<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Source Learning | Yiyang "Diana" Wang</title><link>https://hello-diana.github.io/tags/source-learning/</link><atom:link href="https://hello-diana.github.io/tags/source-learning/index.xml" rel="self" type="application/rss+xml"/><description>Source Learning</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Thu, 01 Oct 2026 00:00:00 +0000</lastBuildDate><image><url>https://hello-diana.github.io/media/icon_hu_9f6d321bccb06734.png</url><title>Source Learning</title><link>https://hello-diana.github.io/tags/source-learning/</link></image><item><title>From Knowledge Access to Source Learning: Developing Source-Specific Competence</title><link>https://hello-diana.github.io/publication/sourcelearn/</link><pubDate>Thu, 01 Oct 2026 00:00:00 +0000</pubDate><guid>https://hello-diana.github.io/publication/sourcelearn/</guid><description>&lt;p&gt;&lt;strong&gt;SourceLearn&lt;/strong&gt; studies how LLM agents can progressively learn from a persistent authoritative source. It builds a reusable source model that represents how knowledge is structured, interpreted, and applied.&lt;/p&gt;
&lt;p&gt;Self-directed learning revisits incompletely understood material, while task-guided learning uses downstream experience to identify gaps. Updates remain grounded in the authoritative source.&lt;/p&gt;</description></item></channel></rss>