LLM评估 on GopherDing's Blog/categories/llm%E8%AF%84%E4%BC%B0/Recent content in LLM评估 on GopherDing's BlogHugo -- gohugo.iozhGopherDingGopherDingWed, 14 Oct 2026 17:47:50 +0800Agent 评测体系搭建：从离线门禁到 LLM-as-a-Judge/posts/tech/agent-%E8%AF%84%E6%B5%8B%E4%BD%93%E7%B3%BB%E6%90%AD%E5%BB%BA%E4%BB%8E%E7%A6%BB%E7%BA%BF%E9%97%A8%E7%A6%81%E5%88%B0-llm-as-a-judge/Wed, 14 Oct 2026 17:47:50 +0800GopherDing/posts/tech/agent-%E8%AF%84%E6%B5%8B%E4%BD%93%E7%B3%BB%E6%90%AD%E5%BB%BA%E4%BB%8E%E7%A6%BB%E7%BA%BF%E9%97%A8%E7%A6%81%E5%88%B0-llm-as-a-judge/用商家经营分析 Agent 串起评测体系搭建：离线门禁、在线监控、Case 四层归因与 LLM-as-a-Judge 日级落地，区别于评估指标入门。速通 AI（九）：RAG 与 Agent 评估体系/posts/tech/%E9%80%9F%E9%80%9A-ai%E4%B9%9Drag-%E4%B8%8E-agent-%E8%AF%84%E4%BC%B0%E4%BD%93%E7%B3%BB/Mon, 20 Jul 2026 15:55:23 +0800GopherDing/posts/tech/%E9%80%9F%E9%80%9A-ai%E4%B9%9Drag-%E4%B8%8E-agent-%E8%AF%84%E4%BC%B0%E4%BD%93%E7%B3%BB/「速通 AI」系列第九篇：RAGAS 框架、Agent 评估五维度、幻觉检测、LLM-as-Judge。