<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Chain-of-Thought on Yuxia&#39;s Blog</title>
    <link>https://luoyuxia.github.io/tags/chain-of-thought/</link>
    <description>Recent content in Chain-of-Thought on Yuxia&#39;s Blog</description>
    <generator>Hugo</generator>
    <language>zh</language>
    <lastBuildDate>Sat, 23 May 2026 14:00:00 +0800</lastBuildDate>
    <atom:link href="https://luoyuxia.github.io/tags/chain-of-thought/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>从 ChatGPT 到 Agent：模型为什么开始会做事</title>
      <link>https://luoyuxia.github.io/posts/%E4%BB%8E-chatgpt-%E5%88%B0-agent%E6%A8%A1%E5%9E%8B%E4%B8%BA%E4%BB%80%E4%B9%88%E5%BC%80%E5%A7%8B%E4%BC%9A%E5%81%9A%E4%BA%8B/</link>
      <pubDate>Sat, 23 May 2026 14:00:00 +0800</pubDate>
      <guid>https://luoyuxia.github.io/posts/%E4%BB%8E-chatgpt-%E5%88%B0-agent%E6%A8%A1%E5%9E%8B%E4%B8%BA%E4%BB%80%E4%B9%88%E5%BC%80%E5%A7%8B%E4%BC%9A%E5%81%9A%E4%BA%8B/</guid>
      <description>从 ChatGPT 到 Agent，模型的评价标准从&amp;rsquo;回答得像不像&amp;rsquo;变成了&amp;rsquo;任务到底有没有完成&amp;rsquo;。本文梳理了这段演进中的五篇关键论文——Chain-of-Thought、ReAct、Toolformer、Reflexion、Self-Refine，拆解模型如何从会回答的问题机器，变成了会推进任务的执行系统。</description>
    </item>
  </channel>
</rss>
