AI代理设计模式

AI代理是一个包裹在决策循环中的LLM：观察、推理、行动、重复。AI代理设计模式命名了该循环的各个部分及其周围的重复形状 — 如何在不产生失控成本的情况下进行推理（ReAct、计划与执行、反思），如何在不失去责任的情况下对世界采取行动（工具使用、代理RAG、交接），以及如何保持循环足够安全以便发布（步骤预算、紧急停止开关、人工干预）。

这些模式不是框架特性。它们是关于行为的承诺，可以在特定基础上进行辩护 — 也可以在特定基础上拒绝。该目录以Christopher Alexander（1977年）和Gang of Four（1994年）的方式分解每个模式，并添加了LLM时代的约束槽（代理绝不能违反的严格禁止），以便每个模式在可以进行论证的生成器下保持其形状。

下面的选择是一个实用的入门集，适用于“我如何构建一个AI代理？”。打开相关指南以获取相邻的框架：更广泛的代理设计模式语言、代理AI架构、多代理协调、RAG和安全堆栈。

Field-tested patterns to start with

• ReAct — Interleave a single thought, a single tool call, and a single observation per step so the agent reasons over fresh evidence.
• Tool Use — Let the LLM produce typed calls against an external toolkit instead of producing free-form text the surrounding system has to parse.
• Plan-and-Execute — Plan all the steps once with a strong model, then execute each step with a cheaper model under the plan.
• Reflection — Have the model review its own output and produce a revised version in one or more passes.
• Augmented LLM — Build the foundational agent block as an LLM augmented with retrieval, tools, and memory that the model actively chooses to use, rather than a bare-model call.
• Agentic RAG — Replace static retrieve-then-generate with autonomous agents that plan, choose sources, retrieve iteratively, reflect, and re-query.
• Supervisor — Place a coordinating agent above a set of specialised agents and route work to them.
• Handoff — Transfer the active conversation from one agent to another, carrying context across the switch.
• Step Budget — Cap the number of tool calls or loop iterations the agent is allowed within a single request.
• Kill Switch — Provide an out-of-band control plane to halt running agent instances without redeploy.
• Human-in-the-Loop — Require explicit human approval at defined points before the agent performs an action.
• Decision Log — Persist the agent's reasoning trace alongside its actions so post-hoc review can explain why.

Recommended reading

• Reasoning — 20 patterns
• Planning & Control Flow — 45 patterns
• Tool Use & Environment — 51 patterns
• Retrieval & RAG — 23 patterns
• Safety & Control — 72 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,…
• 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…
• Multi-Agent Patterns — Patterns for coordinating multiple LLM agents: supervisor, orchestrator-workers, handoff, debate, hierarchical agents, swarm, role assignme…
• AI Agent Safety Patterns — Safety patterns for LLM agents: step budget, kill switch, constitutional charter, approval queue, sandbox isolation, input/output guardrail…