<?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>搜索 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%90%9C%E7%B4%A2/</link><description>Recent content in 搜索 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Thu, 16 Jul 2026 10:30:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%90%9C%E7%B4%A2/index.xml" rel="self" type="application/rss+xml"/><item><title>推理时计算扩展：o1范式背后的技术原理与工程实现</title><link>https://guijiagi.com/posts/b2-48526210/</link><pubDate>Thu, 16 Jul 2026 10:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-48526210/</guid><description>深度解析OpenAI o1系列模型的推理时计算扩展技术，涵盖过程奖励模型、搜索算法与思维链优化</description></item><item><title>大模型推理时计算：Test-time Compute 的理论与实践</title><link>https://guijiagi.com/posts/test-time-compute-theory-practice/</link><pubDate>Sun, 28 Jun 2026 11:17:00 +0800</pubDate><guid>https://guijiagi.com/posts/test-time-compute-theory-practice/</guid><description>深入解析Test-time Compute的原理、方法与实践，探讨推理时计算Scaling的新范式</description></item><item><title>Perplexity Pro Search 评测：AI 搜索的未来形态</title><link>https://guijiagi.com/posts/perplexity-pro-search-review/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/perplexity-pro-search-review/</guid><description>深度评测 Perplexity Pro Search 的多步推理、搜索质量、引用系统及与 Google/Bing 的全面对比</description></item></channel></rss>