<?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>微软 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%BE%AE%E8%BD%AF/</link><description>Recent content in 微软 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 10:29:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%BE%AE%E8%BD%AF/index.xml" rel="self" type="application/rss+xml"/><item><title>开源智能体框架AutoGen深度解析：多Agent协作的工程实践</title><link>https://guijiagi.com/posts/b2-d83bc187/</link><pubDate>Thu, 16 Jul 2026 10:29:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-d83bc187/</guid><description>深入微软AutoGen框架的架构设计与工程实践，解析多Agent协作模式、代码执行与对话管理机制</description></item><item><title>AutoGen 2026多智能体：协作AI的新范式</title><link>https://guijiagi.com/posts/autogen-2026-multi-agent/</link><pubDate>Thu, 02 Jul 2026 11:28:00 +0800</pubDate><guid>https://guijiagi.com/posts/autogen-2026-multi-agent/</guid><description>2026年AutoGen多智能体框架解析，构建协作AI系统</description></item><item><title>Semantic Kernel 2026：微软AI编排框架的成熟之路</title><link>https://guijiagi.com/posts/semantic-kernel-2026-microsoft-ai-orchestration/</link><pubDate>Tue, 30 Jun 2026 09:55:00 +0800</pubDate><guid>https://guijiagi.com/posts/semantic-kernel-2026-microsoft-ai-orchestration/</guid><description>评测Semantic Kernel 2026在AI编排、插件系统与企业集成方面的成熟度</description></item><item><title>AutoGen 2026：微软的多Agent对话框架深度评测</title><link>https://guijiagi.com/posts/autogen-2026-microsoft-multi-agent-framework-review/</link><pubDate>Tue, 30 Jun 2026 09:40:00 +0800</pubDate><guid>https://guijiagi.com/posts/autogen-2026-microsoft-multi-agent-framework-review/</guid><description>全面评测AutoGen 2026版本的多Agent对话编排能力、GroupChat机制与生产就绪度</description></item><item><title>AutoGen 2026：微软的多Agent对话框架深度评测</title><link>https://guijiagi.com/posts/autogen-2026-microsoft-multi-agent-review/</link><pubDate>Tue, 30 Jun 2026 09:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/autogen-2026-microsoft-multi-agent-review/</guid><description>全面评测微软AutoGen 2026版本的多Agent对话能力、GroupChat机制、代码执行环境及与Azure生态的深度集成</description></item><item><title>Semantic Kernel 2026：微软AI编排框架的成熟之路</title><link>https://guijiagi.com/posts/semantic-kernel-2026-enterprise-ai-orchestration/</link><pubDate>Tue, 30 Jun 2026 09:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/semantic-kernel-2026-enterprise-ai-orchestration/</guid><description>回顾Semantic Kernel从实验性项目到企业级AI编排框架的演进，分析其核心抽象、插件系统和与Azure生态的深度集成</description></item><item><title>Semantic Kernel 2026：微软 AI 编排框架的成熟</title><link>https://guijiagi.com/posts/semantic-kernel-2026/</link><pubDate>Sun, 28 Jun 2026 11:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/semantic-kernel-2026/</guid><description>深度评测微软 Semantic Kernel 2026 版本，从 Plugin 生态到多 Agent 编排的全面进化</description></item><item><title>AutoGen 多智能体框架：从对话到协作</title><link>https://guijiagi.com/posts/autogen-multi-agent/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/autogen-multi-agent/</guid><description>深入解析微软 AutoGen 多智能体框架的架构设计、通信机制和生产级应用实践。</description></item><item><title>Microsoft Copilot Studio：企业级 Agent 构建平台</title><link>https://guijiagi.com/posts/copilot-studio-enterprise/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/copilot-studio-enterprise/</guid><description>深入剖析 Microsoft Copilot Studio 的架构设计、开发流程和企业级部署最佳实践。</description></item><item><title>微软 MAI 模型家族：从 1B 到 1T 的全覆盖</title><link>https://guijiagi.com/posts/microsoft-mai-models/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/microsoft-mai-models/</guid><description>微软发布自研 MAI 模型家族，覆盖 1B 到 1T 参数全规模，挑战 OpenAI 依赖，重塑 AI 战略版图。</description></item><item><title>GraphRAG 解析：微软的知识图谱增强 RAG</title><link>https://guijiagi.com/posts/graphrag-explained/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/graphrag-explained/</guid><description>深入解析微软 GraphRAG 的原理、架构和实现，对比 Vector RAG 的差异和适用场景</description></item><item><title>Semantic Kernel 评测：微软的 AI 编排内核</title><link>https://guijiagi.com/posts/semantic-kernel-review/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/semantic-kernel-review/</guid><description>Semantic Kernel 如何用 Plugin 系统编排 AI 能力？Planner 自动编排、Memory 语义记忆、Connector 多模型接入——本文从企业集成视角评测微软的 AI 编排框架。</description></item><item><title>AutoGen 多智能体框架评测：微软的 Agent 雄心</title><link>https://guijiagi.com/posts/autogen-multi-agent-review/</link><pubDate>Wed, 24 Jun 2026 14:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/autogen-multi-agent-review/</guid><description>AutoGen v0.4 新架构解析、多 Agent 对话模式、GroupChat、代码执行、与 LangGraph/CrewAI 横向对比</description></item></channel></rss>