<?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>推理模式 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%8E%A8%E7%90%86%E6%A8%A1%E5%BC%8F/</link><description>Recent content in 推理模式 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Tue, 23 Jun 2026 14:20:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%8E%A8%E7%90%86%E6%A8%A1%E5%BC%8F/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent 循环机制设计：从 ReAct 到 Plan-and-Execute 的演进</title><link>https://guijiagi.com/posts/agent-loop-design/</link><pubDate>Tue, 23 Jun 2026 14:20:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-loop-design/</guid><description>深入分析 Agent 循环设计模式，从经典 ReAct 到现代 Plan-and-Execute</description></item></channel></rss>