, accept the zoomed answer unconditionally and never revisit a wrong answer. To address these issues, we propose AdaGround, a training-free framework with three components: (1) Token-Normalized Adaptive Zooming, which sets the magnification, field of view and zoom depth of each sample from the model's own estimate of the target size; (2) Verifier-in-the-Loop Refinement, which uses one marked-click Yes/No verifier to keep or reject each zoom, choose between zoom chains, trigger re-grounding and, with an existence query, decide when to abstain; and (3) Compositional Structure Grounding, which composes spreadsheet cells from their headers. On Qwen3-VL models, AdaGround surpasses state-of-the-art training-free zooming methods and many trained GUI models, improving accuracy over the backbone by 7.4 to 20.6 points on OSWorld-G and ScreenSpot-Pro, and its gains carry over to held-out UI-Vision. Code is available at https://github.com/bcwang-sjtu/AdaGround

cs.CV · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.13494

SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping

Yu-Chen Lu, Sheng-Feng Yu, Hui-Hsien Weng, Pei-Shuo Wang, Yu-Fang Hu, Liang Hung-Chun, Hung-Yueh Chiang, Kai-Chiang Wu

原文摘要

Large language models (LLM) have achieved remarkable performance across a wide range of tasks. However, their substantial parameter sizes pose significant challenges for deployment on edge devices with limited computational and memory resources. Low-rank compression is a promising approach to address this issue, as it reduces both computational and memory costs, making LLM more suitable for resource-constrained environments. Nonetheless, naïve low-rank compression methods require a significant reduction in the retained rank to achieve meaningful memory and computation savings. For a low-rank model, the ranks need to be reduced by more than half to yield efficiency gains. Such aggressive truncation, however, typically results in substantial performance degradation. To address this trade-off, we propose SkipCat, a novel low-rank compression framework that enables the use of higher ranks while achieving the same compression rates. First, we introduce an intra-layer shared low-rank projection method, where multiple matrices that share the same input use a common projection. This reduces redundancy and improves compression efficiency. Second, we propose a block skipping technique that omits computations and memory transfers for selected sub-blocks within the low-rank decomposition. These two techniques jointly enable our compressed model to retain more effective ranks under the same compression budget. Experimental results show that, without any additional fine-tuning, our method outperforms previous low-rank compression approaches by 7% accuracy improvement on zero-shot tasks under the same compression rate. These results highlight the effectiveness of our rank-maximized compression strategy in preserving model performance under tight resource constraints.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2506.19846

HiMA-Ecom: A Long-Horizon Memory Benchmark for Hierarchical Multi-Agent E-commerce Assistants

Junxing Hu, Ai Han, Haolan Zhan, Pu Wei, Zhiqian Zhang, Yuhang Guo, Jiawei Lu, Zhen Chen 等 11 位作者

原文摘要

Long-horizon agentic systems become long-context systems by accumulation rather than through a single long document, since every step reassembles a prompt from role instructions, tool and sub-agent descriptions, recalled memories, dialogue history, and previous tool outputs, separately for every agent. This paper studies how such accumulated context can be trained, evaluated, and managed in hierarchical multi-agent assistants. We present HiMA-Ecom, a hierarchical multi-agent benchmark for e-commerce assistants with 22.8K instances, of which 17.7K carry memory entries in context, pairing agent-specific supervised fine-tuning data with system-level supervision for end-to-end multi-agent reinforcement learning. Building upon it, HiMA-R1 keeps the context budget of a trajectory under control through Variance-Reduction Group Relative Policy Optimization (VR-GRPO), which samples along an initial trajectory so that sampling cost grows additively with trajectory length and updates the agents with the largest reward variance, together with an efficiency reward on trajectory length and a memory evolution mechanism that repurposes GRPO rewards as cost-free signals for what stays in context. Agents built upon 3B and 7B open-source models match DeepSeek-R1 and surpass DeepSeek-V3 by 6.0 points on average, while reward-driven memory reduces the update steps needed for convergence by roughly 55%.

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 ↗
版本更新 · v2arXiv:2610.33078

Evaluating Visual Language Models on Visual Grounding for Visually Impaired People

Fairooz Azim, Lydia Achour, Claudia Borg, Lina Rojas-Barahona

原文摘要

Visual grounding (VG) in visual question answering (VQA) is a fundamental capability of Vision-Language Models (VLMs), enabling the detection of the most relevant region in an image to answer the question. This reflects the model's capability of multimodal comprehension, which is crucial when interacting with visually impaired people (VIP). Indeed, visual grounding, when applied to assistive scenarios, is not merely a technical feature, but rather a trust and safety requirement. In this work, we study visual grounding in VLMs for visually impaired people. To this end, we assess open-source VLMs on visual grounding using the VizWiz-VQA-Grounding dataset and challenge, which contains real-life images taken by VIP. We propose VG-SHAP, which extends an existing explainability framework to provide visual grounding explanations, allowing the evaluation of black-box VLMs. Our results on the VizWiz-VQA-Grounding challenge show that despite generating correct answers, VLMs struggle to ground in the proper region in the image. However, these results are constrained by the quality of the segmentation model of our explainability framework and further research is necessary.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36849

When All Rollouts Fail: Policy-Compatible Joint Decoding for Hard-Problem Reasoning

Zehao Wang, Hanzhu Chen, Runquan Gui, Zhe Wang, Lin Yang

原文摘要

Reinforcement Learning with Verifiable Rewards (RLVR) derives its learning signal from binary rewards via on-policy exploration and becomes a powerful paradigm for improving the reasoning of large language models. Yet it faces a learning cliff on problems beyond model's current ability: when every rollout fails, the samples reveal nothing about a correct solution, and group-relative estimators (e.g., GRPO, RLOO) collapse the update to zero advantage. Expert trajectories offer a remedy, but they are incompatible with the current policy and often lie in the student's low-probability regions, so the surviving updates demand large parameter shifts and decay into surface-level imitation rather than transferable reasoning. We argue that a useful learning signal on hard problems must be both verifiably correct and sufficiently compatible with the current policy. We propose Policy-Compatible Reinforcement Learning (PICO), which performs distribution-constrained joint decoding: expert data guides decoding at the token level while preserving the student's relative token probabilities, and a dynamic top-k mechanism confines the sampling distribution under a finite divergence budget, yielding trajectories that are verified and policy-compatible by construction. These trajectories are optimized jointly with on-policy rollouts under a mixed-behavior objective that mitigates their distribution mismatch via importance sampling. Experiments across reasoning diverse datasets and agentic benchmarks demonstrate that PICO consistently outperforms standard RLVR and prior off-policy baselines.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36848

Evolving Agent Teams

Shiyi Cao, Ziming Mao, Dacheng Li, Joseph E. Gonzalez, Ion Stoica

原文摘要

The rapid progress of software engineering agents drives interest in applying them to open-ended problems such as GPU kernel optimization. However, we find that existing coding agents converge to local optima on real-world, expert-written kernels (e.g., FlashInfer). We introduce Evolving Agent Teams, a multi-agent framework that escapes such local optima. It features (1) a central supervisor that diagnoses each local optimum and restructures a team of agents; and (2) a persistent file system that comprises a learning document, an evolution history, and per-team artifacts, grounding restructuring with accumulated experience. Under a matched token budget, Evolving Agent Teams consistently outperforms strong coding-agent baselines. With an extended token budget, Evolving Agent Teams generates a CUDA kernel that reaches 1.2x mean speedup over the production FlashInfer MLA paged decode kernel from scratch and wins on 36 of 47 production workloads from FlashInfer-Bench (0.86-0.99x on the remaining 11). It also demonstrates superior performance on tasks such as KDA prefill on AMD MI350X (3.01x over vLLM) and NVIDIA B200 (3.44x over FlashKDA), MoE expert-offload serving on Apple silicon (30.3 tokens/s decode for Qwen3.8-Flash-Next in MLX 4-bit on a 48 GB M4 Pro), and RoboDojo robot manipulation (62.1 on held-out seeds vs. 55.3 for the best leaderboard entry). Code is available at https://github.com/caoshiyi/EAT.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36847

Conservative Policy Iteration For Zero-Sum POSGs

Erwan C. Escudie, Matthia Sabatelli, Jilles Steeve Dibangoye

原文摘要

Occupancy-state reductions make dynamic programming possible for zero-sum partially observable stochastic games (zs-POSGs). Existing point-based solvers usually optimise a central value function. This restores Bellman recursion, but it requires point-based updates over high-dimensional occupancy spaces. We introduce an approximate policy-iteration algorithm for finite-horizon zs-POSGs. The method maintains one policy per player and updates both jointly along occupancy trajectories induced by conservative policy updates. Instead of approximating a full central value function, each update uses a single supporting hyperplane induced by the current joint policy. The algorithm alternates local policy improvements, conservative updates, and persistent exploration. Computation is therefore concentrated on occupancy regions where the current joint policy is exploitable. On finite-horizon zero-sum POSG benchmarks, the method is competitive at small horizons and often improves the runtime-exploitability trade-off at larger horizons compared with PBVI, HSVI, and CFR+.

cs.AI · cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.06286

LLMs Can Leak Training Data But Do They Want To? Evaluating Memorization Propensity in LLMs

Gianluca Barmina, Peter Schneider-Kamp, Lukas Galke Poech

原文摘要

Large language models can reproduce training data, but memorization evaluations mostly measure whether models can be made to do so, not whether they do so without adversarial prompting. We introduce PropMe, a framework that pairs a capability evaluation (prefix attacks) with non-adversarial propensity evaluation, and a propensity metric to relate the two. We check every generation against the model's full indexed training corpus with SimpleTrace, an open-source batch implementation of OLMoTrace span matching. We evaluate Comma, its continually pre-trained descendant DFM Decoder, and OLMo3 32B on Common Pile, Dynaword, and Dolma3, with four non-adversarial settings ranging from no prompt to sentences from unseen in-domain sources. Our results show that natural sentence prompts reproduce far less training text than prefix attacks. Generation with no prompt or a single common word, however, reproduces about as much as prefix attacks, or more, in three out of four model-corpus pairs; most of this text is duplicated licenses, code, and templates. In our setting, continual pre-training reduces long verbatim reproduction of the original corpus only modestly. More broadly, we argue that by testing both capability and propensity, we can attain a more comprehensive picture of a model's memorization behavior.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36826

When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement

Hao Chen, Yukun Yan, Ziyu Han, Ye He, Chuanzhe Guo, Shangzhan Li, Qi Shi, Qingfu Zhu 等 10 位作者

原文摘要

Autonomous agents increasingly depend on harnesses that govern interaction, memory, tools, and execution around large language models (LLMs). While recent work has begun to evolve these harnesses from execution experience, the supervision used to guide evolution often remains relatively static, making it difficult to track changing behavioral weaknesses across rounds and potentially limiting generalization to unseen tasks. To address this issue, we propose RuHarness, a rubric--harness co-evolution framework for continual agent self-improvement. RuHarness continually discovers and reassesses behavioral criteria from execution trajectories, prioritizes the most relevant unresolved weaknesses, and uses them to guide targeted harness updates while keeping the task objective fixed. Extensive experiments across diverse agent tasks and backbone models show that RuHarness outperforms strong harness-evolution baselines, particularly on unseen held-out tasks. Further analyses show that adaptive rubric prioritization tracks shifting weaknesses and supports more sustained improvement and stable generalization across evolution rounds.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2506.01183

Doubly Robust Alignment for Large Language Models

Erhan Xu, Kai Ye, Hongyi Zhou, Luhan Zhu, Francesco Quinzan, Chengchun Shi

原文摘要

This paper studies reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promising results, many algorithms are highly sensitive to misspecifications in the underlying preference model (e.g., the Bradley-Terry model), the reference policy, or the reward function, resulting in undesirable fine-tuning. To address model misspecification, we propose a doubly robust preference optimization algorithm that remains consistent when either the preference model or the reference policy is correctly specified (without requiring both). Our proposal demonstrates superior and more robust performance than state-of-the-art algorithms, both in theory and in practice. The code is available at https://github.com/DRPO4LLM/DRPO4LLM

cs.LG · cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36824

Who Knows What - and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mind

Ziqi Liao, Jiaqi Shen, Yiming Na, Kedi Lyu, Shao-Yuan Lo, Hongxia Xie

原文摘要

Theory of Mind (ToM), the ability to infer others' beliefs, goals, and intentions, is a cornerstone of social intelligence. Multimodal ToM requires inferring an agent's mental state from evidence that is available to that agent, rather than from the complete episode observed by the solver. Existing LLM-based and Bayesian model-based approaches reconstruct global event traces, yet they do not explicitly distinguish objective events from agent-admissible evidence during hypothesis evaluation. Consequently, agent-inaccessible events or semantically misaligned actions and utterances may influence the inferred belief, goal, or social intention, leading to perspective leakage and source or route confusion. We formulate this limitation as an evidence-admissibility problem: evidence should contribute to a mental-state hypothesis only when it is accessible to the relevant agent, preserves its information source, and is diagnostic of the queried mental-state variable. To operationalize this principle, we propose PIP-ToM, an evidence-admissibility interface that constructs agent-specific evidence stores, aligns them with structured mental-state claims, and calibrates model-based hypothesis scores while preserving the underlying Bayesian inference process. PIP-ToM with GPT-4o outperforms existing ToM methods across MuMA-ToM, MMToM-QA, and Hi-ToM, achieving average accuracies of 92.56%, 95.00%, and 95.00%, respectively.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36823

TAPESTRY: A Single Backbone for Video Generation and Robot Control

Jeremy A. Collins, Seungjae Lee, Rachanon Wachakorn, Krishnan Srinivasan, Animesh Garg, Vitor Campagnolo Guizilini, Paarth Shah

原文摘要

Pretrained video generation models encode rich priors about physical interactions, but leveraging them for robot control typically requires either resource-intensive video generation at test time or action heads trained from scratch that do not fully utilize the pretrained backbone. We introduce Tokenizing Actions as Video Patches in a Shared Transformer Policy (TAPESTRY), a world action model that repurposes a pretrained video diffusion transformer into a robotic policy without requiring video generation at inference. Our key idea is to treat robot actions as single-patch tokens in the video model's latent space. A lightweight linear projection maps each action timestep to the patch dimensions of the pretrained VAE, and the resulting tokens are processed by the same patchifying layers and transformer backbone used for video. The shared backbone is optimized through three diffusion objectives sampled per minibatch element: Video diffusion uses VAE latents from robot and human videos to establish dynamics priors. Joint video+action diffusion trains on robot demonstrations using a coupled diffusion timestep and an asymmetric attention mask. Action-only diffusion denoises actions conditioned on clean image latents. At test time, the model generates a compact action token sequence in a single DDIM step from pure noise, producing smooth action chunks at 84 ms per action chunk on consumer hardware and avoiding the cost of full video generation. Across simulation benchmarks and real-robot experiments, TAPESTRY achieves strong performance with substantially lower inference cost than comparable joint video--action policies. More information can be found at https://tapestry-wam.github.io.

cs.RO · cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36807

SetGRPO: Calibrating Grader-Induced Policy Optimization

Jiale Huang, Zixu Li, Zhiwei Chen, Zhiheng Fu, Jinhe Bi, Yupeng Hu

原文摘要

Rubric-based reinforcement learning uses fine-grained grader feedback to train large language models on open-ended tasks, but grader randomness can alter GRPO updates in ways that score discrepancies alone cannot characterize. Because GRPO jointly normalizes rewards within each response group and combines the resulting training coefficients with response-level gradients, a scoring discrepancy can shift the coefficients of the entire group and induce policy-dependent update changes. Selective execution further affects the direction-reversal risk of retained updates. To address this, we propose Set-Valued Group Relative Policy Optimization (SetGRPO). It comprises three modules: (a) Joint Reward Set Calibration constructs a joint uncertainty set for the training coefficients; (b) Geometry-Guided Safe Recovery maps candidate coefficients into the current policy's local update geometry and determines the largest safe recovery ratio for each response group; and (c) Selective Risk-Gated Optimization selects a global threshold through independent risk calibration to control the conditional direction-reversal risk of accepted updates while preserving the original GRPO objective. Under exchangeability, SetGRPO provides finite-sample marginal coverage for the joint coefficient set and simultaneous risk control across candidate thresholds. On ten open-ended benchmarks spanning three domains, SetGRPO achieves the highest macro average among all compared training methods on both Qwen3.5 and Llama3.2 model families.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2604.17866

Latent Abstraction for Retrieval-Augmented Generation

Ha Lan N. T, Minh-Anh Nguyen, Dung D. Le

原文摘要

Retrieval-Augmented Generation (RAG) has become a standard approach for enhancing large language models (LLMs) with external knowledge, mitigating hallucinations, and improving factuality. However, existing systems rely on generating natural language queries at each hop and maintaining a strict architectural separation between retriever and generator, preventing them from leveraging the full representational capacity of the LLM. We propose \textbf{LAnR} (Latent Abstraction for RAG), a unified framework in which a single LLM jointly performs encoding, retrieval, and generation entirely within its own latent space. Rather than generating textual queries, LAnR produces dense retrieval vectors from the hidden states of a designated \texttt{[PRED]} token and uses them to match against encoded document representations from the same model. Furthermore, LAnR adaptively decides when sufficient evidence has been retrieved using a lightweight MLP control head over those same hidden states, eliminating both the separate retriever and explicit token-level stopping reasoning. This design is motivated by our empirical observation that answer token entropy reliably signals retrieval sufficiency. Extensive experiments on six QA benchmarks spanning single-hop and multi-hop settings demonstrate that LAnR outperforms existing RAG methods, while achieving improved inference efficiency through reduced number of retrieval calls and tighter model integration.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v7arXiv:2512.14554

Benchmarking Vietnamese Legal Knowledge of Large Language Models

Nguyen Tien Dong, Minh-Anh Nguyen, Thanh Dat Hoang, Nguyen Tuan Ngoc, Dao Xuan Quang Minh, Phan Phi Hai, Nguyen Thi Ngoc Anh, Binh Vu 等 9 位作者

原文摘要

The rapid advancement of large language models (LLMs) has enabled new possibilities for applying artificial intelligence within the legal domain. Nonetheless, the complexity, hierarchical organization, and frequent revisions of Vietnamese legislation pose considerable challenges for evaluating how well these models interpret and utilize legal knowledge. To address this gap, the Vietnamese Legal Benchmark (VLegal-Bench) is introduced, the first comprehensive benchmark designed to systematically assess LLMs on Vietnamese legal tasks. Informed by Bloom's cognitive taxonomy, VLegal-Bench encompasses multiple levels of legal understanding through tasks designed to reflect practical usage scenarios. The benchmark comprises 10,450 samples generated through a rigorous annotation pipeline, where legal experts label and cross-validate each instance using our annotation system to ensure every sample is grounded in authoritative legal documents and mirrors real-world legal assistant workflows, including general legal questions and answers, retrieval-augmented generation, multi-step reasoning, and scenario-based problem solving tailored to Vietnamese law. By providing a standardized, transparent, and cognitively informed evaluation framework, VLegal-Bench establishes a solid foundation for assessing LLM performance in Vietnamese legal contexts and supports the development of more reliable, interpretable, and ethically aligned AI-assisted legal systems. To facilitate access and reproducibility, we provide a public landing page for this benchmark at https://vilegalbench.cmcai.vn/.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.21628

Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation

Kaiwen Wang, Frank Bieder, Yinzhe Shen, Carlos Fernandez, Jan-Hendrik Pauls, Omer Sahin Tas

原文摘要

Simulation-to-reality translation must bridge the appearance gap between synthetic and real domains while preserving structural and semantic consistency. Conditioning-based methods achieve spatial alignment but introduce computationally expensive control modules. Paired-data methods achieve realism but rely on complex synthesis pipelines, often altering scene geometry and semantics. Training-free editing methods avoid both constraints but lack a learned appearance prior, limiting their perceptual quality. Recently proposed phase-preserving diffusion presents a promising alternative, but Fourier-domain formulations are constrained by global spectral coupling. This coupling induces spatial artifacts such as ringing and boundary leakage, thereby degrading structural and semantic consistency. We introduce Wavelet Phase Diffusion, which addresses this through two components. First, we operate in the Dual-Tree Complex Wavelet Packet Transform domain, whose localized wavelet packets enable spatially adaptive phase injection without global spectral interference. Second, Low-Frequency Randomization (LFR) replaces the low-frequency packet, decoupling the model from the synthetic illumination prior and enabling in-distribution real-world appearance. Both components train on unpaired open-domain data, and introduce negligible inference overhead. The spatial locality further enables instance-level translation, where individual objects or regions are translated to photorealistic appearance independently while the surrounding scene remains untranslated. On vKITTI $\to$ KITTI image translation, $ψ$-PD outperforms prior methods in realism and semantic consistency while maintaining competitive structural alignment. For CARLA video translation, $ψ$-PD approaches the realism of paired-data methods while reducing VLM planner ADE and FDE by $5.4\%$ and $5.1\%$, respectively.

cs.AI · eess.IV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36795

An Algebra of Transformers

Yong Wang, Zhiyan Wang, Hexiao Kang

原文摘要

On the theoretic analyses on transforms, they mainly focus on the computability analysis, such the Turing-completeness of unbounded precision transformers, the advantage of parallelizability of unbounded precision transformers and the limitations of bounded precision transformers. This paper give transformers an algebra for reasoning, which relies heavily on the functional decomposition results of transformers. This algebra uses functional decompositions as atomic actions, includes sequential composition and parallel composition, recursion for feedback and abstraction for hidden layers. As we know, it is the first attempt to model transformers logically and can be used to verify the correctness of transformer based applications.

cs.LO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36794

Select-TTT: Query-Conditioned Selective Fast Weight Updates for In-Place Test-Time Training

Yue Wu, Yang Zhang, Weinan Gan, Chongming Gao, Xinsen Guo, Xiaoyuan Li, Fuli Feng

原文摘要

Test-time training (TTT) enables a deployed language model to internalize incoming context on-the-fly into a small set of fast-weight parameters, rather than merely treating it as transient context for attention. In-Place TTT recently made this idea practical for large language models by repurposing the down-projection of standard MLP blocks as fast weights. However, we find that its benefit largely disappears on realistic web long-context question answering. We attribute this to In-Place TTT's uniform write schedule: every chunk is written with equal strength, so irrelevant content dilutes query-relevant information in fast-weight memory. Building on this insight, we propose Select-TTT, a model-agnostic, query-conditioned rule for In-Place TTT that scales each chunk's write strength by its relevance to the user query. This relevance signal requires no supervision and no new parameters: it is read directly from the model's frozen output head, as the probability mass that a chunk's hidden states assign to the query tokens. A temperature-scaled softmax turns these scores into learning-rate multipliers, leaving the chunk-wise, context-parallel computation of In-Place TTT intact. Select-TTT consistently improves long-context question answering on two benchmarks and two backbones. These findings highlight the value of query-conditioned fast weight writes for practical test-time training on long-context question answering, which is also potentially promising for long-horizon agent tasks involving multiple user queries over evolving contexts.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31850

Rethinking Multi-View Fusion for Urban Representation Learning

Sean Bin Yang, Zongyi Xu, Jilin Hu, Ying Sun, Kristian Torp, Bin Yang, Torben Bach Pedersen, Christian S. Jensen

原文摘要

Urban region representation learning encodes heterogeneous urban signals, such as mobility flows, points of interest, and land-use patterns, into unified embeddings for downstream tasks, including check-in prediction, crime forecasting, and service demand estimation. Existing approaches rely on globally shared fusion and joint optimization, implicitly assuming uniform modality importance and naturally balanced multi-objective training. However, urban data is inherently heterogeneous. Our empirical analysis reveals two structural issues: (i) modality utility varies markedly across regions, causing static fusion to overemphasize signals from certain modalities; and (ii) heterogeneous objectives exhibit persistent gradient imbalance, causing representational bias and unstable training. We present PRISM, a self-adjusting framework for adaptive multi-view learning. PRISM adapts sparse Mixture-of-Experts (MoE) routing to learn region-specific view allocations, while a Proportional-Integral-Derivative (PID)-inspired regulation mechanism mitigates gradient conflicts during optimization. Experiments on three large-scale urban datasets show that PRISM achieves more competitive performance than strong multi-view baselines, while providing more stable optimization behavior and more balanced region representations.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36776

Dependency Graphs of Mathematical Arguments: Representation, Structural Measurement, and Proof Review

Eunji Park

原文摘要

We propose a source-grounded framework for representing and measuring mathematical arguments with assistance from large language models. It includes numbered and unnumbered statements, equations, assumptions, and constructions, distinguishing source occurrences from contextual states and inference records. Proposed dependencies retain source evidence and review status. A measurement contract fixes manuscript versions, boundaries, granularity, proof choices, and macro anchors. On a selected finite directed acyclic graph, depth is the longest prerequisite-path length, and bulk counts distinct ancestor edges. We give a union recurrence that accounts for shared subarguments and identify reachability conditions preserving depth and the macro skeleton; unrestricted refinement need not preserve depth or bulk. A standardized, versioned prompt protocol separates annotation discovery, deterministic recomputation, and review assistance. Cross-paper links support a research agenda on theorem co-use, rare combinations, and connections between dependency communities. These patterns motivate probabilistic premise suggestions and review of possible omissions or unchecked application conditions in human-written and AI-generated proofs. Further applications include source-linked reading support and comparison of individual and collaborative argument shapes. We provide an evaluation design rather than empirical evidence of these benefits. Suggested premises require mathematical validation, and the measures describe a specified representation rather than intrinsic mathematical difficulty, originality, or importance.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.28160

From Code Generator to Engineering Companion: A Plant-aware Agent for PLC Programming

Joschka Kersting, Gesa Benndorf

原文摘要

Programmable Logic Controller (PLC) coding remains a manual, IDE-centric task that demands constant context switching between documentation, project files, and code editors. Recent work has demonstrated that retrieval-augmented large language models can generate vendor-compliant Structured Text at high compilation rates, yet these systems treat code generation as a one-shot pipeline: the engineer submits a query and receives code, with no persistent knowledge of the specific plant. We present a plant-aware conversational copilot that extends this paradigm in three directions: plant-specific context ingestion, a chat-first interaction model for explanation and debugging, and a graduated tool-access ladder from chat to deployment. The system is designed for real plant infrastructure and keeps the engineer in control of each step that produces real-world effects.

cs.SE · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36774

Batching the Reflective Optimization Loop: Parallel Proposals Make GEPA Faster and Better

Jialin Zhang, Lakshya A Agrawal, Shangyin Tan, Donghyun Lee, Lutfi Eren Erdogan, Dan Klein, Koushik Sen, Alex Dimakis 等 9 位作者

原文摘要

Reflective text optimization makes agentic systems better, but the optimization loop is itself a resource-hungry workload whose sequential structure leaves parallel evaluation capacity idle. We extend the open-source GEPA optimizer to propose and evaluate a batch of candidates on each optimization step instead of one candidate at a time. In our sweep on two tasks, most batched runs finished in half the wall-clock time or less, and the fastest in about a quarter to a third. Batched settings also achieved higher held-out test scores, from 68.9% to 72.1% on LiveBench-Math (with $2\times2$) and from 49.0% to 60.0% on HoVer (with $8\times1$). A simple runtime model explains the measured speedups under a finite worker pool, and batched settings also spend their metric-call and dollar budgets more efficiently. We frame the axes along which a reflective optimization step can scale in parallel, a first look at allocating a fixed optimization budget across them.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.22508

Distilling Metacognitive Behaviors through Agentic Editing

Ik-hwan Kim, Hyeongrok Han, Mingi Jung, Sangwon Yu, Jinseok Hong, Sang Hun Kim, Yoonyoung Choi, Sungroh Yoon

原文摘要

Distilling long reasoning traces from a teacher model into a smaller student also passes on the teacher's reasoning habits. Prior work and our annotation of teacher traces show that current reasoning models often start without a plan, verify superficially, abandon promising solution paths, and take unchecked shortcuts. We propose Metacognitive Behavioral Tuning (MBT), which inserts seven metacognitive behaviors into teacher traces at the points where the reasoning lacks them and then trains the student on the edited traces. Because teacher traces are long, how the edits are made matters. Rewriting a whole trace at once summarizes long traces, and choosing all insertion points at once crowds them at the start and end. Our agentic method, MBT-A, edits the trace file line by line and records each edit as a git commit, which avoids summarizing long traces and spreads the insertions. On competition math, a Qwen3.5-4B-Base student trained on MBT-A traces scores 85.4 against 83.1 for SFT on the unedited traces and also outperforms a token-matched control and five prior methods. MBT-A improves two other students as well, and the inserted behaviors clearly transfer to the students' reasoning, with rare ones several times more frequent.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36767

Can LLMs Reliably Grade Olympiad Proofs? A Study of Mathematical Verification with LLMs

Azim Ospanov, Zijin Feng, Ding Ding, Chengwu Liu, Haoli Bai, Jiacheng Sun, Lifeng Shang, Farzan Farnia

原文摘要

Large Language Models (LLMs) have made remarkable progress on solving competition-level mathematics, yet their ability to verify natural-language mathematical proofs remains relatively underexplored. This gap is especially pronounced for Olympiad-level proofs, which require meticulous assessment of each claim in a long reasoning chain. Current proof verification thus primarily relies on expert inspection, which is costly to scale. In this paper, we present a systematic study of LLM-based verification in this setting. Specifically, we introduce a human-curated dataset of USAMO 2025 candidate solutions with expert grading, and conduct a broad evaluation of existing LLM verifiers across frontier models. We also propose TROJAN, an iterative self-critique pipeline for generating high-fidelity adversarial proofs at scale. Our comprehensive evaluation covers 20 models spanning seven metrics, two prompt styles, three inference methods, and three prompt templates, showing that state-of-the-art models still leave considerable room for improvement. To narrow this gap, we propose MABGrader, a Multi-Armed Bandit framework that reframes grading as arm selection over the discrete score space. MABGrader outperforms the SOTA ProofGrader by 26.4% in Quadratic Weighted Kappa and reduces grading error by 14%. Code and dataset are available at https://github.com/aziksh-ospanov/TROJAN.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34365

SEEK: Skill Extraction with Evolving Knowledge against Frontier Science Agents

Cheng Gui, Xiang Zheng, Yutao Wu, Hanxun Huang, Yige Li, Kaidi Xu, Cong Wang, Wei-Ying Ma

原文摘要

Science agents increasingly package domain expertise as reusable skills that plan analyses, select tools, and execute workflows. This modularity creates a confidentiality risk: the interactions that deliver a skill's capability can also reveal the skill itself. We build an extensible benchmark of 40 protected skills across eight open- and closed-source science-agent platforms, comparing direct, fixed-strategy, and bandit-guided iterative probing under reference-based and reference-free evaluation. Leakage is pervasive: all eight platforms (100%) leak at least one protected skill, and four reach 100% attack success under a single direct request. To stress-test platforms that resist simple probing, we propose SEEK (Skill Extraction with Evolving Knowledge), a black-box, self-evolving red-teaming agent that consolidates response-derived evidence in persistent memory and evolves reusable attack skills, using only user-visible responses. On 12 skills from SpatialAgent and Biomni, SEEK achieves 100% attack success while reducing the mean first-success round by 31.8% and 38.2% relative to bandit-guided probing. Against a confidentiality policy that blocks all three benchmark protocols, SEEK still extracts one of six protected skills. These findings show that current science agents do not reliably protect their skills and that defenses must be evaluated against adaptive, multi-turn attackers.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗