<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>推理链优化 on AI内参</title>
    <link>https://www.neican.ai/tags/%E6%8E%A8%E7%90%86%E9%93%BE%E4%BC%98%E5%8C%96/</link>
    <description>Recent content in 推理链优化 on AI内参</description>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Wed, 24 Jun 2026 15:10:06 +0800</lastBuildDate>
    <atom:link href="https://www.neican.ai/tags/%E6%8E%A8%E7%90%86%E9%93%BE%E4%BC%98%E5%8C%96/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>从“凑答案”到“会思考”：TRM如何重塑大模型逻辑评估的深度范式</title>
      <link>https://www.neican.ai/insights/trm-20260624151006306-1/</link>
      <pubDate>Wed, 24 Jun 2026 15:10:06 +0800</pubDate>
      <guid>https://www.neican.ai/insights/trm-20260624151006306-1/</guid>
      <description>TRM引入ME²原则与DAG结构评估，成功将大模型的“推理质量”从模糊的主观判断转化为可度量的科学指标，这一范式转换不仅优化了模型的强化学习流程，更为通往高可信、透明化的推理智能铺平了道路。</description>
    </item>
  </channel>
</rss>
