<?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>基准 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%9F%BA%E5%87%86/</link><description>Recent content in 基准 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>Sun, 28 Jun 2026 11:25:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%9F%BA%E5%87%86/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent 性能基准测试方法论 2026</title><link>https://guijiagi.com/posts/agent-performance-benchmark-methodology-2026/</link><pubDate>Sun, 28 Jun 2026 11:25:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-performance-benchmark-methodology-2026/</guid><description>构建Agent性能基准测试体系，涵盖延迟、吞吐量、成本、质量四维评估方法论</description></item><item><title>vLLM vs SGLang性能基准</title><link>https://guijiagi.com/posts/vllm-vs-sglang-benchmark/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/vllm-vs-sglang-benchmark/</guid><description>vLLM vs SGLang性能基准</description></item><item><title>Agent 基准测试套件：SWE-bench vs WebArena vs GAIA</title><link>https://guijiagi.com/posts/agent-benchmark-suite/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-benchmark-suite/</guid><description>深入对比三大 Agent 基准测试套件：SWE-bench、WebArena 和 GAIA，覆盖设计理念、任务类型、评估方法与适用场景。</description></item><item><title>Agent 评估框架：从任务完成率到自主性评级</title><link>https://guijiagi.com/posts/agent-evaluation-framework/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-evaluation-framework/</guid><description>系统梳理 AI Agent 评估方法论，涵盖基准测试、评估维度、自动化评测工具和生产监控。</description></item></channel></rss>