多智能体模式

多智能体系统是两个或更多 LLM 智能体协调以完成单独无法完成的任务。这里的模式描述了协调所采取的重复形态：一个单一的监督者路由工作，一个协调者将任务分配给工作者，两个智能体辩论以得出更好的答案，一个群体对共享输出进行投票，一个专家层次通过已知协议进行交接。

多智能体并不自动意味着更好。几个模式命名了失败模式（无限辩论、英雄智能体、无限子智能体生成），以便你能够识别它们并选择放弃。经过实地测试的多智能体形态 — 监督者 + 协调者-工作者，监督者控制孤立的子智能体 — 正是因为这些失败模式很常见而存在。

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 — 50 patterns
• Routing & Composition — 24 patterns

Or open the full contents for all 562 patterns in 14 books.

Related guides

• AI Agents Patterns — AI agents patterns: named, reusable shapes for building AI agents that reason, use tools, coordinate, and stay safe — single-agent loops an…
• AI Agents Patterns Catalog — The AI agents patterns catalog: a complete, GoF-formal pattern language for AI agents across reasoning, planning, tool use, retrieval, memo…
• 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 Design Patterns — A GoF-formal catalog of agentic design patterns — named, reusable shapes for building autonomous AI agents: agent loops, tool use, planning…
• Agentic AI Design Patterns — Agentic AI design patterns for systems already in production — what to ship, what to observe, what to budget, what to gate. Augmented LLM,…
• AI Agent Design Patterns — How to build an AI agent: the named shapes you reach for during design and implementation — reasoning (ReAct, plan-and-execute, reflection)…
• Agent Design Patterns — Agent design patterns treat the agent loop as a software-engineering primitive: an observe→reason→act cycle wrapped in tools, memory, super…
• Agentic Patterns — A complete pattern language for agentic systems, organised in Alexander-style books across reasoning, planning, tool use, retrieval, verifi…
• 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…