<?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>RLHF替代 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/rlhf%E6%9B%BF%E4%BB%A3/</link><description>Recent content in RLHF替代 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>Thu, 02 Jul 2026 10:43:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/rlhf%E6%9B%BF%E4%BB%A3/index.xml" rel="self" type="application/rss+xml"/><item><title>DPO训练实践指南：直接偏好优化的工程落地</title><link>https://guijiagi.com/posts/dpo-training-practice/</link><pubDate>Thu, 02 Jul 2026 10:43:00 +0800</pubDate><guid>https://guijiagi.com/posts/dpo-training-practice/</guid><description>系统介绍DPO（Direct Preference Optimization）的训练原理、数据准备与工程实践</description></item></channel></rss>