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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 13:24 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 13:53 — 2026-11-09 13:53（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 13:24最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 3,653 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 13:22（北京时间）
版本更新 · v2arXiv:2609.32596

GAUGE: Group-Wise View-Inconsistency Rectification for Feed-Forward 4D Tracking

Zhuoqian Feng, Weixing Chen, Ziliang Chen, Yang Liu, Liang Lin

原文摘要

Feed-forward models regress dense 3D point trajectories directly from monocular video, yet the residual after global alignment is substantial and lacks a structural explanation. Measured on dynamic query points across models and datasets, the error concentrates along the view direction, while the scale correction each motion group requires differs. The predicted displacement direction nevertheless supports reliable grouping, with a median angle far below the 90° random baseline. The systematic part of the residual is therefore a family of radial degrees of freedom per motion group, along directions 2D observations cannot constrain. We call it group-wise view inconsistency. We present GAUGE (Group-wise Adaptive Unsupervised Gauge Estimation), a training-free and model-agnostic post-hoc module. It recovers motion groups from direction consistency and spatial connectivity, then estimates a per-frame radial scale and group-level translation from 1% to 5% metric anchors, four degrees of freedom per group and frame. On dynamic query points of eight trackers, including D4RT, 4RC and SM4RT, our correction lowers endpoint error by 15.1% to 62.6% over the uncorrected predictions, while spending the same anchors on gradient fine-tuning improves the same models by only -1.1% to 15.2%. Code is publicly available at https://github.com/HCPLab-SYSU/GAUGE.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.10780

How K-12 Teachers Adapt Generative AI to Local Classroom Demands: Cultural Distance Between GenAI Defaults and Everyday Teaching Practices

Qing Xiao, Ruiwei Xiao, Hanqi Jane Li, Phenyo Phemelo Moletsane, Xinying Hou, John Stamper, Hong Shen

原文摘要

Generative AI (GenAI) is entering K-12 classrooms, but its default culture does not always fit local teaching. Existing accounts either treat this misfit as macro-level structural bias or examine it through single-case studies; neither captures how much work teachers must do to make outputs usable across tasks. This exploratory, theory-building qualitative study introduces cultural distance, the gap between GenAI's default cultural repertoire and the situated demands of teachers' practice. Through interviews with 30 K-12 teachers who frequently use GenAI, 10 each from South Africa, Taiwan, and the United States, we identified three levels defined by the effort teachers invested and whether it yielded a usable output: low (minor edits), mid (sustained prompting and revision), and high (structural gaps rooted in unsupported languages, undigitized knowledge, or policy filters that no teacher effort can close). We present cultural distance as a promising framework requiring further examination and draw implications for designers, policymakers, and educators.

cs.HC · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36511

Do AI Scientists Know What's New?

Miri Liu, Xiayu Zhao, Encheng Xie, ChengXiang Zhai

原文摘要

A major challenge facing AI scientific discovery pipelines is how to determine when a generated idea is meaningfully novel. Ideally, novelty checks in these pipelines must be able to reject non-novel ideas while not rejecting too many novel ideas, and they should also be able to distinguish which parts of a proposal are non-novel, as opposed to opaquely discarding entire proposals. We design an analytical framework for evaluation of novelty checks with temporal ground truth at both the proposal- and claim-level, using four datasets of 1,060 proposals built from published papers, reviewer disputes, and generated ideas matching ones the field went on to publish. Auditing existing novelty checks with this framework, we find that checks with high rejection rates on non-novel work also tend to have high false alarms on ideas that are later realized by human researchers, and observe that checks built to evaluate proposals as a whole can point to claim-level prior art only by rejecting the whole proposal. We therefore introduce ClaimNov, a fine-grained, interpretable claim-level novelty module. ClaimNov catches 97% of disguised papers at a 1.5% false-alarm rate, and its claim-level novelty profile cuts the LLM judge's false alarms from 11.8% to 1.5%. Because its verdict rests on claim-level evidence, ClaimNov also keeps proposals that build on established contributions, rejecting only 3% of ICLR-accepted proposals with a reviewer-disputed contribution and keeping 91 of 100 novel proposals with one spliced prior contribution, against 76 for the strongest existing check. Code and data are available at https://github.com/emmatliu/claimnov.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34817

Silent and Costly: Characterizing and Detecting Prompt-Caching Mis-Integration in LLM Agents

Ying Zhang, Ruoqi Guo, Yi Liu, Gelei Deng, Yuekang Li, Yepang Liu, Leo Zhang

原文摘要

Large language model (LLM) services process massive volumes of user requests, resulting in substantial inference costs. To reduce both cost and latency, providers have introduced prompt caching. However, correctly integrating prompt caching is non-trivial due to heterogeneous provider-specific APIs and continuously evolving caching semantics. To understand prompt-caching mis-integration in downstream applications, we conduct the first empirical study of 120 prompt-caching-related pull requests from 10 popular open-source agent systems. Our findings show that prompt-caching mis-integrations arise in both request-side misconfiguration and read-side usage miscount. More importantly, most mis-integrations fail silently without causing observable runtime failures. Motivated by these findings, we design CACHELINT, which models a prompt-caching mis-integration as an invocation site together with the preconditions required for correct cache integration. CACHELINT locates caching invocation sites with CodeQL and discharges each precondition either against a dated provider capability oracle or with an LLM guard check. CACHELINT achieves 0.71 precision and 0.78 recall in identifying the 120 labeled mis-integrations across the 10 studied agent systems. Our evaluation further demonstrates the effectiveness of CACHELINT in real-world settings, identifying 32 mis-integrations across 571 agent projects with 0.86 precision. These findings have received 21 developer confirmations and led to 18 upstream fixes, including one in Anthropic's official SDK.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36499

ProCerDCL: Query-Efficient Black-Box Probabilistic Verification of Deep Learning Compiler Optimization

Zexin Li, Weibo Zhang, Linyi Li, Arvind Easwaran, Simin Chen

原文摘要

We present \tool, a query-efficient framework for black-box probabilistic verification. Given a fixed, sampleable input distribution and a binary property oracle, \tool assesses the property's violation probability $p$ against a threshold $θ$. Under independent sampling and stateless oracle behavior, acceptance asserts $p\leθ$, rejection asserts $p>θ+η$ for a user-specified separation margin, and an inconclusive verdict indicates insufficient evidence for either conclusion. The probability of each type of erroneous verdict is bounded by its specified error budget. To support this three-valued contract efficiently, \tool uses a single sequential test, eliminating the interval family required by the baseline. The test accounts for repeated sampling checks through either corrected exact binomial confidence intervals or an anytime-valid confidence sequence. We apply \tool to probabilistic local model semantic consistency, where the property oracle detects decision-level inconsistencies between reference and compiled executions under a specified perturbation distribution. Our evaluation covers 24 tasks across TorchInductor and TensorRT and examines sampling efficiency, conclusiveness, and diagnostic behavior. For sampling efficiency, we use paired one-model clean-label radius searches: the baseline requires 3.6-4.2 times as many unique samples under matched numerical parameters while providing a weaker decision contract. For model semantic consistency, checks at $θ=10^{-3}$ yield 817 acceptances, 19 inconclusive verdicts, and 4 rejections across 840 input--backend instances from 21 tasks. Case studies of two documented compiler faults further demonstrate what these local verdicts can diagnose.

cs.SE · cs.AI · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36493

AC-JEPA: Anchored Cross-Modal Joint Embedding Predictive Architecture for Visual-to-Symbolic Translation

Chaofei Hong, Ziyang Chen, Baochen Wang, Christina Yi Jin, Qing Zhang

原文摘要

Cross-modal translation requires models to capture shared semantics across modalities while preserving the fine-grained structure required by the target modality. Yet in real-world scientific domains, paired data are often imperfect, while obtaining clean pairs at scale is costly. Supervised fine-tuning (SFT) directly optimizes cross-modal translation through categorical token-level supervision, but this objective is sensitive to errors in the target sequences. JEPA offers a complementary representation-space objective, but most existing formulations focus on prediction within a modality rather than translation across modalities. We introduce Anchored Cross-Modal JEPA (AC-JEPA), an SFT-compatible plug-in that predicts masked intermediate states in both cross-modal directions using paired data. The joint-embedding objective targets cross-modal structure predictable from context, while the causal SFT path retains direct token-level supervision for the target sequence. During self-training, AC-JEPA learns from continuous latent targets derived from imperfect pseudo-labeled pairs, offering intrinsic tolerance to local data errors without promoting pseudo-tokens to hard categorical supervision. Using optical chemical structure recognition as a testbed, AC-JEPA trained on clean pairs achieves 76.07% accuracy on the Simple set of the WildMol benchmark, compared with 67.40% for SFT alone. Using the same pseudo-labeled data for both approaches, AC-JEPA-based self-training further raises accuracy to 80.23%, whereas accuracy under direct SFT drops from 67.40% to 63.47%. These results support SFT-anchored joint-embedding prediction as an effective strategy for cross-modal translation under both curated and imperfect supervision.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.03385

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation

Jiahao Xu, Peiyuan Wang, Hanzhuo Zhang, Zihao Yu, Tianyu Fu, Hao Chen, Xuanhao Xiang, Zixuan Li 等 11 位作者

原文摘要

In robotic manipulation, the tight coupling between grasping and motion planning often obscures the true source of failure, leading to inefficient trial-and-error. To enable efficient long-horizon manipulation, we propose GTP-FA (Grasp-Then-Plan with Failure Attribution), a task-oriented two-stage 'grasp-then-plan' framework that generates grasp candidates and performs downstream motion planning conditioned on the selected grasp. Given a failed manipulation trajectory, we learn a failure attribution model that generalizes to unseen grasps and produces a stable distribution over failure modes for diagnosis-guided optimization. Based on these attribution results, we then optimize both modules in a diagnosis-driven manner: on the grasping side, we inject task-level priors and risk penalties into grasp candidate scoring and optimization to suppress unstable or task-incompatible grasps; on the planning side, we target high-risk initial states through data collection and fine-tuning to address genuine planning bottlenecks. We evaluate the proposed framework in both simulation and real-robot experiments, and show that GTP-FA improves the corresponding base learners across RL, IL, diffusion-policy, and VLA-based settings, achieving substantially higher overall task success rates.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36484

CogArena: Benchmarking Multimodal Agents on Interactive Behavioral Experiments

Kianté Fernandez, Caitlin Chen, Jialu Zhou, Bartek Sadowski, Anthony C. Miceli, Ian Krajbich

原文摘要

Claims about the cognitive capabilities of large language models are typically tested by translating behavioral paradigms into text prompts, bypassing the visual interfaces and time pressure through which human participants actually engage with experiments. At the same time, AI agents can now complete online behavioral tasks and produce human-like data, which raises concerns that online datasets in the social and behavioral sciences are increasingly open to contamination. We introduce CogArena, a benchmark of ten experimental paradigms from the social and behavioral sciences. Agents complete the experiments through a standard web browser, working with the same visual stimuli and response interfaces that online participants use. A three-level scoring procedure evaluates whether the agent completed the task, how accurately it performed, and whether its data show the behavioral signatures each paradigm reliably produces in people. Across four multimodal models, each run ten times per task, we find that finishing an experiment and reproducing its signatures are different things. Many sessions did not finish, and those that did reproduced some signatures reliably and others not at all. CogArena provides the tasks, scoring code, and a public leaderboard for new submissions.

cs.AI · cs.CY · cs.HC · q-bio.NC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.02727

Foreground-Aware Dataset Distillation via Dual-Path Patch Selection

Mingzhuo Li, Guang Li, Longzhen Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama

原文摘要

In this paper, we propose a foreground-aware dataset distillation method that performs content-adaptive dual-path patch selection. With the rising computational cost of training large-scale deep models, dataset distillation has emerged as a promising approach for constructing compact synthetic datasets that retain knowledge from large original datasets. Although optimization-based methods can achieve strong performance, they often incur considerable computational and memory costs and may produce synthetic images that generalize poorly across architectures. Recent non-optimization-based methods alleviate these limitations by constructing distilled images from real-image patches. However, their inflexible patch-construction strategies may either retain redundant background content or discard important foreground structures. To address this issue, we propose a foreground-aware dataset distillation framework with content-adaptive dual-path patch selection. We first use Grounded SAM2 to estimate the foreground occupancy of each image and derive category-specific routing thresholds from the corresponding class-wise distributions. Each image is routed to one of two complementary paths: the candidate-crop selection path for images with relatively sparse foregrounds, or the direct transformation path for images with relatively dominant foregrounds. This dual-path mechanism balances foreground concentration and preservation, reducing redundant background content while retaining the structural integrity of foreground objects at the dataset level. Experiments on CIFAR-10, CIFAR-100, ImageNette, and ImageWoof with two network architectures and three distillation budgets demonstrate that the proposed method outperforms the baseline method RDED in nearly all evaluated settings.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.12868

Counting Clues: A Lightweight Probabilistic Baseline Can Match an LLM

Furong Jia, Yuan Pu, Finn Guo, Monica Agrawal

原文摘要

Large language models (LLMs) excel on multiple-choice clinical diagnosis benchmarks, yet it is unclear how much of this performance reflects underlying probabilistic reasoning. We study this through questions from MedQA that ask for the most likely diagnosis. We introduce Frequency-Based Probabilistic Ranker (FBPR), a lightweight method that scores options with a smoothed Naive Bayes over concept-diagnosis co-occurrence statistics from a large corpus. When co-occurrence statistics are sourced from Dolma, the pretraining corpus for OLMo, and RedPajama, an open reproduction of the LLaMA pretraining-data recipe, FBPR achieves comparable performance to the corresponding LLMs. Furthermore, direct LLM inference and FBPR exhibit complementary strengths, correctly answering largely different subsets of questions with overlap barely above chance. Combining them with a simple hybrid method yields a notable gain over either method alone. These findings show that explicit probabilistic baselines can account for a substantial portion of the benchmark performance on diagnosis questions, while serving as historically grounded reference points and complementary signals for hybridization.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.29968

CulturalRiddles: A Multicultural Benchmark of Riddles

My Chiffon Nguyen, Tianyi Hu, Vinod Anbalagan, Henry Gagnier, Pouya Sadeghi, Farah Abdou, Tidor-Vlad Pricope, Diego MMS Oliveira 等 164 位作者

原文摘要

As LLMs expand their language coverage, evaluating how well they understand and represent diverse cultures becomes increasingly important. However, many benchmarks remain English-centric, with limited cultural coverage and a focus on factual knowledge over its application in real-world cultural contexts. We propose CulturalRiddles, a benchmark of original, culturally grounded riddles created entirely by humans through a participatory community effort, spanning 62 cultures (45 countries, 51 languages). These riddles are deeply rooted in their respective cultures and require abductive and compositional reasoning, alongside detailed factual and social knowledge, language skills, and an understanding of culturally specific associations. We benchmark 28 LLM configurations using both automatic and large-scale human evaluation. Even frontier models achieve at most 22% accuracy in some communities. We publicly release all artifacts alongside an open contribution process to expand the benchmark's linguistic and cultural coverage.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36476

FIDES-Live: Evaluating Behavioral Concordance in Sequential Trading Agents

Arther Tian, Alex Ding, Simon Wu, Aaron Chan

原文摘要

Sequential trading agents produce decisions, orders, execution receipts, account states, and reports that need not agree, even when the final portfolio value is correctly computed. We present FIDES-Live, an operational extension of FIDES from generated strategy concordance to the audit of sequential agent traces. The protocol separates structured decision validity, optional numerical commitment adherence, execution and ledger reconciliation, and receipt- grounded reporting, with explicit coverage and unscorable outcomes. We retrospectively audit ten requested inference routes over 7,299 cryptocurrency account-rounds and a 310-round equity pilot, using real market observations and local paper execution. Cryptocurrency decision validity is 97.35% and structured reporting accuracy is 90.81% among scorable responses, but route-level decision and reporting performance can diverge sharply. Commitment adherence is 94.36% overall; it falls to 62.63% on constraints emitted with nonempty order proposals, compared with 97.56% for valid empty proposals. All retained cash and position transitions reconcile with recorded fills, while execution controls and unavailable quotes explain separate rejection populations. Short-window marked returns provide descriptive context rather than a new test of whether concordance predicts alpha. These observations motivate reporting concordance, evidence coverage, activity, and financial outcomes separately. They do not establish long-run trading skill, semantic faithfulness of explanations, or causal benefits from audit feedback.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.13008

Provenance-Aware Belief Updating in Human-AI Feedback Loops

Tianyi Huang, Eric Liu, Jay Chong, Emily Yin, Wanqi Zhao

原文摘要

In repeated human-AI interaction, a single observation can be quoted, summarized, and returned to a model as multiple reports, making repetition look like independent corroboration. We study whether language models can use supplied report lineage to update according to evidence provenance rather than report count. We introduce Latent Quotient Evidence Training (LQET), a relational objective that combines sparse Bayesian supervision with constraints that encourage stable predictions when reports add no new evidence and consistent updates to the same new evidence across relay histories. On a controlled binary benchmark, LQET reduces new-evidence update RMSE by 41-44\% and log-odds drift after eight relay steps by 89-91\% relative to task-only training across Qwen3-4B and Phi-4-mini, with three paired training seeds per backbone. The gains extend to a closed-loop simulation in which model confidence controls how many relayed reports re-enter the model's context in later rounds. By grounding belief updates in supplied provenance, LQET offers a route toward dynamic human-AI systems in which influence follows new evidence, not the number of times the same evidence returns.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2310.03186

Inferring Inference

Rajkumar Vasudeva Raju, Zhe Li, Scott Linderman, Xaq Pitkow

原文摘要

Patterns of microcircuitry in the cerebral cortex suggest that the brain has an array of repeated canonical computational units. However, neural representations are distributed, so the relevant computations may only be related indirectly to single-neuron transformations. It thus remains an open challenge how to define canonical distributed computations. Here we integrate normative and algorithmic theories of neural computation to present a mathematical framework for inferring canonical distributed computations from large-scale neural activity patterns. At the normative level, we hypothesize that the brain learns a structured internal model of its environment and its latent causes. At the algorithmic level, we propose that this inference process is a nonlinear message-passing algorithm on a graph-structured model of the world. Given a time series of neural activity during a perceptual inference task, our analysis framework finds (i) the neural representation of the relevant latent variables, (ii) interactions between these latent variables that define the brain's internal model of the world, and (iii) message functions that specify the inference algorithm. With enough data, key computational properties are identifiable due to constraints from the symmetries inherent in any canonical computation, up to a joint global transformation of all interactions and the message-passing functions. As a demonstration of this framework, we analyze artificial neural recordings generated by a simulated brain that implicitly implements an approximate inference algorithm. Given simulated inputs and neural activity we successfully recover the latent variables, their neural representation and dynamics, and canonical message functions that govern the dynamics. Analysis of these models reveals features of experimental design required to extract canonical computations from neural data.

q-bio.NC · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36471

When to Intervene? An Empirical Study of Errors and Self-Recovery in LLM Agents

Chiming Duan, Tong Jia, Yingxi Chen, Minghua He, Lingzhe Zhang, Ying Li

原文摘要

LLM agents interact with Web services to perform tasks on users' behalf. Errors during these interactions can disrupt execution and prevent task completion, motivating external intervention. However, agents may self-recover through continued execution, raising the question of when to intervene and when to wait for self-recovery. We present an empirical study of errors and self-recovery in LLM agents. We construct ReInBench, a dataset containing 1,259 agent traces and 1,403 error events across computer-use and Web tasks. Our study examines how often and how quickly agents self-recover, how self-recovery relates to subsequent execution and task completion, and whether self-recovery can be predicted when an error occurs. We find that 725 error events self-recover, often within a few steps, with self-recovery performance differing across Execution LLMs. Self-recovery can also help agents recover from subsequent errors of the same type and support overall task completion. Intervention should therefore prioritize errors unlikely to self-recover, while allowing agents to continue when self-recovery is likely. Building on these empirical findings, we propose ReCoF, a method that predicts whether an error will self-recover to inform whether additional intervention is needed. ReCoF achieves an average relative improvement of 9.02% in Macro-F1 over the strongest baseline on ReInBench. Our code and data can be found at https://method-notes.github.io/ReCoF/.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36456HF 社区推荐

LociArt: A Unified Paradigm for Free-Style Local Video Stylization

Yuxuan Chen, Feng Xie, Jiagao Hu, Fuhao Li, Zepeng Wang, Fei Wang, Daiguo Zhou

原文摘要

Video stylization typically transforms entire scenes, while local artistic editing requires precise region--style association, spatial control, and temporal consistency. We introduce LociArt, a unified paradigm for free-style local video stylization that explicitly specifies where to stylize and what style to apply while preserving non-target content. At its core, GRNStyle builds on Generative Refinement Networks (GRN) and introduces a polar style-aware mask that embeds style identities as equal-norm directions within selected regions. Complementary representation--geometry conditioning combines encoded mask features with raw-mask spatial support, integrating spatiotemporal context with geometric control. To provide paired supervision, we develop an automated pipeline combining global stylization, video object removal, matting, and compositing, and construct the LociArt-100K Dataset with 100K local stylization pairs. We further establish the LociArt Benchmark, comprising 80 source videos and 84 target masks covering 168 foreground/background stylization cases, with a Style Prototype Similarity (SPS) evaluation scheme for regional style quality and complementary measures of non-target preservation and temporal consistency. Experiments show that GRNStyle outperforms existing methods in regional style quality and spatial control while maintaining strong temporal consistency. Qualitative examples further illustrate joint stylization of multiple regions with the same or different learned styles, despite training only on single-region, single-style pairs. Together, these components provide a unified foundation for learning and evaluating controllable local video stylization. Project page: https://higherhu.github.io/lociart/.

cs.CV · cs.AI · cs.MM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36453

Correction or Manipulation? Measuring Epistemic Vigilance in LLM Agents Under User Pressure

Nardine Basta, Venus Haghighi, Dali Kaafar, Amin Beheshti

原文摘要

LLM agents that answer questions and act on behalf of users must decide when to yield to a user who disagrees. Disagreement may correct a genuine error or may be an attempt at manipulation. Prior work shows that models frequently abandon correct answers when challenged by users, yet it remains unclear whether they distinguish correction from manipulation or merely differ in their propensity to concede. We examine this question across seven LLMs from four vendors in two studies, one on the answers agents give and one on the actions they take as customer-support agents whose policy permits account changes only for verified users. Simulated users push toward correct and incorrect answers with graded pressure. Following research on epistemic vigilance, the pressure either appeals to the source, such as claimed authority, or offers content the agent cannot verify, namely a cited source. Drawing on signal detection theory, we measure on a set of benchmark questions how much more readily each agent concedes to correction than to manipulation, separately from its overall propensity to concede. Citations made five of seven models readier to concede and four worse at discriminating, while stronger wording added little. In the agentic study, five models never violated the verification policy, including models that readily abandoned correct answers, so concession on answers did not predict violations of policy. Ministral 3B violated the policy mainly under claimed authority, and Ministral 8B reported changes it had not made. An instruction to revise only on verifiable evidence chiefly shifted propensity to concede rather than improving discrimination. Concession rates alone are therefore misleading, and agents should be evaluated on both their discrimination and the actions they take.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31895

Knowing When to Stop: The Evidence-Action Gap in Coding Agents

Tianyu Chen, Xinran Zhao, Vijay Viswanathan, Shoubin Yu, Mingyuan Zhou, Tongshuang Wu

原文摘要

Coding agents are trained to complete tasks, and they keep trying even when the environment makes completion impossible. The evidence that only outside help can restore progress usually appears within a few steps, yet agents rarely act on it: they over-persist, attempt undesired workarounds, and claim success the record does not support -- a phenomenon we call evidence-action gap. To measure it, we introduce ImpasseBench, which injects twelve realistic environment blockers into otherwise solvable repair tasks and marks, in each trajectory, the step at which the collected evidence becomes sufficient. Scoring actions relative to that step separates appropriate effort from over-persistence and premature handoff. Across eight frontier models and 19,371 trajectories, we find that nearly every run that needs outside help collects sufficient evidence, yet a third still exhaust their budget, and every unsafe request we detect comes after that point. Fortunately, an escalation tool, or an external monitor for models that ignore the tool, already guards against much of this behavior: the tool cuts budget exhaustion from 34.0% to 6.7%, and the monitor nearly triples task success after environment restoration. Even then, a fired escalation is not yet a useful handoff: tickets reliably name the blocker but often omit the agent's own progress and verification status. Taken together, we argue that knowing when to stop therefore needs explicit support, both in the tool that lets an agent hand off and in the report it leaves behind.

cs.SE · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36449

A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs

Alexa R. Tartaglini, Zhengxuan Wu, Thaddäus Wiedemer, Martin Wattenberg, Been Kim, Yuxuan Li

原文摘要

Do vision-language models (VLMs) share our ability to communicate visually? We share preliminary findings, starting from a surprising observation: simple visual symbols like a red heart can strongly influence model behavior on seemingly unrelated tasks, such as steering models towards recursive solutions on simple coding problems. Notably, this steering effect is largely implicit, as models' direct interpretations and thinking traces about visual symbols diverge substantially from their observed behavior. In visual communication between models, this leads to a generation--interpretation gap: while models tend to send shape primitives that they (and humans) find intuitive, these visual cues often fail to steer other models. In further communication games involving abstract concepts and stories, models can creatively use visuals to transmit meaning to one another, although some communications remain non-intuitive to humans. These findings reveal that VLMs might be capable of rich, creative, and visually-grounded communication, but their interpretation and production of visual meaning diverges from human conventions in surprising ways. Together this work highlights both the promise and challenges of visual communication between humans and VLMs.

cs.AI · cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36445

From Solver Trajectories to Teaching Trajectories: Cognition-Aligned Reasoning Distillation

Yashuo Luo, Qianren Mao, Ziqi Qin, Junnan Liu, Haitao Li, Qili Zhang, Yuan Gao, Zhijun Chen 等 9 位作者

原文摘要

Knowledge distillation from large reasoning models (LRMs) often uses raw teacher trajectories as supervision. However, this practice creates a mismatch between the goal of distillation and the nature of teacher trajectories. Advanced LRMs typically improve their reasoning capabilities through reward-driven post-training, such as RLHF. This training optimizes them as strong solvers, rather than as teachers that produce reasoning processes smaller models can easily learn. Since smaller models have different "cognitive capacities" compared to their larger teachers, directly imitating raw teacher trajectories can sometimes be ineffective and often requires a substantial number of high-quality samples. To bridge this mismatch, we propose Cognition-Aligned Reasoning Distillation (CARD), an RL-based framework that transforms solver trajectories into teaching trajectories aligned with the student's cognition. Avoiding expensive resampling, our framework directly transforms existing trajectories. We optimize CARD with two reward signals: (1) a Distribution Alignment Reward that matches the student's predictive distribution, and (2) a Logical Coherence Reward that reduces misleading failed reasoning steps. Comprehensive evaluations across multiple student models and settings demonstrate that CARD outperforms distillation from raw teacher trajectories in in-domain settings while achieving substantial gains in out-of-distribution performance. Code is available at https://github.com/LiteSSLHub/CARD.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36444

RouteDRAG: Learning to Route and Control Agentic Execution for Multimodal Document RAG

Zekai Chen, Hao Zhu, Yu Liu, Xunkai Li, Zejian Kang, Rui Qian, Quanjiang Li, Rong-Hua Li

原文摘要

Web-based applications increasingly rely on understanding long multimodal documents, where answering questions often requires combining information across pages, tables, and figures. Agentic retrieval-augmented generation addresses these tasks through iterative retrieval and reasoning. However, Agentic execution is not always necessary, introducing additional computation and potentially incorrect answers. Our empirical analysis reveals that Agentic execution provides query-dependent benefits, while additional operations may improve, preserve, or degrade answer accuracy. These findings motivate controlling both Agent invocation and subsequent execution. To address these challenges, we propose RouteDRAG, a learning-based framework comprising four components. Unified Document Index organizes multimodal content into a graph-backed index and derives query representations from initial retrieval. Adaptive Path Routing preserves exact answering and predicts the relative benefit of Agent over shorter execution paths. Dynamic Agent Execution maintains an evolving workspace and refines Planner proposals to control tool use and termination. Sequential Policy Learning first trains operation control from observed outcomes and then trains path routing using the resulting Agent's performance. Across two benchmarks, RouteDRAG achieves an average accuracy improvement of 3.47 percentage points over shorter-path-only execution while assigning only 79.3% of queries to Agent. Notably, it also surpasses uniform Agent execution on both benchmarks while requiring fewer answering calls. Our code is now available at https://github.com/Ereshkigal1/RouteDRAG.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36435

Your Agent Acts Differently When You're Around: How User Presence Changes Agent Behavior in Negotiation

Jane Pan, You Lyu, Abe Bohan Hou, Valerie Chen, He He

原文摘要

LLM agents increasingly interact with other agents on behalf of users, yet how users in the loop affect their agents' behavior--for better or worse--remains poorly understood. We study this question through the lens of negotiation, where agents must represent users while strategically bargaining with other agents. To isolate the effect of user presence, we develop PRESENT, a controlled evaluation framework that compares negotiation settings with and without an interactive user, while holding the game, objectives, and user preferences fixed across conditions. Across 11.2k runs spanning 7 games and 8 models, we find that user presence significantly changes both outcomes and behavior. Specifically, negotiation parties with a user obtain higher payouts (+13.7% on average) and their agents negotiate more aggressively. Surprisingly, user presence also induces misaligned behavior, both toward counterparties (where its rate roughly doubles) and toward users (where it emerges in 14.3% of games). These misaligned behaviors are uncorrelated with outcomes and persist even when the user sends only templated, neutral messages. These findings expose two blind spots in current evaluation practice: static instructions miss behaviors that emerge only when users are present, and outcome-level metrics cannot detect them.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36433

LM-DSB: A Lightweight Multi-agent System for Automated Daily Safety Bulletin Generation in Construction

Xianxiang Zhao, Advik Mehta, Falak Sethi, Brian Gue, Qipei Mei, Lingzi Wu

原文摘要

Construction safety management still struggles to produce daily safety bulletins (DSBs), structured daily communications that identify site-specific hazards, convey safety protocols, and set preventive measures for workers. Manual DSB creation takes 2-3 hours daily and yields inconsistent quality, with 25% of crews never conducting pretask planning (Olson et al., 2016), diverting safety personnel from field supervision. This study proposes the Lightweight Multi-Agent DSB System (LM-DSB), which integrates retrieval-augmented generation (RAG) with a locally deployable Large Language Model (LLM) to automate DSB generation on consumer-grade personal computers. LM-DSB coordinates specialized planner, researcher, and writer agents in a hierarchical architecture, enhanced by domain-specific fine-tuning on construction safety documentation and RAG grounding in 37 health, safety, and environment (HSE) documents. A two-phase validation assessed feasibility. Phase 1 comparative evaluation showed the multi-agent RAG system (Llama 3-8B) outperformed all alternative configurations, with strong lexical alignment and coherence (TF-IDF: 0.70, BLEU: 0.39, ROUGE-1: 0.66) and near-complete document generation (length ratio: 1.01 vs. 0.39 for single-agent RAG). Phase 2 expert evaluation (N=40) confirmed practical acceptability (mean scores 3.50-4.20 on a 5-point scale), particularly in regulatory compliance (4.20) and factual accuracy (4.10). The findings show that architectural design enables lightweight models to handle safety-critical documentation on consumer-grade hardware, advancing technology democratization in construction safety management. Limitations include knowledge base scope, language constraints, and lack of field deployment validation; future work should address multimodal integration and workflow adoption.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36425

Repulsive Population Policy Gradients for Behaviorally Diverse Reinforcement Learning

Saeed Hedayatian, Harsh Shah, Celine Mneimneh, Stefanos Nikolaidis

原文摘要

The goal of Quality-Diversity Reinforcement Learning (QD-RL) is to find a population of high-performing policies that solve a decision-making problem in diverse ways. Despite recent progress, QD-RL methods predominantly rely on evolutionary operators--including black-box optimizers, mutations, and crossovers--to facilitate exploration and induce diversity. Scaling these methods becomes increasingly costly as policies and behavior spaces grow larger. Building on the Soft QD view of quality-diversity optimization, we introduce \textbf{Re}pulsive \textbf{P}opulation \textbf{P}olicy \textbf{O}ptimization (\textbf{RePPO}), which adapts PPO to jointly optimize a compact population of diverse, high-quality policies using a population-dependent, dynamically shaped reward. On standard continuous-control tasks, RePPO achieves a strong quality-diversity tradeoff compared with state-of-the-art QD-RL methods. Ablations further characterize this tradeoff by examining how each component affects individual quality and collective diversity. To assess RePPO's scalability, we extend our evaluation to learning from pixels and fine-tuning large language models. In pixel-based tasks, where large policies make most traditional QD-RL methods infeasible, RePPO maintains quality on par with standard PPO while achieving substantially higher diversity. Its successful application to language model fine-tuning further demonstrates, for the first time, that QD-RL methods can scale to this domain. Together, these results show that directly optimizing compact populations with RePPO provides a scalable approach to QD-RL across increasingly complex domains.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.16364

Clinical Note Bloat Reduction for Efficient LLM Use

Jordan L. Cahoon, Chloe Stanwyck, Asad Aali, Rachel Madding, Sulaiman S. Somani, Emma Sun, Yixing Jiang, Renumathy Dhanasekaran 等 9 位作者

原文摘要

Background: Clinical notes contain extensive duplicated text from templates, copy-paste, and auto-populated fields ("note bloat"), diluting clinical signal, limiting longitudinal context, and increasing large language model (LLM) costs. Methods: TRACE removes note bloat using note-level EHR metadata to identify templated and copied content, with frequency-based de-duplication when metadata are unavailable. We evaluated TRACE using blinded physician span review and gold-standard templated-text annotations across four cohorts spanning liver transplant, obstetrics, and inpatient populations at multiple health systems (5.3M notes). We compared zero-shot LLMs and embedding-based classifiers using original and TRACE-processed notes for 20 information extraction tasks and prediction of 5-year survival, postpartum hemorrhage, and 30-day readmission. Results: Only 0.3-6.6% of removed text was flagged as author-generated; TRACE captured 86% of annotated templated characters. Information extraction F1 differences averaged by cohort ranged from -0.009 to +0.004; task-specific prediction F1 differences ranged from -0.011 to +0.018. Among 1,000 randomly sampled Stanford Health Care patients, TRACE reduced chart text by 47.3% (742.7M characters), averaging 220,167 fewer tokens per patient. Using 2024 encounter volumes at a large tertiary academic center and one query per encounter, projected three-year net savings ranged from $1.00M to $13.58M across evaluated model pricing schemes, including initial and annual TRACE processing costs. Conclusion: TRACE substantially reduces clinical note redundancy while preserving information extraction and prediction performance. Underused EHR metadata can reduce LLM inference costs, expand usable longitudinal context, and support scalable clinical AI.

cs.CY · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36415

Verifiable Efficiency Limits of Innate LLM Planning in Sliding Puzzles

Yezhou Cheng, Charles Ling

原文摘要

Tool-assisted planning success can reflect external search and verification, leaving a model's unaided planning ability unresolved. We isolate innate planning through complete plans generated in one response without tools or execution feedback. We propose a verifiable framework that decomposes success-weighted plan efficiency as $\mathrm{SPE}=R\times Q\times E$: execution reliability, planning coordination among legal plans, and action economy among completed plans. Trajectory replay and certified optima verify these factors; the joint score includes unsuccessful attempts. We evaluate 8,400 full-plan outputs from seven model conditions on $4\times4$ sliding puzzles, controlling exact horizon and obstacle count in the primary cohort. Models that complete every trial still become less economical at longer horizons, while higher efficiency among completed plans can coexist with poor goal attainment. SPE separates the overall capability hierarchy, while its factors distinguish coordination failure from inefficient completion. The framework makes long-horizon limitations in unaided planning quantitatively verifiable.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.25135

ScalableRAG: High-Quality RAG with Exact Corpus Operations at Minimal Ingestion Cost

Hilaf Hasson, Aditya Chakravarty, Jayant Thomas, Krishna Gogineni

原文摘要

RAG systems face a capability-cost gap: lightweight retrievers locate evidence but expose no operands for exact corpus-level operations (counts, intersections, aggregations), while knowledge ingestion systems obtain them only through expensive ingestion. ScalableRAG closes this gap with a persistent typed-set workspace: an agent builds named document and value sets at query time and composes them through set algebra, typed extraction, aggregation, and diagnostics. Zero-Ingestion ScalableRAG needs no preprocessing, not even a vector index. It matches the leading baseline on four conventional QA benchmarks (74.75 versus 74.64) and on aggregative Hotels-50 beats every evaluated system, scoring 71.74: 36.23 above the leading baseline (SRAG), and 40.22 points above A-RAG. Removing the workspace drops Hotels-50 to 38.4. On Hotels-350, the partition SRAG itself reports on, ScalableRAG leads SRAG by 9.3 points. Limited-Ingestion ScalableRAG adds a lightweight index and is the only evaluated system above 80 judge score at 5M documents, at 13 to 16 seconds per question and under 20 minutes ingestion; at 1M it scores 84.5 to A-RAG's 80.0 with 16x lower latency and 0.5% of its ingestion time. ScalableRAG combines minimal ingestion, conventional-QA parity, exact corpus operations, and million-document viability; no evaluated alternative provides all four. Our code is available at https://github.com/cohesity/ScalableRAG .

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36405

kw-bench: Breaking Frontier Harnesses on Real-World Tasks

George Juraj Salapa

原文摘要

Each new generation of frontier model pushes the edge of what is possible. Inside a harness -- a loop, a shell, a filesystem, the ability to write and run its own code -- a model can take on increasingly difficult work. A growing body of work treats the coding-agent harness as infrastructure for knowledge work rather than a coding tool, and a new wave of benchmarks tests it there. Most of them are generative: build a financial model, a memo, a spreadsheet from a brief, judged by a rubric or by another model. Few test the expensive part of knowledge work, which is investigative. In audit, tax, due diligence, regulatory reporting, claims or any dispute over numbers, the answer already exists -- hidden in incomplete and inconsistent evidence spread across systems -- and has to be recovered and defended to the cent. We introduce kw-bench, a benchmark built from real engagements specialists described to us. Its first task family is a five-year VAT reconstruction across three generations of SAP -- legacy ECC, a partial S/4HANA migration and a consultant's redesign -- delivered as raw system extracts: page headers, local number formats, partial link tables, no documentation of how anything connects. Grading is deterministic, with no LLM judge. We ran four harnesses -- Claude Code, Codex, OpenCode and micro-cc -- on the same model, DeepSeek v4.1 Flash, for two hours. The two independent, model-agnostic harnesses delivered (OpenCode 0.542, micro-cc 0.528); the two lab harnesses, away from their home model, delivered nothing (0.00 each). What defeated them was inertia: keeping many weak signals alive across a long session. On a frontier model the task collapses. micro-cc and Claude Code on Claude Opus 5.5 scored 0.9986 and 1.000, in 22 and 25 minutes. A weeks-long engagement now costs minutes and a few dollars; below the frontier, the harness decides how far a model gets.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.04751

Trust Region Policy Distillation

Zhengpeng Xie, Li Lyna Zhang, Zeke Xie, Mao Yang

原文摘要

Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust Region Policy Distillation (TOP-D), which transforms the notoriously unstable, high-variance On-Policy Distillation (OPD) into a stable training paradigm by dynamically constructing a proximal teacher. Theoretically, we establish a rigorous framework demonstrating that TOP-D inherently controls gradient variance. By providing a formal global convergence analysis alongside a monotonic improvement bound, we mathematically formalize the reliability and stability of the overall training dynamics. Empirically, TOP-D dramatically enhances training stability, sample efficiency, and final performance on mathematical reasoning tasks. More importantly, TOP-D introduces zero additional computational overhead, positioning itself as a promising alternative to the well-established OPD paradigm.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36389

MAREval: A Multi-Agent Framework for Evaluating Natural Language Recommendation Explanations

Reza Yousefi Maragheh, Jayesh Uddhav Kudase, Aysenur Inan, Ramin Giahi, Kai Zhao, Parth Parikh, Jianpeng Xu, Jason Cho 等 10 位作者

原文摘要

Evaluating natural language explanations in recommender systems is essential for fostering user trust, transparency, and engagement. However, existing evaluation approaches like human evaluations, while accurate, are resource-intensive and impractical at the scale required by modern recommendation platforms. Also, automated methods using single-agent LLMs suffer from prompt sensitivity and inconsistent outputs. To address these challenges, we propose MAREval, a structured multi-agent framework for evaluating recommendation explanations using large language models. MAREval orchestrates (i) a planner agent that uses a novel Chain of Debate (CoD) prompting strategy to coordinate agent roles and enforce logically consistent evaluation plans; (ii) a moderator agent that regulates discussions by mitigating prompt drift; and (iii) an arbitrator agent that aggregates outputs from multiple evaluation rounds and (iv) a Monte Carlo sampling method, improving robustness and alignment with human judgment. We conduct comprehensive evaluations on both public (TopicalChat) and proprietary recommendation datasets, demonstrating that MAREval outperforms state-of-the-art baselines. Comprehensive experiments on a public benchmark and a proprietary e-commerce dataset show that MAREval improves alignment with human judgments over strong singleand multi-agent baselines. Stability analyses indicate substantially lower variability across repeated trials. In a large human-annotation gate, MAREval meets production quality thresholds where prior evaluators fall short, and online A/B testing demonstrates statistically significant improvements in engagement and revenue metrics. These results establish MAREval as a scalable and reliable solution for human-aligned evaluation of recommendation explanations in real-world systems

cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗