A multi-agent system splits a job across several specialised AI agents that coordinate through a shared plan, message bus or orchestrator.
2 min readupdated 2026-08-01
/ quick answer
A multi-agent system (MAS) is an architecture where multiple LLM agents, each with a narrow role and tool set, work on one goal. Coordination usually follows one of three shapes: supervisor (one orchestrator delegates), pipeline (agents run in sequence), or swarm (agents hand off peer-to-peer). MAS buys specialisation and parallelism at the cost of latency, token spend and debuggability.
A multi-agent system splits a job across several specialised AI agents that coordinate through a shared plan, message bus or orchestrator. A multi-agent system (MAS) is an architecture where multiple LLM agents, each with a narrow role and tool set, work on one goal. Coordination usually follows one of three shapes: supervisor (one orchestrator delegates), pipeline (agents run in sequence), or swarm (agents hand off peer-to-peer). MAS buys specialisation and parallelism at the cost of latency, token spend and debuggability. In practice: A content system with a Researcher agent, a Writer agent and an Editor agent supervised by an orchestrator that reruns the Writer whenever the Editor rejects the draft. This dictionary node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Definition
A multi-agent system (MAS) is an architecture where multiple LLM agents, each with a narrow role and tool set, work on one goal. Coordination usually follows one of three shapes: supervisor (one orchestrator delegates), pipeline (agents run in sequence), or swarm (agents hand off peer-to-peer). MAS buys specialisation and parallelism at the cost of latency, token spend and debuggability.
Example
A content system with a Researcher agent, a Writer agent and an Editor agent supervised by an orchestrator that reruns the Writer whenever the Editor rejects the draft.
A multi-agent system (MAS) is an architecture where multiple LLM agents, each with a narrow role and tool set, work on one goal. Coordination usually follows one of three shapes: supervisor (one orchestrator delegates), pipeline (agents run in sequence), or swarm (agents hand off peer-to-peer). MAS buys specialisation and parallelism at the cost of latency, token spend and debuggability.
What is an example of Multi-Agent System?
A content system with a Researcher agent, a Writer agent and an Editor agent supervised by an orchestrator that reruns the Writer whenever the Editor rejects the draft.
Why does Multi-Agent System matter for AI and automation?
A multi-agent system splits a job across several specialised AI agents that coordinate through a shared plan, message bus or orchestrator. It connects to the workflows, prompts and tool stacks linked on this page, so you can move from definition to execution without leaving Onexial.