smolagents/pr_2321/zh/conceptual_guides/react.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;多步骤 agent 是如何工作的？&quot;,&quot;local&quot;:&quot;多步骤-agent-是如何工作的&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/smolagents/pr_2321/zh/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/entry/start.cd933138.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/chunks/scheduler.00b97157.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/chunks/singletons.90f7340d.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/chunks/index.78ea7f15.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/chunks/paths.9ab9ad33.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/entry/app.6e30bf5c.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/chunks/preload-helper.2f70801c.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/chunks/index.a7c1a7a1.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/nodes/0.5a52bc41.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/nodes/3.b47955ec.js">
		<link rel="modulepreload" href="/docs/smolagents/pr_2321/zh/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.3f55db13.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;多步骤 agent 是如何工作的？&quot;,&quot;local&quot;:&quot;多步骤-agent-是如何工作的&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div>  <h1 class="relative group"><a id="多步骤-agent-是如何工作的" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#多步骤-agent-是如何工作的"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>多步骤 agent 是如何工作的？</span></h1> <p data-svelte-h="svelte-gm4bn2">ReAct 框架（<a href="https://huggingface.co/papers/2210.03629" rel="nofollow">Yao et al., 2022</a>）是目前构建 agent 的主要方法。</p> <p data-svelte-h="svelte-ktrkfc">该名称基于两个词的组合：“Reason” （推理）和 “Act” （行动）。实际上，遵循此架构的 agent 将根据需要尽可能多的步骤来解决其任务，每个步骤包括一个推理步骤，然后是一个行动步骤，在该步骤中，它制定工具调用，使其更接近解决手头的任务。</p> <p data-svelte-h="svelte-lhy2wj">ReAct 过程涉及保留过去步骤的记忆。</p> <blockquote class="tip" data-svelte-h="svelte-1syzs5b"><p>阅读 <a href="https://huggingface.co/blog/open-source-llms-as-agents" rel="nofollow">Open-source LLMs as LangChain Agents</a> 博客文章以了解更多关于多步 agent 的信息。</p></blockquote> <p data-svelte-h="svelte-1ghba8i">以下是其工作原理的视频概述：</p> <div class="flex justify-center" data-svelte-h="svelte-4ra9xq"><img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/Agent_ManimCE.gif"> <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/Agent_ManimCE.gif"></div> <p data-svelte-h="svelte-1qm66iv"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/open-source-llms-as-agents/ReAct.png" alt="ReAct agent 的框架"></p> <p data-svelte-h="svelte-1j4ubj4">我们实现了两个版本的 ToolCallingAgent：</p> <ul data-svelte-h="svelte-1qm16ow"><li><a href="/docs/smolagents/pr_2321/zh/reference/agents#smolagents.ToolCallingAgent">ToolCallingAgent</a> 在其输出中生成 JSON 格式的工具调用。</li> <li><a href="/docs/smolagents/pr_2321/zh/reference/agents#smolagents.CodeAgent">CodeAgent</a> 是一种新型的 ToolCallingAgent，它生成代码块形式的工具调用，这对于具有强大编码性能的 LLM 非常有效。</li></ul> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/smolagents/blob/main/docs/source/zh/conceptual_guides/react.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_3wial0 = {
						assets: "/docs/smolagents/pr_2321/zh",
						base: "/docs/smolagents/pr_2321/zh",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/smolagents/pr_2321/zh/_app/immutable/entry/start.cd933138.js"),
						import("/docs/smolagents/pr_2321/zh/_app/immutable/entry/app.6e30bf5c.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 3],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>