<?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>结构化输出 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E7%BB%93%E6%9E%84%E5%8C%96%E8%BE%93%E5%87%BA/</link><description>Recent content in 结构化输出 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, 02 Jul 2026 11:20:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E7%BB%93%E6%9E%84%E5%8C%96%E8%BE%93%E5%87%BA/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM结构化输出指南</title><link>https://guijiagi.com/posts/structured-output-llm-guide/</link><pubDate>Thu, 02 Jul 2026 11:20:00 +0800</pubDate><guid>https://guijiagi.com/posts/structured-output-llm-guide/</guid><description>从JSON Schema到Constrained Decoding，确保LLM输出结构化数据的完整方案</description></item><item><title>结构化输出技术：从JSON Mode到Function Calling</title><link>https://guijiagi.com/posts/structured-output-json-mode-to-function-calling/</link><pubDate>Tue, 30 Jun 2026 10:50:00 +0800</pubDate><guid>https://guijiagi.com/posts/structured-output-json-mode-to-function-calling/</guid><description>全面介绍2026年LLM结构化输出技术，包括JSON Mode、Function Calling、Constrained Decoding等方案及其实际应用</description></item><item><title>SGLang 2026：结构化生成的高性能推理引擎</title><link>https://guijiagi.com/posts/sglang-2026-inference-engine/</link><pubDate>Sun, 28 Jun 2026 11:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/sglang-2026-inference-engine/</guid><description>深入探索 SGLang 2026 版本的 RadixAttention、结构化输出、推理优化与生产部署实践</description></item><item><title>结构化输出 Prompt 设计：让 LLM 稳定输出 JSON 的方法</title><link>https://guijiagi.com/posts/structured-output-prompt-design/</link><pubDate>Sun, 28 Jun 2026 10:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/structured-output-prompt-design/</guid><description>2026年让大模型稳定输出结构化数据的完整方案：从 Prompt 设计到约束解码的工程实践</description></item><item><title>Instructor 框架评测：结构化输出的优雅方案</title><link>https://guijiagi.com/posts/instructor-review/</link><pubDate>Wed, 24 Jun 2026 16:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/instructor-review/</guid><description>评测 Instructor 框架的 Pydantic 模型定义、自动重试、流式结构化输出能力及与 Function Calling 的对比</description></item></channel></rss>