<?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>Data-Flow-Invariant on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/data-flow-invariant/</link><description>Recent content in Data-Flow-Invariant on 兜忆轩 | Cedric's Compiler Notes</description><image><title>兜忆轩 | Cedric's Compiler Notes</title><url>https://douyixuan.github.io/images/papermod-cover.png</url><link>https://douyixuan.github.io/images/papermod-cover.png</link></image><generator>Hugo -- 0.146.0</generator><language>en-us</language><lastBuildDate>Mon, 28 Sep 2026 12:08:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/data-flow-invariant/index.xml" rel="self" type="application/rss+xml"/><item><title>013 · 告诉 Agent 错在哪里，比只说“结果错了”更有用吗？</title><link>https://douyixuan.github.io/posts/ai-silicon-papers/2026-09-28/</link><pubDate>Mon, 28 Sep 2026 12:08:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-silicon-papers/2026-09-28/</guid><description>Ave 把 GPU kernel 优化必须保持的数据关系写成编译期不变量，再用静态分析与具体反例指导 Agent 修复；消融实验支持这种结构化反馈，但其保证范围取决于人预先表达了哪些不变量。</description></item></channel></rss>