<?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>LLM测试 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/llm%E6%B5%8B%E8%AF%95/</link><description>Recent content in LLM测试 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 11:20:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/llm%E6%B5%8B%E8%AF%95/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM回归测试策略：确保更新不引入退化</title><link>https://guijiagi.com/posts/llm-regression-testing/</link><pubDate>Thu, 02 Jul 2026 11:20:00 +0800</pubDate><guid>https://guijiagi.com/posts/llm-regression-testing/</guid><description>2026年LLM回归测试策略与实践，防止模型更新和提示修改导致性能退化</description></item><item><title>LLM自动化测试2026：让AI测试AI</title><link>https://guijiagi.com/posts/automated-testing-llm-2026/</link><pubDate>Thu, 02 Jul 2026 11:18:00 +0800</pubDate><guid>https://guijiagi.com/posts/automated-testing-llm-2026/</guid><description>2026年LLM自动化测试技术全面指南，覆盖测试生成、执行与结果分析</description></item></channel></rss>