<?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>质量控制 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E8%B4%A8%E9%87%8F%E6%8E%A7%E5%88%B6/</link><description>Recent content in 质量控制 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 11:17:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E8%B4%A8%E9%87%8F%E6%8E%A7%E5%88%B6/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM人工评估指南：让人类来判断AI的好坏</title><link>https://guijiagi.com/posts/human-evaluation-llm-guide/</link><pubDate>Thu, 02 Jul 2026 11:17:00 +0800</pubDate><guid>https://guijiagi.com/posts/human-evaluation-llm-guide/</guid><description>2026年LLM人工评估方法论，涵盖评估者选择、标注规范与质量控制</description></item><item><title>Agent监督者架构：多智能体系统的质量控制层</title><link>https://guijiagi.com/posts/agent-supervisor-architecture/</link><pubDate>Thu, 02 Jul 2026 10:09:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-supervisor-architecture/</guid><description>深入探讨Agent监督者架构的设计原理、监督策略与质量控制机制</description></item></channel></rss>