<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Self-Improvement on Yigeng’s Blog</title>
    <link>https://yigengjiang.github.io/tags/self-improvement/</link>
    <description>Recent content in Self-Improvement on Yigeng’s Blog</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <copyright>This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.</copyright>
    <lastBuildDate>Sun, 12 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://yigengjiang.github.io/tags/self-improvement/" rel="self" type="application/rss+xml" />
    
    
    <item>
      <title>Self-Improving Agent Systems: A Unified View of Algorithms, Skills, and Harnesses</title>
      <link>https://yigengjiang.github.io/posts/self_improving_agent_systems/</link>
      <pubDate>Sun, 12 Jul 2026 00:00:00 +0000</pubDate>
      <author>yigeng &amp; GPT 5.6</author>
      <guid>https://yigengjiang.github.io/posts/self_improving_agent_systems/</guid>
      <description>
        <![CDATA[
        <p>Self-improvement is often discussed as if it meant a model rewriting its own weights. That is one[&hellip;] <a href="https://yigengjiang.github.io/posts/self_improving_agent_systems/">https://yigengjiang.github.io/posts/self_improving_agent_systems/</a></p>
        
        ]]>
      </description>
    </item>
    
    
  </channel>
</rss>