<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Cognitive Science on 卓琪的开发笔记</title>
    <link>https://zhuoqidev.com/tags/cognitive-science/</link>
    <description>Recent content in Cognitive Science on 卓琪的开发笔记</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <copyright>© 2026 Liu ZhuoQi</copyright>
    <lastBuildDate>Thu, 30 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://zhuoqidev.com/tags/cognitive-science/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>How Agents Remember You: Human Memory Science and a Code Audit of Six Open-Source Systems</title>
      <link>https://zhuoqidev.com/en/posts/llm-memory-research/</link>
      <pubDate>Thu, 30 Jul 2026 00:00:00 +0000</pubDate>
      
      <guid>https://zhuoqidev.com/en/posts/llm-memory-research/</guid>
      <description>&lt;p&gt;Almost every agent project now claims to provide “long-term memory.”&lt;/p&gt;&#xA;&lt;p&gt;For one project, that means embedding chat history. For another, it means maintaining a user profile. A third lets the model edit Markdown files. A fourth builds a bitemporal knowledge graph. All four use the word &lt;em&gt;memory&lt;/em&gt;, but they are not the same system and should not be placed on one undifferentiated leaderboard.&lt;/p&gt;&#xA;&#xA;&lt;figure&gt;&#xA;      &lt;img class=&#34;my-0 rounded-md&#34; src=&#34;https://zhuoqidev.com/images/posts/llm-memory-research/agent-memory-cover-v3-4k.png&#34; alt=&#34;From biological memory traces to an agent memory stack&#34; /&gt;&#xA;  &#xA;  &#xA;  &lt;/figure&gt;&#xA;&lt;p&gt;To decide whether a system genuinely remembers, I would rather ask three questions:&lt;/p&gt;</description>
      
    </item>
    
  </channel>
</rss>
