<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>Agent Framework - 标签 - lilfry's library</title><link>https://lilfry09.github.io/tags/agent-framework/</link><description>Agent Framework - 标签 - lilfry's library</description><generator>Hugo -- gohugo.io</generator><language>zh-CN</language><managingEditor>lilfry@sjtu.edu.cn (lilfry)</managingEditor><webMaster>lilfry@sjtu.edu.cn (lilfry)</webMaster><copyright>All rights reserved.</copyright><lastBuildDate>Tue, 05 May 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://lilfry09.github.io/tags/agent-framework/" rel="self" type="application/rss+xml"/><item><title>模型更强之后，Agent 框架会怎样退到 runtime</title><link>https://lilfry09.github.io/ai/stronger-agent-models-thinner-frameworks/</link><pubDate>Tue, 05 May 2026 00:00:00 +0800</pubDate><author>fry</author><guid>https://lilfry09.github.io/ai/stronger-agent-models-thinner-frameworks/</guid><description>当模型通过轨迹训练学会规划、工具使用、错误恢复和上下文选择后，Agent 框架最该简化的不是安全和评估，而是替模型思考的调度层。</description></item></channel></rss>