<?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>Research-Methodology on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/research-methodology/</link><description>Recent content in Research-Methodology 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>Sat, 24 Oct 2026 12:14:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/research-methodology/index.xml" rel="self" type="application/rss+xml"/><item><title>039 · 电路通过验证，为什么研究主张仍可能不成立？</title><link>https://douyixuan.github.io/posts/ai-silicon-papers/2026-10-24/</link><pubDate>Sat, 24 Oct 2026 12:14:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-silicon-papers/2026-10-24/</guid><description>八项 EDA Agent 研究尝试保留了成功与失败：正确电路不一定来自通用优化算法，精确求解代理目标也不一定改善物理结果。论文追问，当探索变便宜，什么证据才足以支持研究贡献？</description></item></channel></rss>