<?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>自动化测试 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E8%87%AA%E5%8A%A8%E5%8C%96%E6%B5%8B%E8%AF%95/</link><description>Recent content in 自动化测试 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, 16 Jul 2026 10:33:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E8%87%AA%E5%8A%A8%E5%8C%96%E6%B5%8B%E8%AF%95/index.xml" rel="self" type="application/rss+xml"/><item><title>AI驱动的自动化测试：从用例生成到缺陷预测</title><link>https://guijiagi.com/posts/b2-2c647ec1/</link><pubDate>Thu, 16 Jul 2026 10:33:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-2c647ec1/</guid><description>探讨AI在软件测试全流程中的应用，涵盖测试用例生成、智能回归、视觉测试与缺陷预测技术</description></item><item><title>从零开始构建AI Agent评估管线</title><link>https://guijiagi.com/posts/article-74/</link><pubDate>Mon, 13 Jul 2026 05:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/article-74/</guid><description>系统性介绍AI Agent评估管线的构建方法，从指标设计到数据集构建到自动化评估全流程实操指南</description></item><item><title>AI生成代码的质量评估方法</title><link>https://guijiagi.com/posts/article-34/</link><pubDate>Sun, 12 Jul 2026 22:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/article-34/</guid><description>从功能正确性到代码可维护性，构建AI生成代码的多维评估体系</description></item><item><title>AI生成代码的质量评估方法</title><link>https://guijiagi.com/posts/b2-88900a97/</link><pubDate>Sun, 12 Jul 2026 22:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-88900a97/</guid><description>从功能正确性到代码可维护性，构建AI生成代码的多维评估体系</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><item><title>RAG评估框架：RAGAS指标体系与自定义评估</title><link>https://guijiagi.com/posts/rag-evaluation-framework-ragas/</link><pubDate>Tue, 30 Jun 2026 09:40:00 +0800</pubDate><guid>https://guijiagi.com/posts/rag-evaluation-framework-ragas/</guid><description>系统介绍RAGAS评估框架的核心指标体系、自动化评估流程，以及如何构建自定义评估pipeline</description></item><item><title>Agent 评估自动化：CI/CD 中的 LLM 测试</title><link>https://guijiagi.com/posts/agent-evaluation-cicd-2026/</link><pubDate>Sun, 28 Jun 2026 10:15:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-evaluation-cicd-2026/</guid><description>构建Agent CI/CD测试体系：从单元测试到端到端评估，实现LLM应用的自动化质量保障</description></item></channel></rss>