<?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>Agent-Training on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/agent-training/</link><description>Recent content in Agent-Training 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, 10 Aug 2026 08:00:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/agent-training/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Native Digest 2026-08-10</title><link>https://douyixuan.github.io/posts/ai-native/2026-08-10/</link><pubDate>Mon, 10 Aug 2026 08:00:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-native/2026-08-10/</guid><description>今天关注 AI-native agent 的两个底层问题：工具调用是否应该从 JSON 升级为可编程代码，以及如何低成本生成可验证、可递归变难的长周期 terminal-agent 训练任务。</description></item></channel></rss>