<?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>AI on Yining&#39;s Blog</title>
    <link>https://yningg.github.io/Blogs/tags/ai/</link>
    <description>Recent content in AI on Yining&#39;s Blog</description>
    <image>
      <title>Yining&#39;s Blog</title>
      <url>https://github.com/Yningg/Blogs/tree/master/static/apple-touch-icon.png</url>
      <link>https://github.com/Yningg/Blogs/tree/master/static/apple-touch-icon.png</link>
    </image>
    <generator>Hugo -- 0.158.0</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 18 Mar 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://yningg.github.io/Blogs/tags/ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities</title>
      <link>https://yningg.github.io/Blogs/posts/research/graphai/</link>
      <pubDate>Wed, 18 Mar 2026 00:00:00 +0000</pubDate>
      <guid>https://yningg.github.io/Blogs/posts/research/graphai/</guid>
      <description>&lt;p&gt;This survey presents a first systematic review of how graphs can empower AI agents. It&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Focuses on the potential of graph learning to bolster agent planning, agent execution, agent memory, and multiagent coordination.&lt;/li&gt;
&lt;li&gt;Explores the reciprocal relationship, detailing how AI agents can, in turn, empower and refine graph learning processes.&lt;/li&gt;
&lt;li&gt;Outlines promising applications and identify key future research opportunities&lt;/li&gt;
&lt;/ul&gt;
&lt;h2 id=&#34;preliminaries&#34;&gt;Preliminaries&lt;/h2&gt;
&lt;p&gt;&lt;strong&gt;AI Agents&lt;/strong&gt;: An AI agent is an intelligent model capable of perceiving its environment and making autonomous decisions to achieve specific goals.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
