跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1085新增论文
+884其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 08:33 — 2026-11-19 08:33(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:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 08:00

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。

26,871 已收录论文22,375 AI 相关8,156 有修订112 HF 社区发现

浏览论文库

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 47 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
新论文 · v1arXiv:2611.22009

DiagTrace: An Interactive Benchmark for Clinical Decision Making

Yufan Wang, Rui Yang, Yi Lin, Chunhua Weng, Yifan Peng

原文摘要

Large language models (LLMs) have shown strong performance on medical question answering and diagnostic reasoning benchmarks. However, existing evaluations typically provide all patient information upfront and assess only the final diagnosis or rationale. This setup ignores the need to acquire diagnostic evidence incrementally from incomplete information in real-world diagnosis. To bridge this gap, we introduce DiagTrace, a source-grounded benchmark for evaluating whether LLMs can reconstruct the documented diagnostic trajectory through interactive information seeking. Each benchmark instance is built from a PubMed Central case report and includes an initial presentation, an event bank, a clinical course, and diagnostic references. DiagTrace contains 510 cases across eight specialties, with 225 used to evaluate four LLMs on clinical-course alignment, interaction quality, and efficiency. Results reveal trade-offs in coverage, source-consistent ordering, and turn use.

cs.CL · cs.AI

新论文 · v1arXiv:2611.20755

GPRM: Global Perspective Process Reward Model

Zifan Zhang, Zhengbo Jiao, Shaobo Wang, Jing Zhou, Guoyi Li, Jiayi Chen, Wei Wang, Bing Zhao 等 13 位作者

原文摘要

Process Reward Models (PRMs) are widely used for step-level evaluation of multi-step reasoning in large language models, but existing methods are often limited by weak historical dependency modeling and insufficient global awareness. They typically fail to leverage prior step evaluations for coherent judgment and lack visibility into subsequent reasoning, leading to suboptimal assessment of intermediate steps. To address this issue, we propose the Global Perspective Process Reward Model (GPRM), which jointly models the problem, previous reasoning steps and their evaluations, the current step, and future steps to enable history-aware and globally informed process evaluation. We further introduce a structured evaluation framework along four dimensions---look back, look ahead, self-check, and goal alignment---to assess prior consistency, future plausibility, step validity, and task alignment. Based on this framework, we construct datasets for supervised fine-tuning (SFT) and reinforcement learning (GRPO). Experiments show that, despite using less training data and smaller model sizes, GPRM outperforms strong baseline models by 7.8 and 5.4 points on PRMBench and ProcessBench, respectively. GPRM also generalizes well across tasks, surpassing the GPT-4.1 baseline on Agent Error Bench, improving strong baselines by around 4 points under test-time scaling (TTS), and achieving competitive performance on PPE.

cs.CL

新论文 · v1arXiv:2611.17955

WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents

Imene Kerboua, Fatemeh Pesaran Zadeh, Xing Han Lù, Weijian Qi, Alexander Miller, Junyi Song, Yunjia Tian, Dongjin Kang 等 22 位作者

原文摘要

Web agents powered by large language and vision-language models are increasingly applied to realistic browser work that spans heterogeneous applications, multimodal content, and stateful workflows. However, existing reproducible web-agent benchmarks cover only a small number of web applications drawn from a few software categories, and restrict modality to text and vision. Live benchmarks broaden site coverage but sacrifice reproducibility, since pages and data drift between runs. Moreover, existing benchmarks do not meaningfully evaluate whether agents can understand and use audio and video content embedded within web tasks. To address these gaps, we introduce WebArena-Pro, a benchmark comprising 300 tasks across 20 self-hosted web applications in six domain categories, spanning distinct interface conventions, workflows, and data models. Across the evaluated agents, the best performance is achieved by both Codex with GPT 6.1 Sol and Claude Code with Claude Opus 5.5 at 62.3%, followed by OpenCode with Kimi 3.1 Pro at 60.7%. The strongest GenericAgent configurations, Gemini 3.1 Pro omni and Gemma4 31B, both achieve 30.3%. Among reproducible, human-curated web agent benchmarks, WebArena-Pro provides the broadest application coverage and the most comprehensive multimodal support to date. The benchmark treats audio and video as core observations alongside text and vision, with dedicated actions for extracting information from each. WebArena-Pro runs each task in isolation and supports reproducible, parallel evaluation. Tasks are authored through a dedicated annotator interface, filtered by LLM-assisted triage, and finally validated by humans before release. Project page: https://webarena-pro.github.io

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2611.12305

HumanSightBench: A Benchmark for Human Visual Perception in MLLMs

Zixin Su, Yangguang Lin, Zegang Peng, Yuntong Sun, Xuanyi Wang, Jiahao Wang, Qiankai Xu, Bing Yuan 等 13 位作者

原文摘要

Multimodal large language models (MLLMs) have demonstrated strong performance on knowledge-intensive and reasoning-based vision-language benchmark datasets, but still struggle to solve the visual questions that people can solve easily. Evaluating the differences between MLLMs and human-level visual perception is challenging due to end-to-end evaluation which combines various skills, or because we are uncertain if individual items are valid. Specifically, observed errors may reflect visual perception, language priors, background knowledge, question ambiguity, and underspecified answers. Our guideline for HumanSightBench is that we construct items that are human-easy by construction and model-hard by evaluation. HumanSightBench contains 2,876 visual questions with short answers across 7 top-level perceptual categories and 21 subcategories. We only include items that pass five inclusion gates: question clarity, answer uniqueness, visual grounding, human solvability, and text-only shortcut filtering. According to the protocol, errors are defined as incorrect answers on human-validated visual tasks with the evaluated interface. The inclusion gates are intended to reduce confounds from ambiguity and external knowledge. The best pass@3 score is 65.6% across eight evaluated MLLMs. No evaluated model exceeds 27.5% on Counting. These results identify capability gaps that are hidden by overall scores and can help future training experiments and held-out evaluation.

cs.CV · cs.AI · cs.CL

新论文 · v1arXiv:2611.12856

WorkflowArena:面向基于大语言模型的多智能体系统的可执行工作流编排基准

WorkflowArena: Benchmarking Executable Workflow Orchestration in LLM-Based Multi-Agent Systems

Zheng Jiang, Fang Niu, Bo Peng, Houde Qian, Wenyi Li, Deyao Hong, Mingju Gao, Yizhe Chi 等 13 位作者

AI 速读 基于摘要

提出 WorkflowArena 基准,用 145 个长周期任务评估大模型多智能体系统自主编写并执行工作流编排的能力。

cs.CL · cs.SE

查看原文摘要

Large language model agents are increasingly deployed as multi-agent systems rather than as a standalone model operating within a single context. Recent agent harnesses allow the model to instantiate worker agents and to author the executable workflow that coordinates them, shifting the design of system structure from developers to the model at run time. The quality of this organization therefore constitutes a distinct capability, yet existing benchmarks either measure end-to-end task completion or evaluate coordination under structures specified in advance. We formalize this capability as workflow orchestration and introduce WorkflowArena, a benchmark of 145 long-horizon tasks spanning 8 professional domains, from software engineering and formal mathematics to legal analysis and 3D production. Each task specifies an initial workspace and an integrated deliverable composed of interdependent components, which is assessed by a hidden verifier. Agents determine autonomously whether and how to delegate, and all delegation is recorded, enabling joint evaluation of deliverable quality and the organization of the underlying work. Experiments with nine models show that no single configuration performs best across all domains and that systems exhibit distinct delegation strategies: at high effort, Claude models in Claude Code invoke workflows less frequently but with larger worker groups, whereas GPT models in Codex delegate more frequently in smaller units. When the executing model is held fixed on a challenging subset of tasks, workflows authored by Claude Opus 5.5 substantially improve weaker executors, indicating that workflow organization is itself a measurable determinant of task performance.

新论文 · v1arXiv:2611.12640

TrialDesignBench: Benchmarking Language Models for Phase-I Trial Design Against Clinical Knowledge

Yihan Hank Tang, Peng Yang, Jiayi Xin, Tianqi Shang, Xuyang Chen, Ying Yuan, Yi Lian, Qi Long

原文摘要

AI is used in much of the clinical trial pipeline. However, selecting the statistical design of a trial, a crucial step that determines how drug doses are tested on humans and evaluated, has seen almost no AI progress. LLMs appear to be a natural fit given their strengths in biomedical knowledge and statistical reasoning. Nevertheless, there is currently no appropriate way to evaluate such abilities because recent regulatory and methodological shifts, most notably FDA's Project Optimus, have redefined what constitutes a reasonable design and rendered many previous designs obsolete. To lay the groundwork for AI-assisted trial design, we introduce TrialDesignBench, a benchmark of 617 Phase-I/I-II oncology dose-finding trials, each paired with an expert-validated reference design that is consistent with the latest FDA regulatory initiatives. This reference standard is produced through a formalization of the expert design process. We evaluate five frontier LLMs, none of which matches the reference standard. Our ablation experiments trace this performance gap to two main causes, inference of latent, unrecorded design determinants from trial sources (supplying them raises class-wise balanced accuracy by 0.22) and structured decision-tree reasoning (+0.24). TrialDesignBench offers a reproducible, contemporary-standard objective for evaluating and enhancing AI-assisted trial design.

cs.AI · cs.CL · stat.AP

版本更新 · v2arXiv:2606.17478

From Hidden States to Confessions: Auditing Deception in Reasoning Models

Kexin Chen, Dongxia Wang, Haonan Zhang, Yanhui Li, Xinyu Deng, Yi Liu

原文摘要

As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern. Existing deception monitors typically either score visible transcripts or derive scalar probe scores from representation vectors, leaving little inspectable evidence about why a response is suspicious. We introduce StateWitness, an audit decoder for deception monitoring. It reads a target model's hidden states to answer audit queries and produce confession-style reports of potential failures or violations. We evaluate generalization beyond the decoder's audit training data across two target reasoning models and seven deception datasets. StateWitness achieves 0.916 mean AUROC, with relative gains of 11.6% and 25.0% over the best black-box and activation-probe baselines, respectively, under the same evaluation protocol. When combined with existing monitors, StateWitness reduces missed deceptive examples in simple threshold ensembles. Beyond scalar detection, the decoder returns query-level answers, schema reports, and token- or sentence-level evidence traces for human inspection. We envision StateWitness as one monitoring layer in a broader defense-in-depth strategy.

cs.CL · cs.AI

版本更新 · v2arXiv:2610.33237

Each Insufficient in Its Own Way: Calibrating Language Models Across Varying Evidence States

Jiayi Li, Dennis L. Shung, Bradly C. Stadie

原文摘要

How can a language model know whether it has enough evidence to answer? Language models tend to answer even when the evidence they have is insufficient. Deciding whether to answer or gather more evidence requires a calibrated estimate of how likely an answer is to be correct with the available evidence. However, most calibration work treats the input as fixed, without asking how this estimate should change with the evidence. We introduce evidence-state calibration, which requires a model's confidence before answering to match its probability of answering correctly and to change accordingly whenever the evidence changes this probability. We propose SuffiCE (Sufficiency Confidence Estimation), which fine-tunes the confidence already present in a model's next-token distribution to match how often the model answers correctly from each evidence state. Across clinical diagnosis and multi-hop question answering with four models from two families, SuffiCE reduces the Brier score by up to 60% and increases AUROC by up to 0.16. Its confidence matches the empirical success rate and responds not only to the amount of evidence but also to which evidence is present, showing that models can learn to judge whether their current evidence is enough to answer.

cs.CL

版本更新 · v2arXiv:2610.13202

S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding

Yuhang He, Hongyu Ge, Zihan Lin, Siyi Liu, Yongqi Zhang

原文摘要

Fast rollout generation for long-context reinforcement learning with verifiable rewards (RLVR) requires reducing KV-cache traffic without changing the response groups used for policy optimization. In our profiled RLVR workloads, attention accounts for 72--76\% of autoregressive decoding kernel time. Sparse attention reduces these reads, but sampling directly from a sparse policy changes the response groups used for learning. For group-relative optimization, we show that even exact response-wise reweighting does not generally recover the expected dense-policy update because the advantage of each response depends on the rewards of other group members. We propose Self-Sparse Speculative Rollouts (S$^3$R). It uses sparse attention to propose tokens, then generates responses through full-attention verification and exact speculative sampling. Drafting and verification share the same policy parameter, eliminating the need to train or update a separate drafter. The resulting response groups follow the dense-policy distribution. Under S$^3$R, we characterize speedup conditions and the costs of drafting and verification. We found that dense verification still requires the complete historical KV cache. A KV-aware scheduler therefore limits KV-cache repeated offloading and restoration while maintaining rollout parallelism. % OR thrashing In a matched ablation with an aggressive sparse drafting budget, S$^3$R maintains stable training while direct sparse sampling with training-side correction becomes unstable. On long-context mathematical reasoning, S$^3$R achieves $1.39\times~1.35\times$ the end-to-end training throughput of autoregressive rollouts on Qwen3 model, with comparable task performance.

cs.LG · cs.CL

版本更新 · v2arXiv:2608.18096

MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators

Zijuan Zhao, Zheren Fu, Hou Xia, Licheng Zhang, Yi Liu, Zhendong Mao

原文摘要

Assessing whether multimodal content aligns with macro-societal values, such as peace, justice, and freedom, has become an increasingly urgent challenge. Existing frameworks are largely confined to safety-oriented taxonomies, text-only psychometric probes, or single-label classification. Therefore, we propose MAVEN, a hierarchical framework for macro-societal value evaluation of multimodal content, grounded in international human-rights instruments and cultural value theory. MAVEN organizes values into 6 primary dimensions and 72 secondary indicators, supporting multi-level quantitative scoring. Building on MAVEN, we construct a human-verified multimodal benchmark and a soft-match metric to evaluate VLMs' assessments across value dimensions. For evaluator optimization, we propose a span-adaptive variant of multi-level preference optimization for evaluator distillation, together with a training-free multi-role consensus strategy at inference time. We evaluate existing open- and closed-source VLMs on our benchmark, revealing shared tendencies and clear differences in macro-societal value judgments. Experiments show that our compact 2B evaluator matches its 8B counterpart in the same family and approaches frontier closed-source VLMs, offering a practical path toward scalable macro-societal value evaluation. Our SA-MDPO implementation and MacroValue-Bench are available at https://github.com/zzzzzzzzjj/MAVEN.

cs.CL · cs.LG

新论文 · v1arXiv:2610.39234

AgentHeal: Evaluating Goal-Preserving Resource Recovery of Web Agents under Access Barriers

Zhiyi Liu, Haohua Du, Haoqi Sun, Haisheng Tan

原文摘要

Large language model (LLM) agents have demonstrated strong capabilities in automating complex information-seeking and transactional tasks across the open web. However, their real-world reliability remains limited by access barriers, such as dead links, authentication walls, rate limits, and anti-scraping defenses. These barriers block the primary execution path, causing agents to abort prematurely, loop indefinitely, or quietly compromise the user's original constraints. Existing evaluations either implicitly assume that target resources are freely accessible or focus on transient perturbations that simple retries can resolve, failing to capture scenarios where agents must actively reroute around impassable bottlenecks. To bridge this gap, this paper introduces AgentHeal, a comprehensive benchmark evaluating goal-preserving resource recovery, defined as the ability of web agents to detect non-transient access barriers, pivot to legitimate alternative sources, and fulfill the user's exact original objective. Spanning nine barrier families across a counterfactual sandbox and real-website replay, our experiments on leading LLM backbones show that average task success drops sharply from 89.4% to 43.7% under access barriers. Further analysis reveals that agents frequently fall for deceptive look-alikes, fail to escalate to users when necessary, violate access policies, or waste computation on futile retries, providing actionable diagnostics for developing resilient web agents.

cs.CR · cs.CL

新论文 · v1arXiv:2610.38361

Manifest-Assisted Retrieval in Artificial Intelligence Search: Evidence Gaps and a Security Evaluation

Gangzhen Qian, Kainan Zhou, Chuhong Xu, Hang Xiao, Zhi Jing, Rong Bao, Lu Yi, Zhaoyi Li

原文摘要

The external sources retained in our non-systematic audit did not isolate the incremental security or utility effect of consuming /llms.txt while ordinary retrieval remained fixed. The initial audit covered 39 sources through August 16, 2026, with later targeted updates through October 14. A purposive 15-tool study observed no automatic requests in 45 trials at one endpoint; a non-probability log study found that 97% of domains with detected files received no recorded requests in May 2026. We separate publication, fetch, model use, and action; define five operational threat paths and paired security-utility estimands; and exercise deterministic pre-model controls with 30 author-defined parser fixtures. We also execute a reduced pilot: 24 tasks across eight sites, five conditions, and 120 real model responses, with ordinary evidence held fixed. Frozen automatic scoring identifies attacker-target adoption in $21/24$ raw adversarial responses, with one further response unresolved; the adversarial URLs-only condition has no known adoptions and one unresolved response. The pilot measures output changes conditional on supplied evidence, without live retrieval or external actions. Together, the framework and pilot distinguish manifest-content effects from publication, discovery, and downstream execution, while leaving full retrieval and agent evaluation open.

cs.CR · cs.AI · cs.CE · cs.CL · cs.DB · cs.IR

版本更新 · v2arXiv:2604.09711

Decoupling and Regulating Modality Heads for Fake News Detection under Missing Modality

Kai Qian, Dongjie Xu, Weijie Shi, Yezhao Xu, Jiaqi Wang, Hanghui Guo, Mengze Li, Hao Chen 等 10 位作者

原文摘要

Multimodal news often loses its image or text as it spreads across Web platforms. Existing methods treat this as information loss, assuming that the original veracity label remains valid. This assumption fails for fake news reusing authentic material, whose remainder may be genuine. Detectors should therefore decouple modality cues and adapt their contributions to modality availability. However, coarse news labels provide little guidance for modality decoupling, while training on complete inputs can induce modality bias. To address these challenges, we propose Head-wise Modality Decoupling and Regulation (HMDR) for multimodal large language models. First, Modality Head Decoupling decouples modality representations through soft head grouping by attention preference. Second, Modality Head Regulation regulates head contributions through compensation for imbalanced modality attention. Finally, Modality Invariance Learning promotes invariance by aligning representations of each modality under replacement of the other. Experiments on two benchmarks show that HMDR improves detection under missing modalities while maintaining performance on complete inputs.

cs.CV · cs.CL

版本更新 · v2arXiv:2609.31142

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

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

原文摘要

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

cs.CR · cs.AI · cs.CL

新论文 · v1arXiv:2610.22507HF 社区推荐

RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents

Yunqi Liu, Peiyu Wang, Bingli Wang, Leo Luo, Xuanwu Song, Xudong Ma, Hongxin Li, Yaxin Du 等 24 位作者

原文摘要

Command-line interface (CLI) agents increasingly execute longer-horizon tasks, yet existing benchmarks either assume that user instructions remain fixed throughout execution or evaluate task outcomes without capturing runtime collaboration quality. In this paper, we present REALCLI, a paired benchmark that unifies the evaluation of task execution and human-agent collaboration quality on realistic CLI tasks. To comprehensively measure collaboration, REALCLI builds a five-dimensional framework, operationalized into 22 sub-dimensions and 51 interaction scenario templates. REALCLI provides two modes for paired comparison: REALCLI-EXEC supplies complete specifications upfront, whereas REALCLI-COLLAB introduces a scripted user that delivers progressive information, corrections, constraint revisions, and authorization decisions. Evaluations reveal profound capability gaps in frontier agents: the best configuration attains an average score of only 49.2%, and when evaluated by the joint collaboration score ($J_{\mathrm{collab}}$), the peak performance reaches merely 37.6%. These results show that task effectiveness diverges sharply from collaboration quality, with models consistently struggling in steerability, trust calibration, and safety boundary management. REALCLI provides a rigorous, reproducible foundation for measuring and advancing collaborative CLI agents.

cs.CL

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.8ACL Anthology · ACL 2026

ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring

Deyi Ji, Junyu Lu, Xuanyi Liu, Liqun Liu, Hailong Zhang, Peng Shu, Huan Yu, Jie Jiang 等 10 位作者

原文摘要

Online advertising governance faces significant challenges due to the non-stationary nature of regulatory policies, where emerging mandates (e.g., restrictions on education or aesthetic anxiety) create severe label inconsistencies and reasoning ambiguities in historical datasets. In this paper, we propose ARGUS, a policy-adaptive governance system that enables evolving reinforcement through multi-agent adversarial umpiring. ARGUS addresses the sparsity of new policy data by employing a three-stage framework: (1) Policy Seeding for initial perception; (2) Adversarial Label Rectification, which utilizes a ”Prosecutor-Defender-Umpire” architecture to resolve conflicts between stale labels and new mandates; and (3) Latent Knowledge Discovery, which employs a tripartite dialectical discussion to unearth sophisticated, “gray-area” violations. By leveraging RAG-enhanced policy knowledge and Chain-of-Thought synthesis as dynamic rewards for reinforcement learning, ARGUS synchronizes its reasoning pathways with evolving regulations. Extensive experiments on both industrial and public datasets demonstrate that ARGUS significantly outperforms traditional fine-tuning baselines, achieving superior policy-adaptive learning with minimal gold data.

cs.CL · cs.MA

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1054ACL Anthology · ACL 2026

DVCQR: Dual-View Conversational Query Rewriting with Stage-wise Reinforcement Learning

Chenyi Li, Xinhui Tu Central China Normal University, Zaixiang Wang Central China Normal University

原文摘要

Conversational query rewriting (CQR) addresses context dependence in conversational search by rewriting each user query into a standalone form. Recent approaches leverage reinforcement learning (RL) to directly optimize retrieval effectiveness; however, they typically rely on a single rewrite, which struggles to accommodate the divergent preferences of sparse and dense retrievers and often suffers from conflicting optimization signals. We propose DVCQR, a Dual-View CQR framework that explicitly generates two complementary rewrites for each query: a sparse-view rewrite that emphasizes distinctive lexical anchors, and a dense-view rewrite that captures complete semantic constraints. Both rewrites are produced in a single pass via a structured reasoning process. To further mitigate objective conflicts, we introduce a stage-wise RL strategy that sequentially aligns the sparse and dense views with their corresponding retrievers using rank-based feedback. Extensive experiments on four benchmarks (TopiOCQA, QReCC, CAsT-19, and CAsT-20) demonstrate that DVCQR consistently outperforms state-of-the-art methods on most metrics under both sparse and dense retrieval settings, validating the effectiveness of dual-view rewriting and stage-wise retriever alignment.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1101ACL Anthology · ACL 2026

Scaling Laws for Code: A More Data-Hungry Regime

Xianzhen Luo Harbin Institute of Techology, Wenzhen Zheng, Qingfu Zhu Harbin Institute of Technology, Rongyi Zhang, Houyi Li Fudan University, Siming Huang, YuanTao Fan, Wanxiang Che Harbin Institute of Technology

原文摘要

Code Large Language Models (LLMs) are revolutionizing software engineering. However, scaling laws that guide the efficient training are predominantly analyzed on Natural Language (NL). Given the fundamental differences like strict syntax between code and NL, it is unclear whether these laws are directly applicable to code. To address this gap, we conduct the first large-scale empirical study of scaling laws for code, comprising 117 experimental runs with model sizes from 0.2B to 3.8B and training tokens from 2B to 128B. We fit the Chinchilla law and the Farsser law. First, the results show that the more expressive Farseer law offers greater accuracy. Second, the analysis reveals that Code LLMs scale effectively with model size. Crucially, code represents a more data-hungry regime, requiring a substantially higher data-to-parameter ratio than NL. Finally, two additional sets of experiments on code-NL mixtures show that NL benefits resource-constrained scenarios, but becomes a detriment at higher compute budgets.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.112ACL Anthology · ACL 2026

Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding

Yuhang Zhou Meta, Mingrui Zhang, Ke Li, Mingyi Wang Facebook, Qiao Liu City University of New York, Qifei Wang, Jiayi Liu Meta Platforms Inc., Fei Liu Meta 等 15 位作者

原文摘要

Understanding and reasoning over tables is a critical capability for many real-world applications. Large language models (LLMs) have shown promise on this task, but current approaches remain limited. Fine-tuning based methods strengthen language reasoning; yet they are prone to arithmetic errors and hallucination. In contrast, tool-based methods enable precise table manipulation but rely on rigid schemas and lack semantic understanding. These complementary drawbacks highlight the need for approaches that integrate robust reasoning with reliable table processing. In this work, we propose MIXTURE-OF-MINDS, a multi-agent framework that decomposes table reasoning into three specialized roles: planning, coding, and answering. This design enables each agent to focus on a specific aspect of the task while leveraging code execution for precise table manipulation. Building on this workflow, we introduce a self-improvement training framework that employs Monte Carlo Tree Search (MCTS) rollouts to generate pseudo-gold trajectories and optimize agents with reinforcement learning (RL). Extensive experiments show that MIXTURE-OF-MINDS delivers substantial gains, reaching 62.13% on TableBench and surpassing GPT-o3-mini. These results demonstrate the promise of combining structured multi-agent workflows with RL to advance table understanding.

cs.CL · cs.MA

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1341ACL Anthology · ACL 2026

On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference

Zhengyi Li, Yakai Wang, Jingwen Leng Shanghai Jiao Tong University, Kang Yang, Yu Yu, Jiaping Gui Shanghai Jiao Tong University, Yu Feng Shanghai Jiaotong University, Ning Liu 等 9 位作者

原文摘要

For Transformer models, cryptographically secure inference ensures that the client learns only the final output, while the server learns nothing about the client’s input. However, securely computing nonlinear layers remains a major efficiency bottleneck due to the substantial communication rounds and data transmission required. To address this issue, prior works reveal intermediate activations to the client, allowing nonlinear operations to be computed in plaintext. Although this approach significantly improves efficiency, exposing activations enables adversaries to extract model weights. To mitigate this risk, existing works employ a shuffling defense that reveals only randomly permuted activations to the client. In this work, we show that the shuffling defense is not as robust as previously claimed. We propose an attack that aligns differently shuffled activations to a common permutation and subsequently exploits them to extract model weights. Experiments on Pythia-70m and GPT-2 demonstrate that the proposed attack can align shuffled activations with mean squared errors ranging from 10^{-9} to 10^{-6}. With a query cost of approximately $1, the adversary can recover model weights with L1-norm differences ranging from 10^{-4} to 10^{-2} compared to the oracle weights.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.143ACL Anthology · ACL 2026

CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization

Junyi Li Hong Kong University of Science and Technology, Yongqiang Chen Mohamed bin Zayed University of Artificial Intelligence and Carnegie Mellon University, Ningning Ding The Hong Kong University of Science and Technology (Guangzhou)

原文摘要

Machine unlearning has gained increasing attention in recent years, as a promising technique to selectively remove unwanted privacy or copyrighted information from Large Language Models that are trained on a massive scale of human data. However, the emergence of Large Reasoning Models (LRMs), which emphasize long chain-of-thought (CoT) reasoning to address complex questions, presents a dilemma to unlearning: existing methods either struggle to completely eliminate undesired knowledge from the CoT traces or degrade the reasoning performances due to the interference with the reasoning process. To this end, we introduce Counterfactual Unlearning through iterative Preference Optimization (CiPO), a novel framework that redefines unlearning as the targeted intervention of the CoT reasoning in LRMs. More specifically, given a desired unlearning target answer, CiPO instructs LRMs to generate a logically valid counterfactual reasoning trace for preference tuning. As the LRM adjusts to the counterfactual trace, CiPO iteratively updates the preference learning data to increase the discrepancy from the original model. This iterative loop ensures both desirable unlearning and smooth optimization, effectively mitigating the dilemma. Experiments on challenging benchmarks demonstrate that CiPO excels at unlearning, completely removing knowledge from both the intermediate CoT steps and the final answer, while preserving the reasoning abilities of LRMs.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1511ACL Anthology · ACL 2026

Quantifying and Understanding Uncertainty in Large Reasoning Models

Yangyi Li Iowa State University, Chenxu Zhao, Mengdi Huai Iowa State University

原文摘要

Large Reasoning Models (LRMs) have recently demonstrated significant improvements in complex reasoning. While quantifying generation uncertainty in LRMs is crucial, traditional methods are often insufficient because they do not provide finite-sample guarantees for reasoning-answer generation. Conformal prediction (CP) stands out as a model-agnostic methodology that constructs statistically rigorous uncertainty sets. However, existing CP methods ignore the logical connection between the reasoning trace and the final answer. Additionally, prior studies fail to interpret the origins of uncertainty coverage for LRMs as they typically overlook the specific training factors driving valid reasoning. Notably, it is challenging to disentangle reasoning quality from answer correctness, while simultaneously establishing theoretical guarantees for computationally efficient explanation methods. To address these challenges, we first propose a novel methodology that provides the uncertainty of the reasoning-answer structure with statistical guarantees. Subsequently, we develop a unified example-to-step explanation framework using Shapley values that identifies a provably sufficient subset of training data and their specific reasoning steps sufficient to achieve coverage. We also provide the theoretical analysis for our proposed methods. Extensive experiments on challenging reasoning datasets verify the effectiveness of the proposed methods.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1648ACL Anthology · ACL 2026

NL \Rightarrow Schedule: Evaluate Multitask Scheduling Capability of Large Language Models

Wenrui Liao, Weihong Du, Yi Li, Hongru Liang Sichuan University, Wenqiang Lei Sichuan University

原文摘要

Automated schedule generation for multitask from natural language descriptions has huge potential in modern industry. While classic methods bypass language complexities by using pre-formatted matrices, and recent LLM+solver approaches introduce new fragilities by relying on solver-specific code generation. This raises critical questions: Can large language models (LLMs) solve this NL \Rightarrow Schedule task end-to-end well(RQ1)? If the answer is “no”, where do they fall short(RQ2)? And how can their capabilities be enhanced (RQ3)? To answer these questions, we introduce NL \Rightarrow Schedule, the first benchmark for this task, equipped with a dataset of 240 description-schedule pairs constructed from real-world materials and a rigorous evaluation suite. Our evaluation of nine state-of-the-art LLMs reveals the limitations of different LLMs in procedure grounding and the strengths of advanced LLMs in global planning via local analysis. To address these shortcomings, we propose Mans, a novel multi-agent framework. Extensive experiments show that Mans achieves more robust performance comparable to six state-of-the-art LLM+solver methods. We hope NL \Rightarrow Schedule and Mans will serve as a solid foundation for automatic scheduling.

cs.CL · cs.MA

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1709ACL Anthology · ACL 2026

MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents

Dongming Jiang, Yi Li University of Texas at Dallas, Guanpeng Li University of Florida, Bingzhe Li University of Texas at Dallas

原文摘要

Memory-Augmented Generation (MAG) extends large language models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal, and entity information. This design limits interpretability and alignment between query intent and retrieved evidence, leading to suboptimal reasoning accuracy. In this paper, we propose MAGMA, a multi-graph agentic memory architecture that represents each memory item across orthogonal semantic, temporal, causal, and entity graphs. MAGMA formulates retrieval as policy-guided traversal over these relational views, enabling query-adaptive selection and structured context construction. By decoupling memory representation from retrieval logic, MAGMA provides transparent reasoning paths and fine-grained control over retrieval. Experiments on LoCoMo and LongMemEval demonstrate that MAGMA consistently outperforms state-of-the-art agentic memory systems in long-horizon reasoning task.

cs.CL · cs.AI

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1848ACL Anthology · ACL 2026

Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System

Yifei Wei, Linqing Zhong, Yi Liu, Yuxiang Lu, Xindong He, Maoqing Yao Agibot, Guanghui Ren AgiBot

原文摘要

Vision-Language-Action (VLA) models are a promising paradigm for generalist robotic manipulation by grounding high-level semantic instructions into executable physical actions. However, prevailing approaches typically adopt a monolithic generation paradigm, directly mapping visual-linguistic features to high-frequency motor commands in a flat, non-hierarchical fashion. This strategy overlooks the inherent hierarchy of robotic manipulation, where complex actions can be naturally modeled in a Hybrid Action Space, decomposing into discrete macro-directional reaching and continuous micro-pose alignment, severely widening the semantic-actuation gap and imposing a heavy representational burden on grounding high-level semantics to continuous actions. To address this, we introduce Libra-VLA, a novel Coarse-to-Fine Dual-System VLA architecture. We explicitly decouple the learning complexity into a coarse-to-fine hierarchy to strike a training equilibrium, while simultaneously leveraging this structural modularity to implement an asynchronous execution strategy. The Semantic Planner predicts discrete action tokens capturing macro-directional intent, while the Action Refiner conditions on coarse intent to generate high-frequency continuous actions for precise alignment. Crucially, our empirical analysis reveals that performance follows an inverted-U curve relative to action decomposition granularity, peaking exactly when the learning difficulty is balanced between the two sub-systems. With the asynchronous design, our approach offers a scalable, robust, and responsive solution for open-world manipulation.

cs.CL · cs.CV

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1873ACL Anthology · ACL 2026

Structure Guided Retrieval-Augmented Generation for Factual Queries

Miao Xie, Xiao Zhang, Yi Li, Chunli Lv

原文摘要

Retrieval-Augmented Generation (RAG) has been proposed to mitigate hallucinations in large language models (LLMs), where generated outputs may be factually incorrect. However, existing RAG approaches predominantly rely on vector similarity for retrieval, which is prone to semantic noise and fails to ensure that generated responses fully satisfy the complex conditions specified by factual queries, often leading to incorrect answers. To address this challenge, we introduce a novel research problem, named Exact Retrieval Problem (ERP). To the best of our knowledge, this is the first problem formulation that explicitly incorporates structural information into RAG for factual questions to satisfy all query conditions. For this novel problem, we propose Structure Guided Retrieval-Augmented Generation (SG-RAG), which models the retrieval process as an embedding-based subgraph matching task, and uses the retrieved topological structures to guide the LLM to generate answers that meet all specified query conditions. To facilitate evaluation of ERP, we construct and publicly release Exact Retrieval Question Answering (ERQA), a large-scale dataset comprising 120{,}000 fact-oriented QA pairs, each involving complex conditions, spanning 20 diverse domains. The experimental results demonstrate that SG-RAG significantly outperforms strong baselines on ERQA, delivering absolute improvements from 20.68 to 50.88 points across all evaluation metrics, while maintaining reasonable computational overhead.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1876ACL Anthology · ACL 2026

LongVideoAgent: Multi-Agent Reasoning with Long Videos

Runtao Liu, Ziyi Liu Beijing University of Posts and Telecommunications, Jiaqi Tang, Yue Ma, Renjie Pi, Jipeng Zhang Microsoft, Qifeng Chen Hong Kong University of Science and Technology

原文摘要

Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed LongTVQA and LongTVQA+ which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent.

cs.CL · cs.MA · cs.CV

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1882ACL Anthology · ACL 2026

CAP: Controllable Alignment Prompting for Unlearning in LLMs

Zhaokun Wang, Jinyu Guo University of Electronic Science and Technology of China, Jingwen Pu University of Electronic Science and Technology of China, Hongli Pu, Meng Yang, Xunlei Chen, Jie Ou, Wenyi Li 等 10 位作者

原文摘要

Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. However, existing parameter-modifying methods face fundamental limitations: high computational costs, uncontrollable forgetting boundaries, and strict dependency on model weight access. These constraints render them impractical for closed-source models, yet current non-invasive alternatives remain unsystematic and reliant on empirical experience. To address these challenges, we propose the Controllable Alignment Prompting for Unlearning (CAP) framework, an end-to-end prompt-driven unlearning paradigm. CAP decouples unlearning into a learnable prompt optimization process via reinforcement learning, where a prompt generator collaborates with the LLM to suppress target knowledge while preserving general capabilities selectively. This approach enables reversible knowledge restoration through prompt revocation. Extensive experiments demonstrate that CAP achieves precise, controllable unlearning without updating model parameters, establishing a dynamic alignment mechanism that overcomes the transferability limitations of prior methods.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1964ACL Anthology · ACL 2026

LLMSurgeon: Diagnosing Data Mixture of Large Language Models

Yaxin Luo Mohamed bin Zayed University of Artificial Intelligence, Jiacheng Cui, Xiaohan Zhao, Xinyi Shang, Jiacheng Liu Mohamed bin Zayed University of Artificial Intelligence, Xinyue Bi, Zhaoyi Li, Zhiqiang Shen Mohamed bin Zayed University of Artificial Intelligence

原文摘要

The pretraining data mixture of Large Language Models (LLMs) constitutes their “digital DNA”, shaping model behaviors, capabilities, and failure modes. Yet this composition is rarely disclosed, making post-hoc auditing of data combination or provenance difficult. In this work, we formalize \textbf{Data Mixture Surgery (DMS)}: given only generated text from a target LLM, estimate the domain-level distribution of its pretraining corpus under a predefined taxonomy. We propose \textbf{LLMSurgeon}, a strong framework that casts DMS as an inverse problem under the label-shift assumption. Rather than directly aggregating classifier outputs, LLMSurgeon estimates a calibrated \textit{soft} confusion matrix and solves a constrained inverse problem to correct systematic domain confusion and recover the latent mixture prior. To evaluate, we introduce \textbf{LLMScan}, a recipe-verifiable evaluation suite built from open-source LLMs with transparent pretraining mixtures. Across LLMScan, LLMSurgeon recovers domain mixtures with high fidelity under fixed protocols. Our work presents a practical, post-hoc approach for auditing the \textit{digital DNA} of foundation models without access to their training data. Code is available at: https://github.com/Yaxin9Luo/LLMSurgeon.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1990ACL Anthology · ACL 2026

AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse

Jie Ou, Jinyu Guo University of Electronic Science and Technology of China, Shiyao Guo, Yuang Li, Ruiqi Wu University of Electronic Science and Technology of China, Zhaokun Wang, Wenyi Li, Wenhong Tian

原文摘要

Many-Shot In-Context Learning (ICL) has emerged as a promising paradigm, leveraging extensive examples to unlock the reasoning potential of Large Language Models (LLMs). However, existing methods typically rely on a predetermined, fixed number of shots. This static approach often fails to adapt to the varying difficulty of different queries, leading to either insufficient context or interference from noise. Furthermore, the prohibitive computational and memory costs of long contexts severely limit Many-Shot’s feasibility. To address the above limitations, we propose AdapShot, which dynamically optimizes shot counts and leverages KV cache reuse for efficient inference. Specifically, we design a probe-based evaluation mechanism that utilizes output entropy to determine the optimal number of shots. To bypass the redundant prefilling computation during both the probing and inference phases, we incorporate a semantics-aware KV cache reuse strategy. Within this reuse strategy, to address positional encoding incompatibilities, we introduce a decoupling and re-encoding method that enables the flexible reordering of cached key-value pairs. Extensive experiments demonstrate that AdapShot achieves an average performance gain of \sim10% and a 4.64\times speedup compared to state-of-the-art DBSA.

cs.CL

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