---
title: "What is a multi-agent system in AI?"
description: "A multi-agent system splits one task across several AI agents that coordinate through an orchestrator or a protocol. Learn how it works and when it pays off."
type: "glossary-term"
canonical_url: "https://theaiengineering.com/glossary/multi-agent-system"
markdown_url: "https://theaiengineering.com/glossary/multi-agent-system.md"
topic: "AI agents"
author: "The AI Engineering Editors"
publisher: "The AI Engineering"
updated: "2026-11-06"
keywords: ["Multi-agent system","MAS","multi-agent architecture"]
citation: "The AI Engineering Editors. \"What is a multi-agent system in AI?\" The AI Engineering, updated Nov 06, 2026. https://theaiengineering.com/glossary/multi-agent-system"
---

# What is a multi-agent system in AI?

Also called MAS, multi-agent architecture.

> **Definition of Multi-agent system:** A multi-agent system is an AI architecture in which several language-model agents, each with its own prompt, tools, and context, work on parts of a task and pass results to one another.

A multi-agent system is an AI architecture in which several [AI agents](https://theaiengineering.com/glossary/ai-agent) work on parts of one task and exchange results. Each agent has its own instructions, tools, and [context window](https://theaiengineering.com/glossary/context-window). The agents coordinate through an orchestrator agent, a shared state store, or a protocol such as [A2A](https://theaiengineering.com/glossary/a2a-protocol). The term is older than language models and also names a field of distributed AI research; in LLM engineering it usually means a group of LLM-driven agents.

## How a multi-agent system works

A multi-agent system usually works through an [orchestrator-worker pattern](https://theaiengineering.com/glossary/agent-orchestration): a lead agent splits the task, starts [subagents](https://theaiengineering.com/glossary/subagent) with narrower instructions, and merges what they return. Each subagent runs its own loop in a separate context, so it can explore one branch of the problem without filling the lead agent's context with intermediate results.

**Figure 1: The orchestrator-worker pattern in a multi-agent system.**

A lead agent splits a task across three subagents, each working in its own context, and their condensed findings return to the lead to be merged.

Components:

- **Lead agent**: Plans and splits the task
- **Subagent A**: Own context
- **Subagent B**: Own context
- **Subagent C**: Own context
- **Lead merges condensed findings**

Connections:

- Lead agent → Subagent A
- Lead agent → Subagent B
- Lead agent → Subagent C
- Subagent A → Lead merges condensed findings
- Subagent B → Lead merges condensed findings
- Subagent C → Lead merges condensed findings

Anthropic described this design for its [multi-agent research system](https://www.anthropic.com/engineering/multi-agent-research-system): a lead agent plans the research and spawns subagents that search in parallel, then a separate agent attributes claims to sources. Other topologies include fixed pipelines, where each agent hands off to the next, and peer networks, where agents discover each other through a protocol.

## Multi-agent system vs single agent

A multi-agent system outperforms a single agent on tasks that split into independent parallel parts, and it underperforms on tasks with tight dependencies between steps. On Anthropic's internal research evaluation, a multi-agent setup with Claude Opus 4 as lead and Claude Sonnet 4 subagents outperformed a single-agent Claude Opus 4 by 90.2%.

The same report lists the costs. Multi-agent systems used about 15 times the tokens of a chat interaction, and Anthropic called most coding tasks a poor fit because they offer few parallelizable subtasks. A practical rule: start with one agent, and add agents only when a measured bottleneck, such as context size, parallel search, or separation of permissions, justifies the extra cost and debugging surface.

See [what AI agents are](https://theaiengineering.com/articles/what-are-ai-agents), the [AI agent frameworks](https://theaiengineering.com/articles/ai-agent-frameworks) that support multi-agent orchestration, and [A2A vs MCP](https://theaiengineering.com/articles/a2a-vs-mcp) for the protocols agents use to communicate.

## Related terms

- [AI agent](https://theaiengineering.com/glossary/ai-agent): An AI agent is a software system in which a large language model runs in a loop, calling tools, reading their results, and repeating until the task is complete or a stop condition is reached.
- [Agentic AI](https://theaiengineering.com/glossary/agentic-ai): Agentic AI is the class of AI systems that pursue a goal through multiple steps, using a language model to plan, call tools, and act on the results with limited human input.
- [A2A protocol](https://theaiengineering.com/glossary/a2a-protocol): The A2A (Agent2Agent) protocol is an open standard, introduced by Google in April 2025, that lets AI agents built on different frameworks discover each other, exchange messages, and delegate tasks.
- [Context window](https://theaiengineering.com/glossary/context-window): A context window is the maximum number of tokens a language model can take into account in a single request, including the system prompt, conversation history, tool results, and the generated output.
- [Agent memory](https://theaiengineering.com/glossary/agent-memory): Agent memory is the set of mechanisms that let an AI agent keep and retrieve information beyond a single model call, from the current context window to external stores that persist across sessions.
- [Subagent](https://theaiengineering.com/glossary/subagent): A subagent is an AI agent that another agent starts for one subtask, running in a separate context window with its own instructions and tools, and returning only a condensed result.
- [Agent handoff](https://theaiengineering.com/glossary/agent-handoff): An agent handoff is a transfer of control in which one AI agent passes the conversation, and responsibility for the task, to another agent better suited to the next part of the work.
- [Agent orchestration](https://theaiengineering.com/glossary/agent-orchestration): Agent orchestration is the control logic that decides which agent, model call, or tool runs next in an AI system and what each receives, whether written in code or chosen by a model.

## Guides that cover multi-agent system

- [What are AI agents? How agents work and when to use one](https://theaiengineering.com/articles/what-are-ai-agents): AI agents are LLM systems that call tools in a loop until a task is done. Learn how the loop works, agents vs agentic AI, examples, failure modes, and limits.
- [AI agent frameworks compared: LangGraph, CrewAI, ADK, and more](https://theaiengineering.com/articles/ai-agent-frameworks): An AI agent frameworks comparison of LangGraph, LangChain, CrewAI, the OpenAI, Claude, and Google SDKs, Pydantic AI, Mastra, and more, by language and license.
- [A2A protocol vs MCP: differences and when to use each](https://theaiengineering.com/articles/a2a-vs-mcp): A2A protocol vs MCP: A2A connects AI agents to other agents, and MCP connects an agent to tools and data. Compare agent cards, tasks, transports, and security.
- [Agentic workflows: five patterns and when to use each](https://theaiengineering.com/articles/agentic-workflows): Agentic workflows run LLM and tool calls through steps fixed in code. Learn five patterns, their cost and latency, failure modes, and when to use an agent.
- [How to build an AI agent: a step-by-step guide in Python](https://theaiengineering.com/articles/how-to-build-an-ai-agent): Learn how to build an AI agent from scratch in Python: when you need one, tool schemas, the agent loop, stop conditions, guardrails, evals, and tracing.

Part of the [AI agents](https://theaiengineering.com/topics/ai-agents) topic hub.

## Cite this definition

The AI Engineering Editors. "What is a multi-agent system in AI?" The AI Engineering, updated Nov 06, 2026. https://theaiengineering.com/glossary/multi-agent-system

- Title: What is a multi-agent system in AI?
- Author: The AI Engineering Editors
- Publisher: The AI Engineering
- Updated: 2026-11-06
- URL: https://theaiengineering.com/glossary/multi-agent-system
- Markdown: https://theaiengineering.com/glossary/multi-agent-system.md
