ReAct：使用工具进行推理与行动
学习 ReAct 模式，了解模型如何交替执行推理步骤和工具操作，以解决仅凭记忆无法回答的任务。
ReAct：使用工具进行推理与行动 是 CoddyKit 上的免费 Prompt Engineering & LLM Optimization for Developers 课时。 这是第 4 节课，共 4 节。 你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。 这是 Prompt Engineering & LLM Optimization for Developers 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Prompt Engineering & LLM Optimization for Developers 课程共包含 4 节课。
本课时的部分内容尚未翻译，以英文显示。
When Thinking Is Not Enough
Chain-of-thought helps a model reason, but reasoning alone cannot fetch live data or run code. The ReAct pattern combines Reasoning with Acting so the model can use tools mid-task.
The ReAct Loop
ReAct alternates three roles in a loop:
- Thought: reason about what to do next.
- Action: call a tool with an input.
- Observation: read the tool's result.
Repeat until the answer is ready.
A ReAct Trace
A typical trace looks like this. The model emits a thought, an action, then waits for an observation injected back into the prompt.
Thought: I need today's weather in Paris.
Action: get_weather("Paris")
Observation: 18C, light rain
Thought: I can now answer.
Answer: It is 18C with light rain in Paris.Defining the Tools
You describe the available tools in the prompt: their names, what they do, and the input format. The model picks among them.
Tools:
- search(query): web search
- calc(expr): evaluate math
- get_weather(city): current weatherStopping at the Action
In practice your code stops generation when it sees an Action, executes the real tool, then appends the Observation and resumes the model. The model never invents tool results itself.
Why It Reduces Hallucination
Because the model grounds each step in real observations, ReAct cuts hallucination on factual or computational tasks. The reasoning explains why each tool was called, aiding debugging.
Multi-Step Problems
ReAct shines on tasks needing several lookups: find a company, then its founder, then that person's birth year. Each step's observation feeds the next thought.
Limiting the Loop
Always cap the number of iterations. Without a limit, a confused model can loop forever calling tools. Add a max-step budget and a fallback answer.
for step in range(MAX_STEPS):
out = model(prompt)
if is_answer(out): break
obs = run_tool(parse_action(out))
prompt += observation(obs)Handling Tool Errors
Tools fail: timeouts, bad inputs, empty results. Feed the error back as an observation so the model can retry differently rather than crashing the loop.
Observation: ERROR: city not found.
Thought: I should try the full country name.ReAct vs Plain Chain-of-Thought
- CoT: reasons internally, no external data.
- ReAct: reasons AND acts on the world via tools.
Use ReAct whenever the answer depends on information the model cannot already know.
Foundation for Agents
ReAct is the backbone of modern LLM agents. Frameworks like LangChain implement this thought-action-observation loop under the hood to build autonomous tool-using assistants.
Quick Check
Test your understanding of ReAct.
Recap
ReAct interleaves Thought, Action, and Observation so the model reasons and uses real tools. It grounds answers, reduces hallucination, needs a step limit and error handling, and underpins modern LLM agents.
用 AI 导师学习 Prompt Engineering & LLM Optimization for Developers — 免费
在浏览器中编写并运行真实代码，获得全天候 AI 导师的即时帮助，并在网页或应用中继续学习。
- 课程
- 12
- 课程
- 48
常见问题解答
「ReAct：使用工具进行推理与行动」课时是免费的吗？
是的 — 「ReAct：使用工具进行推理与行动」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Prompt Engineering & LLM Optimization for Developers 课程的其余内容，请升级到 CoddyKit PRO。 Prompt Engineering & LLM Optimization for Developers 课程共包含 4 节课。
「ReAct：使用工具进行推理与行动」这节课中我会学到什么？
学习 ReAct 模式，了解模型如何交替执行推理步骤和工具操作，以解决仅凭记忆无法回答的任务。 你通过在浏览器中直接运行的动手代码来练习 Prompt Engineering & LLM Optimization for Developers，全天候 AI 导师会在你学习这节课的过程中回答你的问题。
学习 Prompt Engineering & LLM Optimization for Developers 需要有经验吗？
无需任何先前经验。CoddyKit 上的 Prompt Engineering & LLM Optimization for Developers 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。 这是第 4 节课，共 4 节。
「ReAct：使用工具进行推理与行动」课时需要多长时间？
大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。
我能在这节 Prompt Engineering & LLM Optimization for Developers 课中编写并运行代码吗？
能。每节 Prompt Engineering & LLM Optimization for Developers 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。