<?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>人类偏好 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E4%BA%BA%E7%B1%BB%E5%81%8F%E5%A5%BD/</link><description>Recent content in 人类偏好 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, 16 Jul 2026 10:45:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E4%BA%BA%E7%B1%BB%E5%81%8F%E5%A5%BD/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型评估方法论：从基准测试到人类偏好的全面评估体系</title><link>https://guijiagi.com/posts/b2-743cce1d/</link><pubDate>Thu, 16 Jul 2026 10:45:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-743cce1d/</guid><description>系统构建大模型评估框架，涵盖知识能力、推理能力、安全性、对齐度等多维度评估方法</description></item></channel></rss>