Everything about Multi-agent system
System of multiple interacting agents
A multi-agent system (MAS) or "self-organized system" is a computational system composed of multiple interacting intelligent agents. Multi-agent systems can solve problems that are difficult or impossible for an individual agent or a monolithic system to solve. Intelligence may include methodic, functional, procedural approaches, algorithmic search or reinforcement learning. With advancements in large language models (LLMs), LLM-based multi-agent systems have emerged as a new area of research, enabling more sophisticated interactions and coordination among agents. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Multi-agent systemA 5-minute orientation
- Skim a recent paper: A multi-agent system for automating scientific discoveryInfluential work since 2022
- Pick up a classic book: Swarm Intelligence Methods for Statistical RegressionThe most-reprinted book on the subject
- Read the landmark paper: Consensus and Cooperation in Networked Multi-Agent SystemsCited 9,217 times
- Go sideways: Distributed artificial intelligenceA closely related topic
- Go sideways: Agent-oriented programmingA closely related topic
📖 Definitions
Noun A computer program or system composed of multiple interacting intelligent agents, capable of solving highly complex problems which are difficult or impossible for an individual agent or monolithic system to solve.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
Consensus and Cooperation in Networked Multi-Agent Systems
Multi-site coordination using a multi-agent system
Agent learning in the multi-agent contracting system [MACS]
Smart Mobility Using Multi-Agent System
COMMAS (COndition Monitoring Multi-Agent System)
Multi-Agent Corporate Memory Management System
Multi-agent neural business control system
Multi-Agent System Testing: A Survey
🆕 Influential since 2022
📚 Books worth reading
- 📕Swarm Intelligence Methods for Statistical RegressionSoumya Mohanty · 2018
Integrated Fault Diagnosis and Control Design of Linear Complex SystemsMohammadreza Davoodi, Nader Meskin · 2018
Regulated agent-based social systemsDaniel Moldt, Mario Paolucci · 2004
Agent-oriented programmingMatthew M. Huntbach, Graem A. Ringwood · 1999
Intelligent agents and multi-agent systemsPacific Rim International Workshop on Multi-Agents (7th 2004 Auckland, N.Z.) · 2002
Multiagent system technologiesIngo J. Timm, Rainer Unland · 2004
Fleet CommandRavi Vale · 2026
The Deterministic SpineRavi Vale · 2026
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Distributed artificial intelligence Distributed Artificial Intelligence (DAI) (also called Decentralized Artificial Intelligence) is a melding of artificial intelligence with distributed…
- Agent-oriented programming Agent-oriented programming (AOP) is a programming paradigm where the construction of the software is centered on the concept of software agents. In contrast…
- Agent verification Agent verification is an activity to gain assurances that purposeful artificial constructs act in accordance with their specifications. While primitive…
- Juan Pavón Juan Pavón (born 19 November 1962) is a Spanish computer scientist, full professor of the Complutense University of Madrid (UCM). He is a pioneer researcher…
- Human-agent team A human-agent team is a system composed of multiple interacting humans and artificial intelligence systems. The artificial intelligence system may be a…
- Agent mining Agent mining is a research field that combines two areas of computer science: multiagent systems and data mining. It explores how intelligent computer…
- Aude Billard Aude G. Billard (born c. August 6, 1971) is a Swiss physicist in the fields of machine learning and human-robot interactions. As a full professor at the…
- Swarm intelligence Swarm intelligence (SI) is the collective behavior of decentralized, self-organized systems, natural or artificial. The concept is employed in work on…