<?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>Reward on Njx&#39;Log</title>
    <link>https://njx-njx.github.io/tags/reward/</link>
    <description>Recent content in Reward on Njx&#39;Log</description>
    <image>
      <title>Njx&#39;Log</title>
      <url>https://njx-njx.github.io/capybara-right.png</url>
      <link>https://njx-njx.github.io/capybara-right.png</link>
    </image>
    <generator>Hugo -- 0.161.1</generator>
    <language>zh-cn</language>
    <lastBuildDate>Fri, 22 May 2026 15:40:00 +0800</lastBuildDate>
    <atom:link href="https://njx-njx.github.io/tags/reward/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Agentic RL: Reward, Behavior, and The Long Shadow Of Feedback</title>
      <link>https://njx-njx.github.io/posts/agentic-rl-reward-and-behavior/</link>
      <pubDate>Fri, 22 May 2026 15:40:00 +0800</pubDate>
      <guid>https://njx-njx.github.io/posts/agentic-rl-reward-and-behavior/</guid>
      <description>A field note on agentic RL: reward design, behavior shaping, credit assignment, online and offline evaluation, and the feedback loops behind agents.</description>
    </item>
  </channel>
</rss>
