<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>搜索技术 on AI内参</title>
    <link>https://www.neican.ai/tags/%E6%90%9C%E7%B4%A2%E6%8A%80%E6%9C%AF/</link>
    <description>Recent content in 搜索技术 on AI内参</description>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Wed, 24 Jun 2026 17:40:04 +0800</lastBuildDate>
    <atom:link href="https://www.neican.ai/tags/%E6%90%9C%E7%B4%A2%E6%8A%80%E6%9C%AF/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>超越“搜索”与“推荐”的边界：大模型时代信息获取范式的重构</title>
      <link>https://www.neican.ai/insights/article-20260624174004964-2/</link>
      <pubDate>Wed, 24 Jun 2026 17:40:04 +0800</pubDate>
      <guid>https://www.neican.ai/insights/article-20260624174004964-2/</guid>
      <description>文章深度剖析了GEMS框架如何通过梯度子空间优化，破解了搜索与推荐多任务协作的难题。强调这一技术不仅提升了信息检索的效率，更标志着信息获取方式正向意图统一的智能化方向演进。</description>
    </item>
  </channel>
</rss>
