<?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 Frontier on YanlunAI</title><link>https://yanlunai.com/en/frontier/</link><description>Recent content in Research Frontier on YanlunAI</description><generator>Hugo -- 0.152.2</generator><language>en</language><lastBuildDate>Mon, 24 Aug 2026 09:00:00 +0800</lastBuildDate><atom:link href="https://yanlunai.com/en/frontier/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent memory is becoming a decision problem—not a storage problem</title><link>https://yanlunai.com/en/frontier/agent-memory-2026/</link><pubDate>Mon, 24 Aug 2026 09:00:00 +0800</pubDate><guid>https://yanlunai.com/en/frontier/agent-memory-2026/</guid><description>The hard part is not storing history. It is deciding what to write, when to retrieve it, and when to forget.</description></item></channel></rss>