<?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>推理增强 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%8E%A8%E7%90%86%E5%A2%9E%E5%BC%BA/</link><description>Recent content in 推理增强 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 10:48:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%8E%A8%E7%90%86%E5%A2%9E%E5%BC%BA/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型推理增强技术：o1之后的推理范式演进</title><link>https://guijiagi.com/posts/b2-ff7086a1/</link><pubDate>Thu, 16 Jul 2026 10:48:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-ff7086a1/</guid><description>分析o1之后推理增强技术的最新进展，涵盖隐式CoT、过程奖励模型与推理时搜索的工程实践</description></item><item><title>知识图谱增强大模型：神经符号融合的实践路径</title><link>https://guijiagi.com/posts/b2-97b38611/</link><pubDate>Thu, 16 Jul 2026 10:18:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-97b38611/</guid><description>探讨知识图谱与大语言模型融合的技术方案，涵盖知识注入、推理增强与可解释性提升</description></item><item><title>Prompt工程进阶：思维链、自一致性与推理增强技术</title><link>https://guijiagi.com/posts/b2-337d8871/</link><pubDate>Thu, 16 Jul 2026 10:12:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-337d8871/</guid><description>从CoT到ToT再到GoT，系统梳理提示工程中的推理增强技术栈及其适用场景</description></item><item><title>推理增强提示技术：让AI的推理更深入</title><link>https://guijiagi.com/posts/reasoning-prompt-techniques/</link><pubDate>Thu, 02 Jul 2026 11:13:00 +0800</pubDate><guid>https://guijiagi.com/posts/reasoning-prompt-techniques/</guid><description>2026年推理增强提示技术全面指南，覆盖Self-Consistency、ToT、ReAct等进阶技巧</description></item><item><title>自我一致性Self-Consistency技巧</title><link>https://guijiagi.com/posts/self-consistency-technique/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/self-consistency-technique/</guid><description>Self-Consistency技巧的原理、实现与优化策略，提升推理可靠性的利器</description></item></channel></rss>