arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

AI 大模型

AI Agent

智能体、工具调用、规划、工作流、多智能体和自主任务执行。

共收录 93944 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 工具调用 5130 篇

2602.19526 2026-02-24 cs.CL 74%

How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1

如何训练你的深度研究代理?搜索-R1中的提示、奖励和策略优化

Yinuo Xu, Shuo Lu, Jianjie Cheng, Meng Wang, Qianlong Xie, Xingxing Wang, Ran He, Jian Liang

机构 * CASIA(中国科学院自动化研究所) NLPR & MAIS(自然语言处理与人工智能研究室) School of AI UCAS(中国科学院大学人工智能学院) Meituan Inc(美团公司)

专题命中 工具调用 :agent(title);分类 cs.CL

AI总结 本文提出通过优化提示模板、奖励函数和策略优化方法来提升深度研究代理的性能,通过实验发现快速思考模板和REINFORCE在性能和稳定性上表现更优,同时引入Search-R1++基线提升了Search-R1的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.11551 2026-02-13 cs.CL 74%

SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agent

SIGHT: 基于自证证据和信息增益多样分支的强化学习

Wenlin Zhong, Jinluan Yang, Yiquan Wu, Yi Liu, Jianhang Yao, Kun Kuang

机构 * Zhejiang University(浙江大学) Chongqing Ant Consumer Finance Co., Ltd.(重庆蚂蚁消费金融有限公司) Alibaba Group(阿里巴巴集团)

专题命中 工具调用 :agent(title);分类 cs.CL

AI总结 SIGHT通过自证证据和信息增益驱动多样化分支,提升搜索代理的自主推理能力,减少冗余并增强探索策略。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.16376 2026-02-12 cs.CL 74%

Polymer-Agent: Large Language Model Agent for Polymer Design

聚合物代理:用于聚合物设计的大型语言模型代理

Vani Nigam, Achuth Chandrasekhar, Amir Barati Farimani

机构 * Department of Materials Science and Engineering, Carnegie Mellon University(材料科学与工程系,卡内基梅隆大学) Department of Mechanical Engineering, Carnegie Mellon University(机械工程系,卡内基梅隆大学)

专题命中 工具调用 :agent(title);分类 cs.CL

AI总结 本文提出基于LLM的聚合物代理,通过结构-性质预测和生成技术,助力实验室研究人员高效发现新型聚合物结构。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04220 2026-02-03 cs.CL 74%

On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement

关于代理搜索中群体相对策略优化崩溃:懒惰似然位移

Wenlong Deng, Yushu Li, Boying Gong, Yi Ren, Christos Thrampoulidis, Xiaoxiao Li

机构 * University of British Columbia(不列颠哥伦比亚大学) Vector Institute(向量研究所) Meta AI

专题命中 工具调用 :agent(title);分类 cs.CL

AI总结 本文提出LLDS正则化方法,解决GRPO在代理搜索中因LLD导致的训练崩溃问题,提升模型性能达45.2%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.13059 2025-12-16 cs.CL 74%

An Open and Reproducible Deep Research Agent for Long-Form Question Answering

一个开放且可重复的深度研究代理用于长格式问答

Ikuya Yamada, Wataru Ikeda, Ko Yoshida, Mengyu Ye, Hinata Sugimoto, Masatoshi Suzuki, Hisanori Ozaki, Jun Suzuki

机构 * Studio Ousia(Ousia工作室) Tohoku University(东京大学) DENTSU SOKEN INC.(DENTSU SOKEN公司) RIKEN(日本学术振兴会) NII LLMC(日本信息处理学会LLMC)

专题命中 工具调用 :agent(title);分类 cs.CL

AI总结 该研究提出一个开放的深度研究代理,结合开源大语言模型和网络搜索API,通过偏好微调提升长格式问答的推理质量。

Comments Technical report of a winning system in the NeurIPS MMU-RAG competition

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.08706 2025-12-10 cs.SE 74%

RESTifAI: LLM-Based Workflow for Reusable REST API Testing

RESTifAI:基于大语言模型的可重用REST API测试工作流

Leon Kogler, Maximilian Ehrhart, Benedikt Dornauer, Eduard Paul Enoiu

专题命中 工具调用 :workflow(title);分类 cs.SE

AI总结 RESTifAI是一种基于大语言模型的工具,用于生成可重用且适用于CI/CD的REST API测试,通过系统性构建测试场景并验证功能和鲁棒性。

Comments Accepted for ICSE 2026 Demonstration track

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.27569 2025-11-03 cs.CL 74%

MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval

Qi Luo, Xiaonan Li, Yuxin Wang, Tingshuo Fan, Yuan Li, Xinchi Chen, Xipeng Qiu

机构 * School of Computer Science, Fudan University(复旦大学计算机学院)

专题命中 工具调用 :agentic(title);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17052 2025-10-21 cs.AI 74%

ToolCritic: Detecting and Correcting Tool-Use Errors in Dialogue Systems

Hassan Hamad, Yingru Xu, Liang Zhao, Wenbo Yan, Narendra Gyanchandani

机构 * Amazon(亚马逊)

专题命中 工具调用 :tool-use(title);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.15692 2025-08-29 cs.LG 74%

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Jaehyun Nam, Jinsung Yoon, Jiefeng Chen, Jinwoo Shin, Sercan Ö. Arık, Tomas Pfister

机构 * Google Cloud(谷歌云) KAIST(韩国科学技术院)

专题命中 工具调用 :agent(title);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.13121 2025-08-19 cs.AI 74%

Bayesian Optimization-based Search for Agent Control in Automated Game Testing

Carlos Celemin

机构 * Production R\&D, Tencent Amsterdam, Netherlands

专题命中 工具调用 :agent(title);分类 cs.AI

Journal ref 2024 IEEE Conference on Games (CoG), Milan, Italy, 2024, pp. 1-4

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.10570 2025-05-19 cs.SE 74%

LongFuncEval: Measuring the effectiveness of long context models for function calling

Kiran Kate, Tejaswini Pedapati, Kinjal Basu, Yara Rizk, Vijil Chenthamarakshan, Subhajit Chaudhury, Mayank Agarwal, Ibrahim Abdelaziz

专题命中 工具调用 :function calling(title);分类 cs.SE

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.07184 2025-05-13 cs.CL 74%

Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs

Yifan Wei, Xiaoyan Yu, Tengfei Pan, Angsheng Li, Li Du

机构 * State Key Laboratory of CCSE,School of Computer Science and Engineering,Beihang University(信息与通信系统国家重点实验室,计算机科学与工程学院,北京航空航天大学) Beijing Academy of Artificial Intelligence(北京人工智能研究院) Beijing Institute of Technology(北京理工大学)

专题命中 工具调用 :agent(title);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.08752 2025-04-15 cs.IR cs.AI 74%

Patience is all you need! An agentic system for performing scientific literature review

David Brett, Anniek Myatt

机构 * Recursion Pharmaceutical(Recursion制药公司)

专题命中 工具调用 :agentic(title);分类 cs.AI

Comments 10 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.17598 2025-03-05 cs.DL cs.AI cs.IR 74%

Agentic AI for Improving Precision in Identifying Contributions to Sustainable Development Goals

William A. Ingram, Bipasha Banerjee, Edward A. Fox

机构 * Virginia Tech(弗吉尼亚理工大学)

专题命中 工具调用 :agentic(title);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.19356 2025-02-27 cs.LG cs.SY eess.SY 74%

Recurrent Auto-Encoders for Enhanced Deep Reinforcement Learning in Wilderness Search and Rescue Planning

Jan-Hendrik Ewers, David Anderson, Douglas Thomson

机构 * Autonomous Systems And Connectivity Research Division, University of Glasgow(格拉斯哥大学自治系统与连接研究部门)

专题命中 工具调用 :planning(title);分类 cs.LG

Comments Submitted to Machine Learning with Applications

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.02035 2024-11-05 cs.AI 74%

SibylSat: Using SAT as an Oracle to Perform a Greedy Search on TOHTN Planning

Gaspard Quenard, Damier Pellier, Humbert Fiorino

专题命中 工具调用 :planning(title);分类 cs.AI

Journal ref ECAI 2024, Oct 2024, Santiago de Compostela, Spain. pp.4157 - 4164

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.19994 2024-10-04 cs.AI 74%

A Study on the Implementation Method of an Agent-Based Advanced RAG System Using Graph

Cheonsu Jeong

专题命中 工具调用 :agent(title);分类 cs.AI

Journal ref 2024 Knowledge Management Research

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.09844 2024-07-11 cs.AI 74%

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Quentin Gallouédec, Edward Beeching, Clément Romac, Emmanuel Dellandréa

专题命中 工具调用 :agent(title);分类 cs.AI

Journal ref 38th Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET 2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.17325 2024-06-26 cs.SE 74%

AI Tool Use and Adoption in Software Development by Individuals and Organizations: A Grounded Theory Study

Ze Shi Li, Nowshin Nawar Arony, Ahmed Musa Awon, Daniela Damian, Bowen Xu

专题命中 工具调用 :tool use(title);分类 cs.SE

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.15960 2024-06-12 cs.AI 74%

Budget-Constrained Tool Learning with Planning

Yuanhang Zheng, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

专题命中 工具调用 :planning(title);分类 cs.AI

Comments Accepted for Findings of ACL 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.02626 2024-03-21 cs.CV cs.LG 74%

Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use

Imad Eddine Toubal, Aditya Avinash, Neil Gordon Alldrin, Jan Dlabal, Wenlei Zhou, Enming Luo, Otilia Stretcu, Hao Xiong, Chun-Ta Lu, Howard Zhou, Ranjay Krishna, Ariel Fuxman, Tom Duerig

专题命中 工具调用 :tool-use(title);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.15328 2024-01-31 cs.CL 74%

Equipping Language Models with Tool Use Capability for Tabular Data Analysis in Finance

Adrian Theuma, Ehsan Shareghi

专题命中 工具调用 :tool use(title);分类 cs.CL

Comments Accepted to EACL2024; code, model and dataset are available at https://raven-lm.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏
2103.11863 2022-11-15 cs.RO cs.AI 74%

Online search of unknown terrains using a dynamical system-based path planning approach

Karan Sridharan, Patrick McNamee, Zahra Nili Ahmadabadi, Jeffrey Hudack

专题命中 工具调用 :planning(title);分类 cs.AI

Journal ref J Intell Robot Syst 106, 21 (2022)

详情

展开后加载摘要…

URL PDF HTML 收藏
2208.14046 2022-08-31 cs.LG cs.DC 74%

A Deep Neural Networks ensemble workflow from hyperparameter search to inference leveraging GPU clusters

Pierrick Pochelu, Serge G. Petiton, Bruno Conche

专题命中 工具调用 :workflow(title);分类 cs.LG

Journal ref ACM International Conference Proceeding Series 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2105.04976 2022-01-03 cs.CL 74%

Designing an Automatic Agent for Repeated Language based Persuasion Games

Maya Raifer, Guy Rotman, Reut Apel, Moshe Tennenholtz, Roi Reichart

专题命中 工具调用 :agent(title);分类 cs.CL

Comments Accepted for TACL in December 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2004.01056 2021-05-17 cs.AI cs.MA 74%

Improving Confidence in the Estimation of Values and Norms

Luciano Cavalcante Siebert, Rijk Mercuur, Virginia Dignum, Jeroen van den Hoven, Catholijn Jonker

专题命中 工具调用 :agent(abstract,comments);autonomous agent(abstract);分类 cs.AI;multi-agent(comments)

Comments 16 pages, 3 figures, pre-print for the International Workshop on Coordination, Organizations, Institutions, Norms and Ethics for Governance of Multi-Agent Systems (COINE), co-located with AAMAS 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
2010.04747 2020-10-13 cs.CL 74%

MEEP: An Open-Source Platform for Human-Human Dialog Collection and End-to-End Agent Training

Arkady Arkhangorodsky, Amittai Axelrod, Christopher Chu, Scot Fang, Yiqi Huang, Ajay Nagesh, Xing Shi, Boliang Zhang, Kevin Knight

专题命中 工具调用 :agent(title);分类 cs.CL

Comments 10 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
1911.01235 2019-11-05 cs.SE 74%

Strategic API Analysis and Planning: APIS Technical Report

Jennifer Horkoff, Juho Lindman, Imed Hammouda, Eric Knauss

专题命中 工具调用 :planning(title);分类 cs.SE

详情

展开后加载摘要…

URL PDF HTML 收藏
1711.11180 2019-02-18 cs.AI 74%

Improved Learning in Evolution Strategies via Sparser Inter-Agent Network Topologies

Dhaval Adjodah, Dan Calacci, Yan Leng, Peter Krafft, Esteban Moro, Alex Pentland

专题命中 工具调用 :agent(title);分类 cs.AI

Comments This paper is obsolete

详情

展开后加载摘要…

URL PDF HTML 收藏
1802.05991 2018-05-09 cs.NE cs.AI 74%

The N-Tuple Bandit Evolutionary Algorithm for Game Agent Optimisation

Simon M Lucas, Jialin Liu, Diego Perez-Liebana

专题命中 工具调用 :agent(title);分类 cs.AI

Comments 9 pages, 3 figures, 3 table. This is the final version of the article accepted by WCCI2018

详情

展开后加载摘要…

URL PDF HTML 收藏