Multi-Agent Patterns

A multi-agent system is two or more LLM agents that coordinate to do something neither would do alone. The patterns here describe the recurring shapes that coordination takes: a single supervisor routing work, an orchestrator parcelling tasks to workers, two agents debating to a better answer, a swarm voting on a shared output, a hierarchy of specialists handing off through a known protocol.

Multi-agent does not automatically mean better. Several patterns name the failure modes (infinite debate, hero agent, unbounded subagent spawn) so you can recognise them and walk away. The most field-tested multi-agent shapes — supervisor + orchestrator-workers, supervisor over isolated subagents — exist precisely because the failure modes are common.

Field-tested patterns to start with

• Supervisor — Place a coordinating agent above a set of specialised agents and route work to them.
• Orchestrator-Workers — An orchestrator dynamically breaks a task into subtasks at runtime and delegates each to a worker LLM, then synthesises results.
• Handoff — Transfer the active conversation from one agent to another, carrying context across the switch.
• Debate — Have multiple agents argue different positions on a question and converge through structured exchange.
• Hierarchical Agents — Organise agents in a tree where higher-level agents decompose tasks for lower-level agents, recursively.
• Swarm — Run many peer agents that interact directly without a central supervisor, achieving emergent coordination.
• Role Assignment — Assign each agent a named role (researcher, writer, critic, planner) with a role-specific prompt, tool palette, and acceptance criteria.
• Voting-Based Cooperation — Finalise a decision across multiple agents by collecting and tallying their votes on candidate options, so the joint output reflects collective rather than single-agent judgement.
• Inter-Agent Communication — Define a protocol for agents to exchange tasks, capabilities, and results across process or vendor boundaries.
• Conversational Multi-Agent — Have agents converse turn by turn until a completion criterion fires; agent roles drive the conversation forward.
• Subagent Isolation — Run subagents in isolated workspaces so their writes do not collide and parallelism is safe.
• Agent-as-Tool Embedding — Wrap a sub-agent (with its own loop, prompt, and tool palette) behind a single function-shaped tool signature, so the parent agent calls it like any other tool and never sees the sub-agent's internal…

Recommended reading

• Multi-Agent — 44 patterns
• Routing & Composition — 21 patterns

Or open the full contents for all 421 patterns in 14 books.

Related guides

• LLM Agent Design Patterns — A GoF-formal catalog of LLM agent design patterns: ReAct, tool use, plan-and-execute, reflection, step budget, and more. Each pattern decom…
• Agentic AI Architecture — How to structure agentic AI: the architectural patterns that hold an LLM-powered system together. Supervisor, orchestrator-workers, augment…
• RAG Agent Patterns — Patterns for building retrieval-augmented generation agents: naive RAG, agentic RAG, hybrid search, cross-encoder reranking, contextual ret…
• AI Agent Safety Patterns — Safety patterns for LLM agents: step budget, kill switch, constitutional charter, approval queue, sandbox isolation, input/output guardrail…