AI Agent - arXivDaily 专题

1902.06527 2019-02-19 cs.LG cs.AI cs.MA 88%

Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement Learning

Woojun Kim, Myungsik Cho, Youngchul Sung

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

Comments The 33rd AAAI Conference on Artificial Intelligence (AAAI) 2019

1902.01554 2019-02-06 cs.AI cs.LG cs.MA 88%

Learning to Schedule Communication in Multi-agent Reinforcement Learning

Daewoo Kim, Sangwoo Moon, David Hostallero, Wan Ju Kang, Taeyoung Lee, Kyunghwan Son, Yung Yi

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

Comments Accepted in ICLR 2019

1901.08492 2019-01-28 cs.MA cs.AI cs.LG 88%

Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning

Sanjeevan Ahilan, Peter Dayan

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

1802.09756 2018-11-02 stat.ML cs.AI cs.LG 88%

Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising

Junqi Jin, Chengru Song, Han Li, Kun Gai, Jun Wang, Weinan Zhang

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

Journal ref CIKM 2018, Turin, Italy

1810.08515 2018-10-24 cs.LG cs.AI cs.CV stat.ML 88%

Transfer Learning versus Multi-agent Learning regarding Distributed Decision-Making in Highway Traffic

Mark Schutera, Niklas Goby, Dirk Neumann, Markus Reischl

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

Comments Proc. of the 10th International Workshop on Agents in Traffic and Transportation (ATT 2018), co-located with ECAI/IJCAI, AAMAS and ICML 2018 conferences (FAIM 2018)

Journal ref CEUR Workshop Proceedings 2018

1809.11044 2018-10-01 cs.LG cs.AI cs.MA stat.ML 88%

Relational Forward Models for Multi-Agent Learning

Andrea Tacchetti, H. Francis Song, Pedro A. M. Mediano, Vinicius Zambaldi, Neil C. Rabinowitz, Thore Graepel, Matthew Botvinick, Peter W. Battaglia

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

1706.06122 2018-10-01 cs.LG cs.AI 88%

VAIN: Attentional Multi-agent Predictive Modeling

Yedid Hoshen

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

Comments NIPS 2017 Wrong sign fixed in Eqs:3-5

1809.03152 2018-09-11 cs.AI cs.GT cs.LG 88%

A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising

Di Wu, Cheng Chen, Xun Yang, Xiujun Chen, Qing Tan, Jian Xu, Kun Gai

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

1807.09936 2018-07-27 cs.LG cs.AI cs.MA stat.ML 88%

Multi-Agent Generative Adversarial Imitation Learning

Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon

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

1807.09427 2018-07-26 cs.AI cs.LG stat.ML 88%

Multi-Agent Reinforcement Learning: A Report on Challenges and Approaches

Sanyam Kapoor

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

Comments 25 pages, 6 figures

1703.04908 2018-07-25 cs.AI cs.CL 88%

Emergence of Grounded Compositional Language in Multi-Agent Populations

Igor Mordatch, Pieter Abbeel

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

1704.02906 2018-07-17 cs.CV cs.AI cs.GR cs.LG stat.ML 88%

Multi-Agent Diverse Generative Adversarial Networks

Arnab Ghosh, Viveka Kulharia, Vinay Namboodiri, Philip H. S. Torr, Puneet K. Dokania

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

Comments This is an updated version of our CVPR'18 paper with the same title. In this version, we also introduce MAD-GAN-Sim in Appendix B

1703.06182 2018-05-23 cs.LG cs.AI cs.MA 88%

Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability

Shayegan Omidshafiei, Jason Pazis, Christopher Amato, Jonathan P. How, John Vian

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

Comments Accepted to ICML 2017

Journal ref Proceedings of the 34th International Conference on Machine Learning (ICML 2017), Sydney, Australia, PMLR 70:2681-2690, 2017

1702.08887 2018-05-22 cs.AI cs.LG cs.MA 88%

Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning

Jakob Foerster, Nantas Nardelli, Gregory Farquhar, Triantafyllos Afouras, Philip H. S. Torr, Pushmeet Kohli, Shimon Whiteson

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

Comments Camera-ready version, International Conference of Machine Learning 2017; updated to fix print-breaking image

1802.09640 2018-03-28 cs.AI cs.LG 88%

Modeling Others using Oneself in Multi-Agent Reinforcement Learning

Roberta Raileanu, Emily Denton, Arthur Szlam, Rob Fergus

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

Comments 10 pages, 16 figures, submitted to ICML 2018

1802.08757 2018-02-28 cs.LG cs.AI cs.MA math.OC stat.ML 88%

Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents

Kaiqing Zhang, Zhuoran Yang, Han Liu, Tong Zhang, Tamer Başar

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

1707.04402 2018-02-28 cs.MA cs.AI cs.LG 88%

Lenient Multi-Agent Deep Reinforcement Learning

Gregory Palmer, Karl Tuyls, Daan Bloembergen, Rahul Savani

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

Comments 9 pages, 6 figures, AAMAS2018 Conference Proceedings

1706.08502 2017-08-22 cs.CL cs.AI cs.CV 88%

Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog

Satwik Kottur, José M. F. Moura, Stefan Lee, Dhruv Batra

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

Comments 9 pages, 7 figures, 2 tables, accepted at EMNLP 2017 as short paper

1704.02882 2017-05-23 cs.AI cs.LG cs.MA stat.ML 88%

Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning

El Mahdi El Mhamdi, Rachid Guerraoui, Hadrien Hendrikx, Alexandre Maurer

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

1612.07182 2017-03-07 cs.CL cs.CV cs.GT cs.LG cs.MA 88%

Multi-Agent Cooperation and the Emergence of (Natural) Language

Angeliki Lazaridou, Alexander Peysakhovich, Marco Baroni

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

Comments Accepted at ICLR 2017

1612.01294 2016-12-06 cs.CV cs.AI cs.LG cs.NE 88%

Message Passing Multi-Agent GANs

Arnab Ghosh, Viveka Kulharia, Vinay Namboodiri

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

Comments The first 2 authors contributed equally for this work

1605.06676 2016-05-25 cs.AI cs.LG cs.MA 88%

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

Jakob N. Foerster, Yannis M. Assael, Nando de Freitas, Shimon Whiteson

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

1604.05577 2016-04-20 cs.SE cs.AI cs.MA 88%

Contribution to the Formal Specification and Verification of a Multi-Agent Robotic System

Nadeem Akhtar, Malik M. Saad Missen

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

Comments arXiv admin note: text overlap with arXiv:1501.05120

Journal ref European Journal of Scientific Research, ISSN 1450-216X / 1450-202X Vol.117 No.1 January, 2014, pp. 35-55

1411.3792 2014-11-17 cs.AI cs.MA cs.SE 88%

An Approach to Model Checking of Multi-agent Data Analysis

Natalia Garanina, Eugene Bodin, Elena Sidorova

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

Comments In Proceedings MOD* 2014, arXiv:1411.3453

Journal ref EPTCS 168, 2014, pp. 32-44

cs/0009012 2009-11-30 cs.CL cs.AI cs.MA 88%

Modeling Ambiguity in a Multi-Agent System

Christof Monz

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

Comments 7 pages

2608.24306 2026-08-26 cs.CL 新提交 88%

Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research

该追责哪个智能体？定位智能体深度研究中的忠实度与引用错误

Eran Hirsch, David Wan, Han Wang, Elias Stengel-Eskin, Mohit Bansal, Ido Dagan

机构 * Bar-Ilan University（巴伊兰大学）； UNC Chapel Hill（北卡罗来纳大学教堂山分校）； University of Texas at Austin（德克萨斯大学奥斯汀分校）

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

AI总结本研究针对智能体深度研究系统的引用召回率低问题，提出定位错误来源的评估方法与四类错误分类法，应用于三个开源系统发现协调器为主要错误来源，通过简单干预提升5%引用召回率且不降低质量。

Comments Accepted to EMNLP 2026 (Main Conference). Code: https://github.com/eranhirs/who-is-the-agent-to-blame

2505.18334 2026-07-28 cs.RO cs.AI cs.MA 版本更新 88%

CoopReflect: Towards Natural Language Communication for Cooperative Autonomous Driving via Multi-Agent Learning

CoopReflect：通过多智能体学习实现协同自动驾驶的自然语言通信

Jiaxun Cui, Chen Tang, Jarrett Holtz, Janice Nguyen, Alessandro G. Allievi, Hang Qiu, Peter Stone

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）； Robert Bosch LLC（罗伯特·博世有限公司）； University of California, Riverside（加州大学河滨分校）； Sony AI（索尼人工智能）

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

AI总结研究探索自然语言用于车对车通信的潜力，开发基于大语言模型的驾驶智能体，引入CoopReflect多智能体学习框架，通过试错等为智能体配备相关知识，实验表明其能生成更优消息，实现跨场景泛化并降低决策延迟。

Journal ref Proc. 25th Int. Conf. Autonomous Agents and Multiagent Systems (AAMAS), 744-752 (2026)

2607.18719 2026-07-22 cs.MA cs.AI 新提交 88%

Strategy-Following Multi-Agent Deep Reinforcement Learning Considering Control Strategies Provided to Other Agents

考虑提供给其他智能体的控制策略的策略跟随多智能体深度强化学习

Yamato Takahagi, Gentoku Nakasone, Yoshinari Motokawa, Toshiharu Sugawara

机构 * Department of Computer Science and Communications Engineering（计算机科学与通信工程系）； Waseda University（早稻田大学）

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

AI总结研究提出多智能体系统学习方法，能让智能体通过人类指令控制，未接指令的智能体可基于其他智能体行动补充工作。该方法扩展了可控性研究，实验表明使用此方法的智能体性能优于传统方法，能转向更好的合作结构。

Comments 8 pages, 14 figures, 24th IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT 2025)

2606.20485 2026-06-19 q-fin.RM cs.AI nlin.AO physics.soc-ph 新提交 88%

Optimal Order of Multi-Agent and General Many-Body Systems

多智能体与一般多体系统的最优序

Jake J. Xia

机构 * Harvard Management Company（哈佛管理公司）； Massachusetts Institute of Technology（麻省理工学院）

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

AI总结提出一个分析多智能体系统的通用框架，基于智能体的权力和响应函数，推导出宏观性质，并引入风险偏好系数研究增长与韧性之间的权衡，得出最优有序度。

Comments Key Words: Many body systems, multi agent crowd interactions, feedback loops, agent power, response function, utility function, risk appetite, order, optimal order, fragility, mobility, synchronization, useful energy, entropy, concentration, correlation, task dependency, receiver dependency, collective intelligence, AI model scaling law

2605.00914 2026-05-05 cs.MA cs.AI 88%

The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate

共识的成本：孤立自我修正胜过无指导的同质多智能体辩论

Blaž Bertalanič, Carolina Fortuna

机构 * Jo z ef Stefan Institute Ljubljana Slovenia ； Jo z ef Stefan Institute

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

AI总结研究探讨了同质多智能体辩论中共识失败的机制，发现孤立自我修正在成本与准确性上优于无指导的同伴交流，尤其在参数规模7-8B时效果更佳。

Comments 19 pages, ACM Conference on AI and Agentic Systems

1. 多智能体 14943 篇

Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement Learning

Learning to Schedule Communication in Multi-agent Reinforcement Learning

Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning

Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising

Transfer Learning versus Multi-agent Learning regarding Distributed Decision-Making in Highway Traffic

Relational Forward Models for Multi-Agent Learning

VAIN: Attentional Multi-agent Predictive Modeling

A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising

Multi-Agent Generative Adversarial Imitation Learning

Multi-Agent Reinforcement Learning: A Report on Challenges and Approaches

Emergence of Grounded Compositional Language in Multi-Agent Populations

Multi-Agent Diverse Generative Adversarial Networks

Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability

Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning

Modeling Others using Oneself in Multi-Agent Reinforcement Learning

Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents

Lenient Multi-Agent Deep Reinforcement Learning

Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog

Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning

Multi-Agent Cooperation and the Emergence of (Natural) Language

Message Passing Multi-Agent GANs

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

Contribution to the Formal Specification and Verification of a Multi-Agent Robotic System

An Approach to Model Checking of Multi-agent Data Analysis

Modeling Ambiguity in a Multi-Agent System

Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research

CoopReflect: Towards Natural Language Communication for Cooperative Autonomous Driving via Multi-Agent Learning

Strategy-Following Multi-Agent Deep Reinforcement Learning Considering Control Strategies Provided to Other Agents

Optimal Order of Multi-Agent and General Many-Body Systems

The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate