<?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>Cross-Repository on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/cross-repository/</link><description>Recent content in Cross-Repository 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>Fri, 06 Nov 2026 08:00:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/cross-repository/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Native Digest 2026-11-06</title><link>https://douyixuan.github.io/posts/ai-native/2026-11-06/</link><pubDate>Fri, 06 Nov 2026 08:00:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-native/2026-11-06/</guid><description>CrossSWE 用真正需要多仓联合修改的任务评测 Coding Agent 的接口一致性；ServerBench 让 Agent 从头设计 LLM 推理服务，以有状态请求、GPU 成本和独立验证检验优化成果。两篇论文共同推进从单仓 Patch 到系统级工程交付的评测边界。</description></item></channel></rss>