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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 21:50 — 2026-11-21 21:50(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 24 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.23751

Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow

Rui Li, Liyang He, Zheng Zhang, Zhenya Huang, Qi Liu

原文摘要

Autonomous LLM agents incur substantial cost and latency by invoking a large model (System-2) at every step, even when many intermediate actions choose among a small set of known candidates. Existing dual-system agents offload such decisions to a lightweight System-1 model, but rely on workflow-specific hooks authored per environment. We present AnyS1, a framework that turns human-authored procedural skills, whose instructions naturally specify where choices arise and which options apply, into a shared, domain-general source of decision points. Offline, AnyS1 mines grounded enumerable decisions across over 1,000 public skills, gathers execution-grounded trajectory states inside isolated containers to construct Any-DP, and trains a single calibrated 4B pointer System-1 with label smoothing. At run time, compiled workflows resolve routine decisions in one forward pass and fall back to System-2 when confidence falls below a calibrated threshold. Across three unseen benchmarks and distinct System-2 model families, AnyS1 preserves task reliability while cutting episode cost by 75-91% and model-call time by 63-92% relative to an uncompiled System-2 agent, and maintains performance under zero-shot threshold transfer.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2610.20474

AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents

Peidong Wang, Ying Chang, Zhiming Ma, Lirong Che, Zihao Liu, Xiaocui Yang, Shi Feng, Daqi Liu 等 13 位作者

原文摘要

Failures in long-horizon embodied tasks can arise from how a vision-language-action model (VLA) is called or from its execution capabilities. We introduce AdaRSI, an on-demand recursive self-improvement framework in which a coding agent first refines its tools and procedures, then adapts sub-steps that remain unreliable after testing alternative instructions and approaches. The agent collects demonstrations, tests their utility through temporary fine-tuning probes, and pools accepted data across tasks to train a specialist VLA that works alongside the original executor. At the end of each development round, its records are summarized into shared experience that guides subsequent diagnosis and data collection. On unseen composite tasks in RoboCasa365, AdaRSI raises success from 4.6% to 13.3%. On perturbed LIBERO-Pro 2.0 tasks, success rises from 32.9% to 49.1%. On RoboCasa365's Composite-Unseen suite, it achieves higher success than adapting every manipulation sub-step, using 34% of the GPU time and 36% of the demonstrations. On a real robot, the agent autonomously collects demonstrations and adapts the executor to recover fallen bottles, improving task completion.

cs.CL · cs.RO

版本更新 · v2arXiv:2611.17461

Tracing Knowledge and Reasoning in LLMs

Yang Wang, Xiao Wang, Yiqi Liu, Chenghao Xiao, Eleni Vasilaki, Goran Nenadic, Chenghua Lin

原文摘要

Current evaluations of Large Language Models (LLMs) report performance at the dataset or task level, revealing what a model achieves but offering little insight into the internal processing associated with its performance. We propose a task-centric framework for characterising the model-internal processing elicited by a benchmark. It combines attention- and activation-based signals with representation-based measures to characterise benchmarks spanning a continuum from retrieval-dominant to reasoning-dominant and to surface failure modes that task-level scores conceal. We evaluate 16 LLMs across 24 diverse benchmarks and conduct targeted internal-state analyses on representative models and tasks, observing systematic differences in processing between knowledge-centric and reasoning-centric tasks. We shift evaluation from asking what score a model achieves toward characterising the processing patterns associated with that score, potentially supporting more targeted benchmark selection and more informed model choice. We open source our code at https://github.com/extraordinarylab/trace-kr.

cs.CL

新论文 · v1arXiv:2611.01834

LegoEnv: Self-Evolving Agentic Environments via Modular Recombination

Zhuosong Jiang, Chengxu Wu, Junqi Liu, Yujie Yi, Siqin Wang, Zhixuan Huang, Jinqian Jiang, Lijun Xiao 等 14 位作者

原文摘要

LLM agents learn by interacting with environments, yet existing environments are designed for specific tasks and fail to generalize to new ones. Recent methods automate environment construction with LLMs. However, they generate each environment from scratch, neither reusing parts shared across environments nor carrying a fix from one environment to the rest. To address this, we propose a new paradigm of evolving environment atoms, which composes environments from reusable atoms (intent, rule, data and server) and evolves the atoms when an environment fails to give reliable feedback (e.g., an application lacks a tool the task requires). To instantiate this paradigm, we introduce LegoEnv, which builds 5,465 verified environments over 223 applications, and one round of evolution raises the share of solvable environments from 71.6% to 88.3%. On AutomationBench, SFT on these environments lifts Qwen3.6-27B from 16.0% to 32.0%, and RL with their verifiers lifts Qwen3.8-27B from 37.6% to 40.3%. Further analyses show steady gains with corpus size, transfer to unseen applications, and failures concentrated in a few shared root causes.

cs.CL · cs.AI

新论文 · v1arXiv:2611.01621

FinForesight: A Diagnostic Backtesting Benchmark for Deep Research Systems in Financial Forecasting

Fengyuan Liu, Mukai Li, Jieshun You, Yilin Zheng, Chenjia Min, Yizhou Zhang, Harper Chen, Qi Liu

原文摘要

Anticipating financial outcomes requires synthesizing evolving evidence and reasoning under uncertainty, making deep research systems promising tools for forecasting. Yet evaluating forecasting ability is challenging because historical backtests may reward memorized outcomes or information retrieved after the forecast date. Live forecasting avoids direct access to realized outcomes, but feedback arrives only after events resolve. To obtain timely feedback and assess historical scores, we introduce FinForesight, a diagnostic backtesting benchmark for financial deep research systems. Across the Chinese, U.S., and Hong Kong markets, the benchmark evaluates four forecasting tasks: valuation, return ranking, event direction, and future financial fundamentals. Two capability diagnostic tasks assess counterfactual reasoning and financial calculation, scored separately from forecasting performance. Our harness-compatible framework restricts retrieved evidence to information available at the forecast date. We compare pretraining-era, resolved post-cutoff, and live evaluations to test whether controlled backtests approximate future performance. Pretraining-era scores exceed post-cutoff scores in most temporal comparisons, and stronger retrieval controls narrow the gap between post-cutoff backtests and live results. Forecasting attribution and robustness analyses reveal how scores respond to retrieval policy and how predictions respond to prompt rewrites and numerical perturbations. The code and benchmark data are publicly available.

cs.CL · cs.LG

版本更新 · v6arXiv:2602.15620

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens

Shiqi Liu, Zeyu He, Guojian Zhan, Letian Tao, Zhilong Zheng, Jiang Wu, Yinuo Wang, Yang Guan 等 13 位作者

原文摘要

Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In practice, they often suffer from late-stage performance collapse, leading to degraded reasoning quality and unstable training. We identify a key factor behind this instability: a small fraction of tokens, termed spurious tokens (around 0.01%), which contribute little to the reasoning outcome but receive disproportionately amplified gradient updates due to inheriting the full sequence-level reward. We present a unified framework for evaluating token-level optimization impacts across spurious risk, gradient norms, and entropy changes. Building on the analysis of token characteristics that severely disrupt optimization, we propose the Silencing Spurious Tokens (S2T) mechanism to efficiently suppress their gradient perturbations. Incorporating this mechanism into a group-based objective, we propose Spurious-Token-Aware Policy Optimization (STAPO), which promotes stable and effective large-scale model refinement. Across six mathematical benchmarks and three model scales, STAPO consistently demonstrates superior entropy stability and achieves average accuracy improvements over baselines including GRPO, 20-Entropy, and JustRL under two widely-adopted evaluation settings.

cs.CL · cs.AI

新论文 · v1arXiv:2610.37276

Where Should the Evaluation Budget Go in LLM-Driven Agent Scaffold Evolution?

Sichun Luo, Yi Huang, Mukai Li, Haochen Luo, Guanzhi Deng, Haibo Wang, Jian Xu, Zefa Hu 等 10 位作者

原文摘要

Large language model (LLM)-driven agent scaffold evolution improves agent workflows through iterative candidate generation and evaluation. Evaluation both guides subsequent search and determines the final scaffold, but evaluating every candidate on the full task set incurs substantial execution costs. We investigate how evaluation budgets can be allocated across these two roles. Our experiments show that sparse feedback can sustain productive evolution, while additional targeted evaluation improves final selection. Replay analyses further show that shared informative items and a common scoring reference support comparisons among closely matched candidates. Motivated by these findings, we propose \method, an evaluation allocation framework that combines sparse search-time feedback with targeted final confirmation. A short fully evaluated warm-up establishes a shared informative core and calibrates a response model whose item parameters remain fixed during search. After search, \method refits the model and applies paired successive halving, reusing accumulated observations and executing only missing evaluations. Across four benchmarks and two evolution frameworks, \method achieves higher mean performance than full evaluation in most settings while using approximately half as many evaluation cells.

cs.LG · cs.AI · cs.CL · cs.NE

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-long.1282ACL Anthology · ACL 2026

Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage

Xueting Li, Qi Liu, Chenghao Xu Hohai University, Xu Yang, Guangtao Lyu, Jiahua Li Xidian University, Cheng Deng

原文摘要

High-resolution visual tokens impose substantial computational burdens owing to extreme redundancy in Large Visual Language Models (LVLMs). Existing visual token pruning methods typically leverage simple metrics derived from human experience, such as attention or similarity, to rank and select tokens within a highly entangled feature space. However, these metrics lack interpretability and often introduce human bias, failing to capture the genuine semantic significance of tokens, especially amidst the inherent semantic complexity and ambiguity of visual tokens. To mitigate this limitation, we propose a novel Semantically Comprehensive Token Selection (SCTS) method for unbiased, interpretable visual token pruning via a concept-driven paradigm. To unravel the model’s intrinsic semantic representation mechanism, we first introduce a Sparse Autoencoder to disentangle visual features into an interpretable space, with each dimension encoding a distinct semantic concept. We then formulate the token pruning task as a Maximum Concept Coverage problem, quantifying the Marginal Semantic Gain (MSG) of each token’s contribution to uncovered concepts and iteratively selecting tokens with the highest MSG. This concept-centric approach prioritizes tokens with unique semantic contributions, guaranteeing semantic comprehensiveness while preserving robust performance even at high compression ratios. Extensive experiments across multiple LVLM architectures and benchmarks verify that SCTS consistently outperforms state-of-the-art approaches, achieving a superior trade-off between computational efficiency and semantic completeness.

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.1371ACL Anthology · ACL 2026

LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring

Ning Li, Zheng Zhang, Zhenya Huang University of Science and Technology of China, Rui Li, Yi Zhan, Yinbo Luo, Qi Liu University of Science and Technology of China, Enhong Chen University of Science and Technology of China

原文摘要

The rapid advancement of large language models (LLMs) has driven the deployment of LLM-based AI tutors on online learning platforms. This widespread adoption highlights an urgent need for systematic benchmarks to evaluate their tutoring capabilities. However, existing evaluations predominantly focus on isolated, short-term interactions, overlooking the inherently long-term nature of learning. To bridge this gap, we introduce LongTutor, a benchmark for long-term personalized tutoring grounded in formative assessment theory. Built from expert-annotated real-world learning logs, LongTutor evaluates LLMs across three progressive tasks: historical evidence acquisition, knowledge state diagnosis, and adaptive teaching action. Our experiments reveal a critical capability mismatch: while LLMs excel at evidence acquisition, they struggle to effectively leverage long-term history for accurate diagnosis and adaptive teaching. To enable scalable benchmark expansion, we further propose an automated generator–verifier pipeline, paving the way toward truly long-term AI tutoring systems.

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.1390ACL Anthology · ACL 2026

Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees

Zheng Zhang, Qi Liu University of Science and Technology of China, Siyuan Liang Nanyang Technological University, Ning Li, Zirui Hu Nanyang Technological University, Weibo Gao University of Science and Technology of China, Rui Li, Zhenya Huang University of Science and Technology of China 等 11 位作者

原文摘要

Large language models (LLMs) have achieved remarkable performance across diverse tasks, largely driven by large-scale pretraining. However, this data abundance introduces test data contamination, where benchmark datasets overlap with pretraining corpora, undermining the reliability of model evaluation by confounding memorization with genuine generalization. To mitigate this issue, existing training data detectors attempt to identify clean (unseen) samples from contaminated test sets, but often suffer from residual contamination due to the black-box nature of LLMs. As a result, contaminated data may be mistakenly retained, leading to unreliable evaluation.To address this challenge, we propose FTD (FDR-controlled Training Data detection), a principled framework that detects and filters contaminated evaluation data while providing a statistical guarantee: the proportion of contaminated samples mistakenly retained as clean, the false discovery rate (FDR), is provably controlled below a user-specified threshold. FTD combines multiple complementary detectors via an adaptive weighting strategy, and we theoretically show it achieves high statistical power under valid FDR control. Extensive experiments on real-world benchmarks demonstrate that FTD significantly reduces residual contamination compared to existing methods while preserving evaluation consistency.

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.1647ACL Anthology · ACL 2026

ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants

Pei Wang, Yanan Wu Beijing University of Posts and Telecommunications, Xiaoshuai Song, Weixun Wang Alibaba Group, Gengru Chen Alibaba Group, Zhongwen Li, Kezhong Yan, Qi Liu 等 16 位作者

原文摘要

Large language model (LLM)-based agents are increasingly deployed in e-commerce shopping. To perform thorough, user-tailored product searches, agents should interpret personal preferences, engage in multi-turn dialogues, and ultimately retrieve and discriminate among highly similar products. However, existing research has yet to provide a unified simulation environment that consistently captures all of these aspects, and always focuses solely on evaluation benchmarks without training support. In this paper, we introduce ShopSimulator, a large-scale and challenging Chinese shopping environment. Leveraging ShopSimulator, we evaluate LLMs across diverse scenarios, finding that even the best-performing models achieve less than 40% full-success rate. Error analysis reveals that agents struggle with deep search and product selection in long trajectories, fail to balance the use of personalization cues, and to effectively engage with users. Further training exploration provides practical guidance for overcoming these weaknesses, with the combination of supervised fine-tuning (SFT) and reinforcement learning (RL) yielding significant performance improvements.

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.189ACL Anthology · ACL 2026

Disco-RAG: Discourse-Aware Retrieval-Augmented Generation

Dongqi Liu, Hang Ding, Qiming Feng, Xurong Xie, Zhucun Xue, Chengjie Wang Shanghai Jiao Tong University and Tencent YouTu Lab, Jian Li Tencent Youtu, Jiangning Zhang 等 9 位作者

原文摘要

Retrieval-Augmented Generation (RAG) has emerged as an important means of enhancing the performance of large language models (LLMs) in knowledge-intensive tasks. However, most existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing structural cues and constrains its ability to synthesize knowledge from dispersed evidence across documents. To overcome these limitations, we propose Disco-RAG, a discourse-aware framework that explicitly injects discourse signals into the generation process. Our method constructs intra-chunk discourse trees to capture local hierarchies and builds inter-chunk rhetorical graphs to model cross-passage coherence. These structures are jointly integrated into a planning blueprint that conditions the generation. Experiments on question answering and long-document summarization benchmarks show the efficacy of our approach. Disco-RAG achieves state-of-the-art results on the benchmarks without fine-tuning. These findings underscore the important role of discourse structure in advancing RAG systems.

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.1965ACL Anthology · ACL 2026

The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP

Sheriff Issaka, Keyi Wang, Yinka Ajibola, Oluwatumininu Samuel-Ipaye, Zhaoyi Zhang University of Wisconsin - Madison, Nicte Aguillon Jimenez University of Wisconsin - Madison, Evans Kofi Agyei, Abraham Lin 等 20 位作者

原文摘要

Despite representing nearly one-third of the world’s languages, African languages remain critically underserved by modern NLP technologies, with 88% classified as severely underrepresented or completely ignored in computational linguistics. We present the African Languages Lab (All Lab), a comprehensive research initiative that addresses this technological gap through systematic data collection, model development, and empirical analysis. Our contributions include: (1) a quality-controlled data collection pipeline, yielding the largest validated African multi-modal speech and text dataset spanning 40 languages with 19 billion text tokens and 12,628 hours of aligned speech data; (2) extensive experimental validation demonstrating that even modest-scale models, when fine-tuned on targeted language data, achieve substantial improvements over untrained baselines, averaging +23.69 ChrF++, +0.33 COMET, and +15.34 BLEU points across 31 evaluated languages; and (3) a comparative analysis against Google Translate in which a 1B-parameter model matched or surpassed the commercial system in several languages including Yoruba and Twi, revealing that data scarcity, rather than model scale, constitutes the primary bottleneck for low-resource NLP, and suggesting that systematic dataset development yields disproportionate returns for low-resource languages.

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.1984ACL Anthology · ACL 2026

GUIDE: Towards Scalable Advising for Research Ideas

Yaowenqi Liu, Bingxu Meng, Rui Pan University of Illinois at Urbana-Champaign, Yuxing Liu University of Illinois at Urbana-Champaign, Jerry Huang, Jiaxuan You, Tong Zhang UIUC

原文摘要

The field of AI research is advancing at an unprecedented pace, enabling automated hypothesis generation and experimental design across diverse domains such as biology, mathematics, and artificial intelligence. Despite these advancements, there remains a significant gap in the availability of scalable advising systems capable of providing high-quality, well-reasoned feedback to refine proposed hypotheses and experimental designs. To address this challenge, we explore key factors that underlie the development of robust advising systems, including model size, data reweighting, context length, confidence estimation, and structured reasoning processes. Our findings reveal that a relatively small model, when equipped with a well-compressed literature database and a structured reasoning framework, can outperform powerful general-purpose language models such as Deepseek-R1 in terms of acceptance rates for self-ranked top-30% submissions to ICLR 2025. Moreover, when limited to high-confidence predictions, our system achieves an acceptance rate exceeding 90% on the ICLR 2025 test set, underscoring its potential to significantly enhance the quality and efficiency of hypothesis generation and experimental design.

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.2001ACL Anthology · ACL 2026

C-World: A Computer Use Agent Environment Creator

Ziqiao Xi, Shuang Liang, Qi Liu University of California, San Diego, Jiaqing Zhang, Letian Peng, Fang Nan University of California, San Diego, Meshal Nayim, Tianhui Zhang University of California, San Diego 等 12 位作者

原文摘要

To close the gap between LLM-based agents and humans in planning and reasoning, agents need large-scale, diverse environments for continuous learning—yet building such environments is itself prohibitively expensive. We present C-World, an environment creation system that enables users to build agent environments on demand. We define a complete agent environment through four components: an Action Space of 5,571 format-unified tools across 204 common applications, a Task Distribution engine that synthesizes long-horizon workflows with wild constraints, a Transition Function implemented as a state controller that injects realistic failures and perturbations, and a Reward Signal combining verifiable metrics with LLM-based judgment. C-World operates in two modes: a realistic mode grounded in live API execution, and a synthesized mode powered by the World Engine, which approximates tool behavior without live service access, enabling scalable environment creation—including environments for domains and tools that do not yet exist in the real world. Evaluation of nine state-of-the-art LLMs reveals that planning ability is uniformly strong but execution remains the bottleneck, and that constraint following—not tool invocation—is the dominant failure mode. The World Engine achieves Spearman \rho = 0.883 ranking correlation with real execution, and fine-tuning on just 1,170 C-World trajectories outperforms baselines trained on 119k samples, demonstrating C-World’s dual value as a rigorous evaluation environment and a scalable data engine. Our code and data are available at https://ziqiao-git.github.io/C-World/.

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.2058ACL Anthology · ACL 2026

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang Fudan University, Honglin Guo Fudan University, Baodai Huang, Tinggang Chen, Qi Zhang 等 25 位作者

原文摘要

Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic evaluations. However, most existing benchmarks evaluate agents in simplified, idealized settings. They typically rely on pre-packaged tool interfaces, overlook critical steps, and assume inputs are clean and fully specified. Consequently, they understate the difficulty of real deployments, where uncertainty and noise are ubiquitous and agents must proactively explore the environment to uncover new tools. To bridge this gap, we present AgentGym2, a new evaluation framework with task instances grounded in real-world end-to-end working demands. Beyond reasoning and planning, it measures agents’ ability to execute end-to-end procedures, discover tools via exploration, compose tools for unseen tasks, and remain robust to noisy and underspecified information. Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2, revealing a substantial gap between the capability of current agents and the demands of real-world applications.

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.2121ACL Anthology · ACL 2026

EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

Mukai Li, Linfeng Song Google, Zhenwen Liang Tencent AI Lab, Jiahao Xu Tencent AI Lab, Shansan Gong, Qi Liu University of Hong Kong, Haitao Mi Tencent AI Lab, Dong Yu CapitalOne

原文摘要

Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP), attaining substantial performance gains through widely adopted test-time scaling strategies, notably reflective Chain-of-Thought (CoT) reasoning and increased sampling passes. However, they both introduce significant computational overhead for inference. Moreover, existing cost analyses typically regulate only the number of sampling passes, while neglecting the substantial disparities in sampling costs introduced by different scaling strategies. In this paper, we systematically compare the efficiency of different test-time scaling strategies for ATP models and demonstrate the inefficiency of the current state-of-the-art (SOTA) open-source approaches. We then investigate approaches to significantly reduce token usage and sample passes while maintaining the original performance. Specifically, we propose two complementary methods that can be integrated into a unified EconRL pipeline for amplified benefits: (1) a dynamic Chain-of-Thought (CoT) switching mechanism designed to mitigate unnecessary token consumption, and (2) Diverse parallel-scaled reinforcement learning (RL) with trainable prefixes to enhance pass rates under constrained sampling passes. Experiments on miniF2F and ProofNet demonstrate that our EconProver-GD achieves comparable performance to baseline methods with only 12% of the computational cost. This work provides actionable insights for deploying lightweight ATP models without sacrificing performance.

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.431ACL Anthology · ACL 2026

OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows

Qiushi Sun University of Hong Kong, Mukai Li, Zhoumianze Liu, Zhihui Xie University of Hong Kong, Fangzhi Xu Xi'an Jiaotong University, Zhangyue Yin, Kanzhi Cheng Nanjing University, Zehao Li University of Science and Technology of China 等 14 位作者

原文摘要

Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms. While these agents hold great promise for advancing digital automation, their potential for unsafe operations, such as system compromise and privacy leakage, is raising significant concerns. Detecting these safety concerns across the vast and complex operational space of mobile environments presents a formidable challenge that remains critically underexplored. To establish a foundation for mobile agent safety research, we introduce MobileRisk-Live, a dynamic sandbox environment accompanied by a safety detection benchmark comprising realistic trajectories with fine-grained annotations. Built upon this, we propose OS-Sentinel, a novel hybrid safety detection framework that synergistically combines a Formal Verifier for detecting explicit system-level violations with a VLM-based Contextual Judge for assessing contextual risks and agent actions. Experiments show that achieves 10%–30% improvements over existing approaches across multiple metrics. Further analysis provides critical insights that foster the development of safer and more reliable autonomous mobile agents. Our code, environment, and data are available at https://qiushisun.github.io/OS-Sentinel-Home/.

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.538ACL Anthology · ACL 2026

Cognitive Alpha Mining via LLM-Driven Code-Based Evolution

Fengyuan Liu, Yi Huang China Mobile Research Institute, Sichun Luo University of Hong Kong, Yuqi Wang, Yazheng Yang, Xinye Li, Zefa Hu Jiutian Research, China Mobile, Junlan Feng 等 9 位作者

原文摘要

Discovering effective predictive signals, or “alphas,” from financial data with high dimensionality and extremely low signal-to-noise ratio remains a difficult open problem. Despite progress in deep learning, genetic programming, and, more recently, large language model (LLM)–based factor generation, existing approaches still explore only a narrow region of the vast alpha search space. Neural models tend to produce opaque and fragile patterns, while symbolic or formula-based methods often yield redundant or economically ungrounded expressions that generalize poorly. Although different in form, these paradigms share a key limitation: none can conduct broad, structured, and human-like exploration that balances logical consistency with creative leaps.To address this gap, we introduce the Cognitive Alpha Mining Framework (CogAlpha), which combines code-level alpha representation with LLM-driven reasoning and evolutionary search. Treating LLMs as adaptive cognitive agents, our framework iteratively refines, mutates, and recombines alpha candidates through multi-stage prompts and financial feedback. This synergistic design enables deeper thinking, richer structural diversity, and economically interpretable alpha discovery, while greatly expanding the effective search space.Experiments on 5 stock datasets from 3 stock markets demonstrate that CogAlpha consistently discovers alphas with superior predictive accuracy, robustness, and generalization over existing methods. Our results highlight the promise of aligning evolutionary optimization with LLM-based reasoning for automated and explainable alpha discovery.

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.64ACL Anthology · ACL 2026

RAM-SD: Retrieval-Augmented Multi-agent framework for Sarcasm Detection

Ziyang Zhou, Ziqi Liu, Yan Wang, Yiming Lin, Yangbin Chen Xi'an Jiaotong-Liverpool University

原文摘要

Sarcasm detection remains a significant challenge due to its reliance on nuanced contextual understanding, world knowledge, and multi-faceted linguistic cues that vary substantially across different sarcastic expressions. Existing approaches, from fine-tuned transformers to large language models, apply a uniform reasoning strategy to all inputs, struggling to address the diverse analytical demands of sarcasm. These demands range from modeling contextual expectation violations to requiring external knowledge grounding or recognizing specific rhetorical patterns. To address this limitation, we introduce RAM-SD, a Retrieval-Augmented Multi-Agent framework for Sarcasm Detection. The framework operates through four stages: (1) contextual retrieval grounds the query in both sarcastic and non-sarcastic exemplars; (2) a meta-planner classifies the sarcasm type and selects an optimal reasoning plan from a predefined set; (3) an ensemble of specialized agents performs complementary, multi-view analysis; and (4) an integrator synthesizes these analyses into a final, interpretable judgment with a natural language explanation. Evaluated on four standard benchmarks, RAM-SD achieves a state-of-the-art Macro-F1 of 77.74%, outperforming the strong GPT-4o+CoC baseline by 7.01 points. Our framework not only sets a new performance benchmark but also provides transparent and interpretable reasoning traces, illuminating the cognitive processes behind sarcasm comprehension.

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.957ACL Anthology · ACL 2026

Fisher-Driven Adaptive Locating for Knowledge Editing in Large Language Models

Chenghao Xu Hohai University, Jiexi Yan, Guangtao Lyu, Qi Liu, Muli Yang A*STAR, Cheng Deng

原文摘要

Large language models (LLMs) store extensive factual knowledge acquired during pretraining, yet this knowledge is inherently static and may become inaccurate or outdated, leading to knowledge hallucinations. Knowledge editing offers an efficient alternative to full retraining by enabling targeted factual updates while preserving overall model behavior. Existing locate-then-edit methods, however, rely on fixed layer selection strategies, treating the locating stage as a static design choice and failing to account for the hierarchical and instance-dependent nature of knowledge representation in LLMs. In this paper, we propose FiDAL, a Fisher-driven adaptation-aware locating strategy that dynamically identifies which model components should be edited for a given knowledge update. FiDAL formulates localization as a weight-level decision problem and leverages Fisher Information to select layers that are both influential and sensitive to factual modifications. A lightweight probing stage with low-rank modulation enables efficient localization with minimal overhead. Experiments on standard benchmarks demonstrate that FiDAL consistently improves editing effectiveness and knowledge preservation across multiple editing methods.

cs.CL

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

新论文 · v1arXiv:2503.19786Google Research

Gemma 3 技术报告

Gemma 3 Technical Report

Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova 等 216 位作者

AI 速读 基于摘要

Gemma 3 是 Gemma 轻量级开放模型家族的多模态新版本,参数规模为 1B 至 27B,新增视觉理解、更广的语言覆盖和至少 128K 的长上下文,并通过调整局部与全局注意力层比例来降低 KV-cache 内存。

cs.CL · cs.AI

查看原文摘要

We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision understanding abilities, a wider coverage of languages and longer context - at least 128K tokens. We also change the architecture of the model to reduce the KV-cache memory that tends to explode with long context. This is achieved by increasing the ratio of local to global attention layers, and keeping the span on local attention short. The Gemma 3 models are trained with distillation and achieve superior performance to Gemma 2 for both pre-trained and instruction finetuned versions. In particular, our novel post-training recipe significantly improves the math, chat, instruction-following and multilingual abilities, making Gemma3-4B-IT competitive with Gemma2-27B-IT and Gemma3-27B-IT comparable to Gemini-1.5-Pro across benchmarks. We release all our models to the community.

版本更新 · v5arXiv:2403.05530Google Research

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent 等 1137 位作者

原文摘要

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

cs.CL · cs.AI