代理模式

本网站的其他指南专注于单一角度（代理循环、多代理协调、RAG、安全），而“代理模式”是整个词汇的总称。当一个模式假设系统本身决定下一步做什么时，它就是代理的；该目录收集了每一个这样的决策形状，并将其整理成一种语言。

该语言按照亚历山大风格的书籍组织 — 每个关注点一本：推理、规划和控制流、工具使用和环境、检索、验证和反思、多代理协调、路由和组合、安全和控制、治理和可观察性。以下选择是每本书中的一个经典模式，因此本页作为语言的地图，而不是代理循环原语的重新列出。打开专门的指南以获取更深入的信息。

每个模式都是GoF分解的：意图、上下文、问题、力量、因此、解决方案、后果（好处 + 负担）、约束（严格禁止）、相关[]。约束槽是代理时代的补充；它是保持模式命名的原因，即使在存在可以绕过任何经验法则的生成器的情况下。

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.
• Plan-and-Execute — Plan all the steps once with a strong model, then execute each step with a cheaper model under the plan.
• Tool Use — Let the LLM produce typed calls against an external toolkit instead of producing free-form text the surrounding system has to parse.
• Agentic RAG — Replace static retrieve-then-generate with autonomous agents that plan, choose sources, retrieve iteratively, reflect, and re-query.
• Agent-as-a-Judge — Evaluate an agent's full trajectory (steps, tool calls, intermediate states) by another agent rather than scoring only the final output.
• 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.
• 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
• Verification & Reflection — 32 patterns
• Multi-Agent — 50 patterns
• Routing & Composition — 26 patterns
• Safety & Control — 72 patterns
• Governance & Observability — 47 patterns

Or open the full contents for all 565 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 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…