arXivDaily arXiv每日学术速递 周一至周五更新

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 14795 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 多智能体 14795 篇

2510.20875 2025-12-12 cs.LG cs.AI cs.CV 88%

CC-GRMAS: A Multi-Agent Graph Neural System for Spatiotemporal Landslide Risk Assessment in High Mountain Asia

CC-GRMAS:一种用于高亚洲山区时空滑坡风险评估的多智能体图神经系统

Mihir Panchal, Ying-Jung Chen, Surya Parkash

机构 * Department of Computer Engineering(计算机工程系) Dwarkadas Jivanlal Sanghvi College of Engineering(德瓦尔卡斯·吉文拉尔·桑格维学院) College of Computing(计算机学院) Georgia Institute of Technology(佐治亚理工学院) Geo-Hydro Meteorological Risks Management Division(地质-水文气象灾害管理部) National Institute of Disaster Management(国家灾害管理研究所)

专题命中 多智能体 :agent(title,abstract);multi-agent(title);planning(abstract);分类 cs.AI、cs.LG

AI总结 CC-GRMAS通过多智能体图神经系统提升高亚洲山区滑坡风险评估的准确性和响应效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.09935 2025-12-12 cs.AI cs.LG 88%

Exploring Health Misinformation Detection with Multi-Agent Debate

探索多智能体辩论中的健康 misinformation 检测

Chih-Han Chen, Chen-Han Tsai, Yu-Shao Peng

机构 * National Taiwan University(台湾国立大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

AI总结 本文提出一种两阶段框架,通过多智能体辩论与自动化评分结合,提升健康虚假信息检测的准确性与说服力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19253 2025-12-11 cs.LG cs.AI 88%

MAESTRO: Multi-Agent Environment Shaping through Task and Reward Optimization

MAESTRO:通过任务和奖励优化进行多智能体环境塑造

Boyuan Wu

机构 * Department of Mechanical and Industrial Engineering(机械与工业工程系) University of Toronto(多伦多大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

AI总结 MAESTRO通过任务和奖励优化提升多智能体强化学习的环境塑造能力,结合LLM生成课程和奖励函数,提高性能和稳定性。

Comments Preprint. 16 pages, 6 figures. Preliminary version; extended experiments and analysis forthcoming

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18321 2025-12-10 cs.CL cs.AI 88%

LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions

大语言模型难以应对同伴压力:在多智能体社交互动中崩溃

Maojia Song, Tej Deep Pala, Ruiwen Zhou, Weisheng Jin, Amir Zadeh, Chuan Li, Dorien Herremans, Soujanya Poria

机构 * Singapore University of Technology and Design(新加坡科技设计大学) Nanyang Technological University(南洋理工大学) National University of Singapore(国立新加坡大学) Lambda Labs(Lambda实验室)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.CL

AI总结 研究探讨了大语言模型在多智能体社交互动中的表现,提出KAIROS基准用于评估模型在复杂社交动态中的决策能力,发现模型规模和训练方法对抵抗社交影响至关重要。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.04652 2025-12-10 cs.AI cs.SE 88%

LLM Collaboration With Multi-Agent Reinforcement Learning

大语言模型与多智能体强化学习的协同

Shuo Liu, Tianle Chen, Zeyu Liang, Xueguang Lyu, Christopher Amato

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.SE

AI总结 本研究提出MAGRPO算法,将大语言模型协同工作建模为多智能体强化学习问题,通过有效协同提升生成质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.06046 2025-12-09 cs.SE cs.AI 88%

Beyond Prototyping: Autonomous, Enterprise-Grade Frontend Development from Pixel to Production via a Specialized Multi-Agent Framework

超越原型:通过专用多智能体框架实现从像素到生产的自主企业级前端开发

Ramprasath Ganesaraja, Swathika N, Saravanan AP, Kamalkumar Rathinasamy, Chetana Amancharla, Rahul Das, Sahil Dilip Panse, Aditya Batwe, Dileep Vijayan, Veena Ashok, Thanushree A P, Kausthubh J Rao, Alden Olivero, Roshan, Rajeshwar Reddy Manthena, Asmitha Yuga Sre A, Harsh Tripathi, Suganya Selvaraj, Vito Chin, Kasthuri Rangan Bhaskar, Kasthuri Rangan Bhaskar, Venkatraman R, Sajit Vijayakumar

机构 * EdgeVerve Systems Limited(EdgeVerve系统有限公司) Infosys Limited(Infosys有限公司) Microsoft Corporation(微软公司) BCT Digital(BCT数字)

专题命中 多智能体 :agent(title,abstract);multi-agent(title);workflow(abstract);分类 cs.AI、cs.SE

AI总结 AI4UI通过专用多智能体框架实现自主企业级前端开发,提升从像素到生产的效率与质量。

Comments 17 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21298 2025-12-09 cs.MA cs.AI cs.LG 88%

Large Language Models Miss the Multi-Agent Mark

大语言模型错失多智能体标记

Emanuele La Malfa, Gabriele La Malfa, Samuele Marro, Jie M. Zhang, Elizabeth Black, Michael Luck, Philip Torr, Michael Wooldridge

机构 * Department of Computer Science, University of Oxford(牛津大学计算机科学系) Department of Informatics, King’s College London(伦敦国王学院信息学院) Department of Engineering, University of Oxford(牛津大学工程系) University of Sussex(苏塞克斯大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

AI总结 本文指出大语言模型多智能体系统在理论与实践间的差距,强调需整合MAS核心概念以避免误解和错失机会。

Comments NeurIPS 2025 - position track -

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16708 2025-12-05 cs.SE cs.AI cs.MA 88%

Multi-Agent Code Verification via Information Theory

通过信息论的多智能体代码验证

Shreshth Rajan

机构 * Noumenon Labs(诺默恩实验室) Harvard University(哈佛大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.SE

AI总结 通过信息论构建多智能体系统,有效检测代码错误,准确率达79.3%,运行效率高。

Comments 18 pages, 3 figures, 9 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11306 2025-12-03 cs.CL cs.AI cs.MA 88%

iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference

iMAD: 智能多智能体辩论用于高效准确的LLM推理

Wei Fan, JinYi Yoon, Bo Ji

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.CL

AI总结 iMAD通过智能触发多智能体辩论,高效减少令牌消耗并提升LLM推理准确性

Comments Accepted in AAAI 2026 (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.02405 2025-12-03 cs.CV cs.AI cs.LG 88%

WISE: Weighted Iterative Society-of-Experts for Robust Multimodal Multi-Agent Debate

WISE: 加权迭代专家社会用于鲁棒多模态多智能体辩论

Anoop Cherian, River Doyle, Eyal Ben-Dov, Suhas Lohit, Kuan-Chuan Peng

机构 * Mitsubishi Electric Research Labs(三菱电机研究实验室) Cambridge Rindge and Latin School(剑桥林恩和拉丁学校)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

AI总结 本文提出WISE框架,通过多模态多智能体辩论提升视觉语言推理任务的准确性,实验显示在多个数据集上提升了2-7%的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01321 2025-12-02 cs.AI cs.LG 88%

Extending NGU to Multi-Agent RL: A Preliminary Study

将NGU扩展到多智能体RL:初步研究

Juan Hernandez, Diego Fernández, Manuel Cifuentes, Denis Parra, Rodrigo Toro Icarte

机构 * Department of Computer Science, Pontifical Catholic University of Chile(天主教智利大学计算机科学系) Millennium Institute for Intelligent Healthcare Engineering (iHEALTH)(智能医疗工程研究院) National Center for Artificial Intelligence (CENIA)(人工智能国家中心)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

AI总结 本研究将NGU算法扩展至多智能体RL环境,通过共享经验缓冲区和优化内在探索信号,提升了多智能体任务中的性能与稳定性。

Comments 9 pages, 4 figures, 1 table. Accepted at the LatinX in AI (LXAI) Workshop at NeurIPS 2025. Includes experimental results for Multi-NGU and Multi-DQN in the PettingZoo simple_tag environment

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15809 2025-12-02 cs.CL cs.AI cs.DB 88%

Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration

链式查询:通过多智能体协作释放LLM在SQL辅助表格理解中的潜力

Songyuan Sui, Hongyi Liu, Serena Liu, Li Li, Soo-Hyun Choi, Rui Chen, Xia Hu

机构 * Rice University(里士大学) Samsung Electronics America(三星电子美国分公司) Warner Bros. Discovery(华纳兄弟发现)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.CL

AI总结 链式查询通过多智能体协作提升SQL辅助表格理解的准确性与有效性

Comments AACL 2025 Main Conference (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.00047 2025-12-02 cs.CL cs.AI 88%

Emergent Convergence in Multi-Agent LLM Annotation

多智能体大语言模型注释中的涌现收敛

Angelina Parfenova, Alexander Denzler, Juergen Pfeffer

机构 * Lucerne University of Applied Sciences and Arts(卢塞恩应用科学与艺术大学) Technical University of Munich(慕尼黑技术大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.CL

AI总结 本研究通过模拟多智能体协作任务,揭示了大语言模型在无显式角色提示下涌现的协调策略,展示了词汇和语义上的收敛及不对称影响模式。

Journal ref EMNLP2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14299 2025-11-25 cs.AI cs.CL cs.MA 88%

DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning

DataSage: 基于外部知识检索、多角色辩论和多路径推理的多智能体协作以实现洞察发现

Xiaochuan Liu, Yuanfeng Song, Xiaoming Yin, Xing Chen

机构 * ByteDance, China(字节跳动)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.CL

AI总结 DataSage通过多智能体协作、外部知识检索和多路径推理,提升数据洞察发现的准确性和深度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03463 2025-11-25 cs.SE cs.AI 88%

ALMAS: an Autonomous LLM-based Multi-Agent Software Engineering Framework

ALMAS: 一种基于自主LLM的多智能体软件工程框架

Vali Tawosi, Keshav Ramani, Salwa Alamir, Xiaomo Liu

机构 * J.P. Morgan AI Research(摩根大通人工智能研究)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.SE

AI总结 ALMAS是一种基于自主LLM的多智能体软件工程框架,旨在通过模块化集成与人类开发者协作,实现软件开发生命周期中的自动化任务。

Comments Accepted to MAS-GAIN Workshop at ASE 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.02912 2025-11-25 cs.MA cs.AI cs.LG cs.SY eess.SY 88%

Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Models

传达计划,而非感知:基于具身世界模型的可扩展多智能体协调

Brennen A. Hill, Mant Koh En Wei, Thangavel Jishnuanandh

机构 * Department of Computer Science University of Wisconsin-Madison(计算机科学系 明尼苏达大学) Department of Computer Science National University of Singapore(计算机科学系 新加坡国立大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

AI总结 本文提出基于具身世界模型的意图通信方法,通过端到端学习与工程化设计对比,展示在复杂环境下更优的协调能力。

Comments Published in the Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Scaling Environments for Agents (SEA). Additionally accepted for presentation in the NeurIPS 2025 Workshop: Embodied World Models for Decision Making (EWM) and the NeurIPS 2025 Workshop: Optimization for Machine Learning (OPT)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18467 2025-11-25 cs.CR cs.AI cs.CL 88%

Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems

代码中的阴影:探索基于LLM的多智能体软件开发系统的风险与防御

Xiaoqing Wang, Keman Huang, Bin Liang, Hongyu Li, Xiaoyong Du

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.CL

AI总结 本文研究了基于LLM的多智能体软件开发系统中的安全风险,提出IMBIA攻击及Adv-IMBIA防御机制,揭示了恶意智能体对软件开发过程的威胁及防御策略。

Comments Accepted by AAAI 2026 Alignment Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18181 2025-11-25 cs.LG cs.AI 88%

MOMA-AC: A preference-driven actor-critic framework for continuous multi-objective multi-agent reinforcement learning

MOMA-AC: 一种基于偏好驱动的连续多目标多智能体强化学习框架

Adam Callaghan, Karl Mason, Patrick Mannion

机构 * University of Galway(Galway大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

AI总结 MOMA-AC通过多目标多智能体actor-critic框架,在连续空间中实现多目标策略的帕累托最优,提升预期效用和超体积,展现稳定的可扩展性。

Comments 23 pages, 5 figures

Journal ref Neurocomputing, Volume 664, 2026, 132032, ISSN 0925-2312

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17165 2025-11-24 cs.AI cs.LG 88%

MIR: Efficient Exploration in Episodic Multi-Agent Reinforcement Learning via Mutual Intrinsic Reward

MIR: 通过互惠内在奖励实现回合制多智能体强化学习中的高效探索

Kesheng Chen, Wenjian Luo, Bang Zhang, Zeping Yin, Zipeng Ye

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

AI总结 MIR通过互惠内在奖励机制,提升多智能体强化学习中稀疏回合制奖励下的探索效率与团队协作性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07392 2025-11-21 cs.CR cs.AI cs.LG 88%

From Static to Adaptive Defense: Federated Multi-Agent Deep Reinforcement Learning-Driven Moving Target Defense Against DoS Attacks in UAV Swarm Networks

从静态到适应性防御:基于联邦多智能体深度强化学习的移动目标防御用于无人机蜂群网络中的DDoS攻击防护

Yuyang Zhou, Guang Cheng, Kang Du, Zihan Chen, Tian Qin, Yuyu Zhao

机构 * School of Cyber Science and Engineering, Southeast University, Purple Mountain Laboratories, and Jiangsu Province Engineering Research Center of Security for Ubiquitous Network(网络信息安全学院,东南大学,紫金山实验室,江苏省 ubiquitous 网络安全工程研究中心)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

AI总结 本文提出基于联邦多智能体深度强化学习的移动目标防御框架,用于无人机蜂群网络中的DDoS攻击防护,通过动态防御策略提升网络韧性。

Comments 15pages; Accepted by IEEE TCCN

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15061 2025-11-20 cs.AI cs.IR cs.LG 88%

Beyond GeneGPT: A Multi-Agent Architecture with Open-Source LLMs for Enhanced Genomic Question Answering

Haodong Chen, Guido Zuccon, Teerapong Leelanupab

机构 * The University of Queensland(昆士兰大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

Comments This paper has been accepted to SIGIR-AP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13759 2025-11-19 cs.LG cs.AI 88%

Multi-Agent VLMs Guided Self-Training with PNU Loss for Low-Resource Offensive Content Detection

Han Wang, Deyi Ji, Junyu Lu, Lanyun Zhu, Hailong Zhang, Haiyang Wu, Liqun Liu, Peng Shu, Roy Ka-Wei Lee

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

Comments 8 pages, 4 figures, Fortieth AAAI Conference on Artificial Intelligence (AAAI-26)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18708 2025-11-19 cs.MA cs.AI cs.LG 88%

Skill-Aligned Fairness in Multi-Agent Learning for Collaboration in Healthcare

Promise Osaine Ekpo, Brian La, Thomas Wiener, Saesha Agarwal, Arshia Agrawal, Gonzalo Gonzalez-Pumariega, Lekan P. Molu, Angelique Taylor

机构 * Cornell Tech(康奈尔科技) Microsoft Research(微软研究院)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12630 2025-11-18 cs.CL cs.AI 88%

Knots: A Large-Scale Multi-Agent Enhanced Expert-Annotated Dataset and LLM Prompt Optimization for NOTAM Semantic Parsing

Maoqi Liu, Quan Fang, Yang Yang, Can Zhao, Kaiquan Cai

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) Beihang University(北航) State Key Laboratory of CNS/ATM(国家空管流量管理技术实验室) Aviation Data Communication Corporation(航空数据通信公司)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.CL

Comments Accepted to Advanced Engineering Informatics

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11992 2025-11-18 cs.MA cs.AI cs.LG 88%

Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams

Hung Du, Hy Nguyen, Srikanth Thudumu, Rajesh Vasa, Kon Mouzakis

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

Comments Accepted poster at the IEEE Consumer Communications & Networking Conference (CCNC) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08832 2025-11-13 cs.LG cs.AI 88%

TIGER-MARL: Enhancing Multi-Agent Reinforcement Learning with Temporal Information through Graph-based Embeddings and Representations

Nikunj Gupta, Ludwika Twardecka, James Zachary Hare, Jesse Milzman, Rajgopal Kannan, Viktor Prasanna

机构 * University of Southern California(美国南加州大学) DEVCOM Army Research Office(国防部陆军研究办公室)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08319 2025-11-12 cs.CL cs.AI cs.MA 88%

Adaptive Multi-Agent Response Refinement in Conversational Systems

Soyeong Jeong, Aparna Elangovan, Emine Yilmaz, Oleg Rokhlenko

机构 * KAIST(韩国科学技术院) Amazon(亚马逊) Collate University College London(伦敦大学学院)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.CL

Comments LaCATODA Workshop @ AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17697 2025-11-07 cs.AI cs.LG cs.MA 88%

A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning

Anjie Liu, Jianhong Wang, Samuel Kaski, Jun Wang, Mengyue Yang

机构 * HKUST (GZ)(香港科技大学(广州)) INFORMED-AI Hub(INFORMED-AI中心) University of Bristol(布里斯托大学) ELLIS Institute Finland(芬兰ELLIS研究所) Centre for Artificial Intelligence(人工智能中心) University College London(伦敦大学学院) School of Engineering Mathematics and Technology(工程数学与技术学院)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

Comments Published in NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.07109 2025-11-05 cs.CL cs.AI cs.CY cs.MA 88%

I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy

Gian Maria Campedelli, Nicolò Penzo, Massimo Stefan, Roberto Dessì, Marco Guerini, Bruno Lepri, Jacopo Staiano

机构 * Fondazione Bruno Kessler(布鲁诺·克塞勒基金会) University of Trento(特伦托大学) Samaya AI(Samaya人工智能)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04251 2025-11-04 cs.AI cs.LG cs.MA 88%

Language-Driven Coordination and Learning in Multi-Agent Simulation Environments

Zhengyang Li, Sawyer Campos, Nana Wang

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏