<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Systems on KAD</title>
    <link>https://www.kad8.com/tags/systems/</link>
    <description>Recent content in Systems on KAD</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>© 2026 </copyright>
    <lastBuildDate>Fri, 03 Jul 2026 21:52:29 +0800</lastBuildDate><atom:link href="https://www.kad8.com/tags/systems/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>AReaL 2.0 Open Source: Building Self-Evolving AI Agents with Online RL</title>
      <link>https://www.kad8.com/ai/areal-2.0-open-source-building-self-evolving-ai-agents-with-online-rl/</link>
      <pubDate>Fri, 03 Jul 2026 21:52:29 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/areal-2.0-open-source-building-self-evolving-ai-agents-with-online-rl/</guid>
      <description>&lt;blockquote&gt;
&lt;p&gt;AReaL 2.0 Open Source: Building Self-Evolving AI Agents with Online RL&lt;/p&gt;&lt;/blockquote&gt;
&lt;p&gt;AI agents have rapidly evolved from impressive demonstrations into production systems powering software engineering, customer support, research, and enterprise automation. As adoption accelerates, the industry&amp;rsquo;s focus is shifting away from a simple question—&lt;em&gt;Can an agent complete a task?&lt;/em&gt;—toward a far more ambitious one:&lt;/p&gt;</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/areal-2.0-open-source-building-self-evolving-ai-agents-with-online-rl/featured-AReaL_2.0_reinforcement_learning.jpeg" />
    </item>
    
  </channel>
</rss>
