<?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>Agent评测 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/agent%E8%AF%84%E6%B5%8B/</link><description>Recent content in Agent评测 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 10:16:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/agent%E8%AF%84%E6%B5%8B/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Agent评测方法论：构建科学的智能体能力评估体系</title><link>https://guijiagi.com/posts/b2-d5b0a891/</link><pubDate>Thu, 16 Jul 2026 10:16:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-d5b0a891/</guid><description>系统构建AI Agent能力评估框架，涵盖任务完成率、工具使用效率、自主决策能力等核心评测维度</description></item><item><title>AI Agent 评测基准 2026：GAIA、SWE-bench、AgentBench 横评</title><link>https://guijiagi.com/posts/agent-evaluation-benchmarks-2026/</link><pubDate>Tue, 30 Jun 2026 16:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-evaluation-benchmarks-2026/</guid><description>2026年主流Agent评测基准深度解析：GAIA、SWE-bench、AgentBench、WebArena等评测体系的能力维度与局限性</description></item></channel></rss>