<?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>技能优化 on MessageDaily</title><link>https://inkeast.github.io/MessageDaily/tags/%E6%8A%80%E8%83%BD%E4%BC%98%E5%8C%96/</link><description>Recent content in 技能优化 on MessageDaily</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Sat, 19 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://inkeast.github.io/MessageDaily/tags/%E6%8A%80%E8%83%BD%E4%BC%98%E5%8C%96/index.xml" rel="self" type="application/rss+xml"/><item><title>SKILLAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback 精读</title><link>https://inkeast.github.io/MessageDaily/posts/2026-09-19-skillaa-paper-reading/</link><pubDate>Sat, 19 Sep 2026 00:00:00 +0000</pubDate><guid>https://inkeast.github.io/MessageDaily/posts/2026-09-19-skillaa-paper-reading/</guid><description>南京大学发表于 ICLR 2027 的 SKILLAA 把&amp;rsquo;冻结模型上的技能库优化&amp;rsquo;从平面文本编辑升级为图结构手术：技能的适用性、执行与组建统一表达为图，失败经溯因归因路由到图中唯一可编辑表面（缺技能族→加节点、缺激活线索→只改 when_to_use、规则有害→只换局部语义），Local Gate 验证原子编辑组、Big Gate 决定周期级提交，不合格即回滚。gpt-5.6-sol 后端下 SearchQA 81.5%、LiveMath 66.7%、DocVQA 91.2%，全部主设置取得最高观测均值。对研究 Agent Skill 优化的读者，这是 SkillOpt 之后必须读的下一站。</description></item></channel></rss>