Multi-agent system

Related papers: 20

About

A multi-agent system (MAS) is a computational framework composed of multiple autonomous agents — software programs, robots, or other intelligent entities — that perceive their environment, make independent decisions, and interact with one another to accomplish individual or collective goals. In robotics and AI, MAS are used to coordinate teams of robots for tasks such as formation control, search and rescue, distributed sensing, and cooperative manipulation, where agents communicate locally or operate without direct communication to achieve emergent group behavior. Agents may be homogeneous or heterogeneous, and their interactions can be cooperative, competitive, or mixed, depending on the application. Multi-agent reinforcement learning extends this framework by enabling agents to learn effective joint policies through experience. MAS matter because they offer scalability, robustness, and parallelism that single-agent approaches cannot match — if one agent fails, others continue operating. They also enable solutions to problems too complex or spatially distributed for any individual agent, making them foundational to modern autonomous systems, swarm robotics, and human-autonomy teaming applications.

Top Cited Papers

An Introduction to MultiAgent Systems

Michael Wooldridge

Citations: 5185 • 2002

An Overview of Recent Progress in the Study of Distributed Multi-Agent Coordination

Yongcan Cao, Wenwu Yu, Wei Ren, Guanrong Chen

Citations: 2385 • 2012

A Comprehensive Survey of Multiagent Reinforcement Learning

Lucian Buşoniu, Robert Babuška, Bart De Schutter

Citations: 2178 • 2008

Distributed multi‐vehicle coordinated control<i>via</i>local information exchange

Wei Ren, Ella Atkins

Citations: 1478 • 2006

Cooperative Multi-Agent Learning: The State of the Art

Liviu Panait, Sean Luke

Citations: 1250 • 2005

Multiagent Systems: A Survey from a Machine Learning Perspective

Peter Stone, Manuela Veloso

Citations: 1188 • 2000

MASON: A Multiagent Simulation Environment

Sean Luke, Claudio Cioffi‐Revilla, Liviu Panait, Keith Sullivan, Gabriel Balan

Citations: 1007 • 2005

Multi-agent Reinforcement Learning: An Overview

Lucian Buşoniu, Robert Babuška, Bart De Schutter

Citations: 746 • 2010

Remote Agent: to boldly go where no AI system has gone before

Nicola Muscettola, P. Pandurang Nayak, Barney Pell, Brian C. Williams

Citations: 700 • 1998

Cooperative Control of Multi-Agent Systems: Optimal and Adaptive Design Approaches

Frank L. Lewis, Hongwei Zhang, Kristian Hengster‐Movric, Abhijit Das

Citations: 602 • 2013

Formation Control and Collision Avoidance for Multi-agent Non-holonomic Systems: Theory and Experiments

Silvia Mastellone, Dušan M. Stipanović, Christopher R. Graunke, Koji A. Intlekofer, Mark W. Spong

Citations: 450 • 2007

Cooperative Heterogeneous Multi-Robot Systems

Yara Rizk, Mariette Awad, Edward Tunstel

Citations: 416 • 2019

A taxonomy for multi-agent robotics

Gregory Dudek, Michael Jenkin, Evangelos Milios, D. Wilkes

Citations: 402 • 1996

A control Lyapunov function approach to multiagent coordination

Petter Ögren, Magnus Egerstedt, Xiaoming Hu

Citations: 388 • 2002

Secure Cooperative Event-Triggered Control of Linear Multiagent Systems Under DoS Attacks

Zhi Feng, Guoqiang Hu

Citations: 385 • 2019

Layered Learning in Multiagent Systems

Peter Stone

Citations: 381 • 2000

Cooperative Control of Distributed Multi‐Agent Systems

Citations: 362 • 2007

Cooperative Control of Multiple Nonholonomic Mobile Agents

Wenjie Dong, Jay A. Farrell

Citations: 345 • 2008

Situation awareness-based agent transparency and human-autonomy teaming effectiveness

Jessie Y. C. Chen, Shan Lakhmani, Kimberly Stowers, Anthony R. Selkowitz, Julia L. Wright, Michael Barnes

Citations: 327 • 2018

Introducing the tileworld: experimentally evaluating agent architectures

Martha E. Pollack, Marc Ringuette

Citations: 316 • 1990