AI Agent - arXivDaily 专题

2106.03160 2021-06-09 cs.CE 89%

Multi-agent Modeling of Hazard-Household-Infrastructure Nexus for Equitable Resilience Assessment

Amir Esmalian, Wanqiu Wang, Ali Mostafavi

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

2106.00936 2021-06-03 cs.RO 89%

Least-Restrictive Multi-Agent Collision Avoidance via Deep Meta Reinforcement Learning and Optimal Control

Salar Asayesh, Mo Chen, Mehran Mehrandezh, Kamal Gupta

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

2105.00434 2021-05-04 cs.RO cs.SY eess.SY 89%

Dynamic Routing for Traffic Flow through Multi-agent Systems

Jizhe Zhou, Qiwei Chen, Qin Li

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

1912.10539 2021-04-15 eess.SY cs.SY math.OC 89%

PDE-based multi-agent formation control using flatness and backstepping: analysis, design and robot experiments

Gerhard Freudenthaler, Thomas Meurer

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Comments Preprint submitted to Automatica (accepted as Regular Paper on October 25, 2019)

2010.08184 2021-03-05 cs.RO 89%

PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelong

Mehul Damani, Zhiyao Luo, Emerson Wenzel, Guillaume Sartoretti

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Comments \c{opyright} 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

1809.03531 2021-02-02 cs.RO 89%

PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning

Guillaume Sartoretti, Justin Kerr, Yunfei Shi, Glenn Wagner, T. K. Satish Kumar, Sven Koenig, Howie Choset

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Comments \c{opyright} 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

1904.11372 2021-01-28 q-bio.CB nlin.AO q-bio.PE 89%

A Multi-agent approach for $\textit{in silico}$ simulations of micro-biological systems

Daniele Proverbio, Luca Gallo, Barbara Passalacqua, Jacopo Pellegrino, Marco Maggiora

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；autonomous agent(abstract)

Journal ref Swarm Intell 14, 313-331 (2020)

2010.09054 2020-12-15 cs.MA 89%

Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences

Raphael Köster, Kevin R. McKee, Richard Everett, Laura Weidinger, William S. Isaac, Edward Hughes, Edgar A. Duéñez-Guzmán, Thore Graepel, Matthew Botvinick, Joel Z. Leibo

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

2009.14495 2020-10-01 eess.SY cs.SY 89%

Forced variational integrator for distance-based shape control with flocking behavior of multi-agent systems

Leonardo Colombo, Patricio Moreno, Mengbin Ye, Hector Garcia de Marina, Ming Cao

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；autonomous agent(abstract)

Comments Presented at IFAC World Congress 2020, 6 pages + refs

2009.03934 2020-09-10 cs.MA 89%

Metis: Multi-Agent Based Crisis Simulation System

George Sidiropoulos, Chairi Kiourt, Lefteris Moussiades

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

2003.01848 2020-07-17 cs.AI cs.CL cs.LG cs.MA 89%

On Emergent Communication in Competitive Multi-Agent Teams

Paul Pu Liang, Jeffrey Chen, Ruslan Salakhutdinov, Louis-Philippe Morency, Satwik Kottur

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

Comments AAMAS 2020, code: https://github.com/pliang279/Competitive-Emergent-Communication

2005.07064 2020-05-15 cs.CL cs.AI cs.LG 89%

Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning

Angeliki Lazaridou, Anna Potapenko, Olivier Tieleman

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

Comments to appear at ACL 2020

2004.05185 2020-04-14 cs.CY 89%

Stochastic Multi-Agent-Based Model to Measure Community Resilience-Part 2: Simulation Results

Jaber Valinejad, Lamine Mili, Konstantinos Triantis, Michael von Spakovsky, C. Natalie van der Wal

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

1911.08626 2019-11-21 cs.RO cs.MA cs.SY eess.SY math.OC 89%

Intermittent Connectivity for Exploration in Communication-Constrained Multi-Agent Systems

Filip Klaesson, Petter Nilsson, Aaron D. Ames, Richard M. Murray

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

1911.03743 2019-11-12 cs.MA cs.AI cs.CL cs.LG 89%

A perspective on multi-agent communication for information fusion

Homagni Saha, Vijay Venkataraman, Alberto Speranzon, Soumik Sarkar

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

Comments NeuRIPS 2019, Workshop on Visually Grounded Interaction and Language, Vancouver, CA

1910.04995 2019-10-14 eess.SY cs.SY math.OC 89%

Variational collision and obstacle avoidance of multi-agent systems on Riemannian manifolds

Rama Seshan Chandrasekaran, Leonardo J. Colombo, Margarida Camarinha, Ravi Banavar, Anthony Bloch

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Comments Submitted to European Control Conference 2020

1906.05616 2019-06-14 cs.NE cs.MA 89%

Decentralised Multi-Demic Evolutionary Approach to the Dynamic Multi-Agent Travelling Salesman Problem

Thomas E. Kent, Arthur G. Richards

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

1905.01361 2019-05-07 cs.MA math.OC 89%

Fuzzy Q-Learning Based Multi-Agent System for Intelligent Traffic Control by a Game Theory Approach

Abolghasem Daeichian, Amir Haghani

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；autonomous agent(abstract)

Comments 10 pages, 10 figures

Journal ref Arabian Journal for Science and Engineering (2017): 1-7

1810.01155 2019-03-01 cs.IT cs.MA math.IT 89%

Learning-Based Physical Layer Communications for Multi-agent Collaboration

Arsham Mostaani, Osvaldo Simeone, Symeon Chatzinotas, Bjorn Ottersten

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；autonomous agent(abstract)

Comments Submitted to SPAWC 2019

1801.00258 2018-01-03 math.OC 89%

Distributed Observers Design for Leader-Following Control of Multi-Agent Networks (Extended Version)

Yiguang Hong, Guanrong Chen, Linda Bushnell

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；autonomous agent(abstract)

Comments Automatica 2008

1511.05774 2015-11-19 cs.ET 89%

Applications of Multi-Agent Slime Mould Computing

Jeff Jones

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Journal ref Int. J. of Parallel, Emergent and Distributed Systems, 1-30 (2015)

1108.3223 2015-03-19 cs.MA cs.CG cs.DC 89%

Randomized Optimal Consensus of Multi-agent Systems

Guodong Shi, Karl Henrik Johansson

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；autonomous agent(abstract)

0806.3031 2009-12-01 cs.MA 89%

Multi Site Coordination using a Multi-Agent System

Thibaud Monteiro, Daniel Roy, Didier Anciaux

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Journal ref Computers in Industry 58, 4 (2007) pp. 367-377

2608.14588 2026-08-18 cs.AI cs.CL cs.MA 新提交 89%

The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines

幻觉滚雪球：将多智能体大语言模型流水线中的错误传播建模为状态转移

Prabhjot Singh, Bhushan Pawar

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

AI总结该研究发现多智能体LLM流水线中存在幻觉滚雪球效应，即幻觉会随状态转移而逃逸，且边界门控验证比末端检查更能有效降低幻觉存活率，还提出了最优验证资源分配策略。

Comments 10 pages, 3 figures; accepted at the FAGEN Workshop (Failure Modes in Agentic AI), ICML 2026

2606.20236 2026-06-19 cs.AI cs.LG cs.MA 新提交 89%

A Multi-Agent system for Multi-Objective constrained optimization

多目标约束优化的多智能体系统

Federica Filippini

机构 * University of Milano-Bicocca（米兰比可卡大学）

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

AI总结提出MAMO，通过多智能体强化学习解耦任务执行与目标设计，自动学习奖励权重以平衡主目标优化与约束违反，提升动态环境下RL的自主性和鲁棒性。

Comments Presented at the 17th Workshop on Optimization and Learning in Multiagent Systems (OptLearnMAS, https://optlearnmas.github.io), co-located with the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026)

2603.15183 2026-03-17 cs.DC cs.AI cs.LG cs.MA 89%

Token Coherence: Adapting MESI Cache Protocols to Minimize Synchronization Overhead in Multi-Agent LLM Systems

令牌一致性：适应MESI缓存协议以最小化多智能体大语言模型系统中的同步开销

Vladyslav Parakhin

机构 * Independent Researcher（独立研究者）

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

AI总结本文提出令牌一致性理论，通过将MESI协议应用于多智能体系统，减少同步开销，验证了在多智能体大语言模型中同步成本与缓存一致性问题的对应关系，并通过形式化验证协议确保安全性与一致性。

Comments 25 pages. Code and reproduction scripts at https://github.com/hipvlady/agent-coherence

2603.10098 2026-03-12 cs.GT cs.AI cs.LG 89%

Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models

代码空间响应预言机：利用大语言模型生成可解释的多智能体策略

Daniel Hennes, Zun Li, John Schultz, Marc Lanctot

机构 * Google（谷歌）； DeepMind（深度思维）

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

AI总结本文提出代码空间响应预言机，利用大语言模型生成可解释的多智能体策略，通过代码生成任务提升策略的可解释性和复杂策略发现能力。

Comments Accepted as an Extended Abstract at the Twenty-Fifth International Conference on Autonomous Agents and Multiagent Systems (AAMAS)

2602.22786 2026-02-27 cs.MA cs.AI cs.LG 89%

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

QSIM：通过动作相似性加权Q学习缓解多智能体强化学习中的过估计

Yuanjun Li, Bin Zhang, Hao Chen, Zhouyang Jiang, Dapeng Li, Zhiwei Xu

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

AI总结 QSIM通过动作相似性加权Q学习缓解多智能体强化学习中的过估计问题，提升学习稳定性与性能。

Comments 19 pages, 15 figures, 7tables. Accepted to the 36th International Conference on Automated Planning and Scheduling (ICAPS 2026)

2602.08104 2026-02-24 cs.AI cs.LG cs.MA 89%

Interpretable Failure Analysis in Multi-Agent Reinforcement Learning Systems

多智能体强化学习系统中的可解释性故障分析

Risal Shahriar Shefin, Debashis Gupta, Thai Le, Sarra Alqahtani

机构 * Wake Forest University（威克森林大学）； Indiana University（印第安纳大学）

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

AI总结本文提出了一种两阶段梯度框架，用于多智能体强化学习系统中可解释的故障检测与归因分析，通过几何分析和敏感性分析提高故障诊断的透明度和准确性。

Comments Accepted to the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026)

2601.07136 2026-01-13 cs.SE cs.AI 89%

A Large-Scale Study on the Development and Issues of Multi-Agent AI Systems

多智能体AI系统的发展与问题的大型研究

Daniel Liu, Krishna Upadhyay, Vinaik Chhetri, A. B. Siddique, Umar Farooq

机构 * Louisiana State University（路易斯安那州立大学）； University of Kentucky（肯塔基大学）

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

AI总结本文通过分析多智能体AI系统的开发和问题，揭示了生态系统的发展模式及维护挑战，强调了改进测试和文档的重要性。

Comments 8 pages, 8 figures, IEEE BigData Workshop on Software Engineering for Agentic AI 2025

1. 多智能体 14777 篇

Multi-agent Modeling of Hazard-Household-Infrastructure Nexus for Equitable Resilience Assessment

Least-Restrictive Multi-Agent Collision Avoidance via Deep Meta Reinforcement Learning and Optimal Control

Dynamic Routing for Traffic Flow through Multi-agent Systems

PDE-based multi-agent formation control using flatness and backstepping: analysis, design and robot experiments

PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelong

PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning

A Multi-agent approach for $\textit{in silico}$ simulations of micro-biological systems

Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences

Forced variational integrator for distance-based shape control with flocking behavior of multi-agent systems

Metis: Multi-Agent Based Crisis Simulation System

On Emergent Communication in Competitive Multi-Agent Teams

Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning

Stochastic Multi-Agent-Based Model to Measure Community Resilience-Part 2: Simulation Results

Intermittent Connectivity for Exploration in Communication-Constrained Multi-Agent Systems

A perspective on multi-agent communication for information fusion

Variational collision and obstacle avoidance of multi-agent systems on Riemannian manifolds

Decentralised Multi-Demic Evolutionary Approach to the Dynamic Multi-Agent Travelling Salesman Problem

Fuzzy Q-Learning Based Multi-Agent System for Intelligent Traffic Control by a Game Theory Approach

Learning-Based Physical Layer Communications for Multi-agent Collaboration

Distributed Observers Design for Leader-Following Control of Multi-Agent Networks (Extended Version)

Applications of Multi-Agent Slime Mould Computing

Randomized Optimal Consensus of Multi-agent Systems

Multi Site Coordination using a Multi-Agent System

The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines

A Multi-Agent system for Multi-Objective constrained optimization

Token Coherence: Adapting MESI Cache Protocols to Minimize Synchronization Overhead in Multi-Agent LLM Systems

Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

Interpretable Failure Analysis in Multi-Agent Reinforcement Learning Systems

A Large-Scale Study on the Development and Issues of Multi-Agent AI Systems