Multi-Agent Systems
A multi-agent system is made up of several autonomous agents that interact in a common environment to solve problems beyond a single agent. We first define what an agent is, review the system's properties (autonomy, decentralization, interaction), coordination among agents, and its uses, including systems based on large language models.
A multi-agent system brings together several autonomous agents that interact in a shared environment and may cooperate, coordinate or compete. It helps to start with what an agent is: an entity—a program, a robot—situated in an environment, able to perceive it and act on it autonomously to achieve its goals.
What characterizes them
Their defining features are each agent's autonomy, local view—none has global knowledge of the problem—interaction among agents, whether communicating directly or acting on the shared environment. Moreover, each agent may have its own goals, which sometimes conflict.
Coordination, cooperation and competition
That is why multi-agent systems revolve around coordination: mechanisms that make one agent's actions fit with others'. Agents may cooperate toward a common goal or compete in defence of their own interests. When they communicate, the FIPA standards catalogue provides interaction protocols for requests, queries, proposals and contract nets. Those protocols structure message exchanges; they do not determine each agent's strategy by themselves.
Where they are used
A 2025 survey reviews multi-agent coordination in search and rescue, warehouse automation and logistics, transportation, humanoid robots and satellite systems. It also includes systems built around large language models: since 2023, surveys have examined language agents that divide roles and collaborate on complex tasks, alongside open problems in coordination and reliability.
Pieces using this term
This article was produced with artificial intelligence under human editorial oversight.
