<?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>架构对比 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%9E%B6%E6%9E%84%E5%AF%B9%E6%AF%94/</link><description>Recent content in 架构对比 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>Tue, 30 Jun 2026 11:30:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%9E%B6%E6%9E%84%E5%AF%B9%E6%AF%94/index.xml" rel="self" type="application/rss+xml"/><item><title>MoE架构深度对比：DeepSeek V4 vs Qwen3.5 vs Llama 4</title><link>https://guijiagi.com/posts/moe-architecture-comparison/</link><pubDate>Tue, 30 Jun 2026 11:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/moe-architecture-comparison/</guid><description>深度对比三大MoE架构大模型的技术细节和性能表现</description></item><item><title>MoE 架构深度对比：DeepSeek V4 vs Qwen3.5 vs Llama 4 Behemoth</title><link>https://guijiagi.com/posts/moe-architecture-deepseek-v4-vs-qwen35-vs-llama4-behemoth/</link><pubDate>Sun, 28 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/moe-architecture-deepseek-v4-vs-qwen35-vs-llama4-behemoth/</guid><description>三大MoE架构大模型的技术深度对比：路由机制、专家设计、推理效率全方位解析</description></item></channel></rss>