https://ahren09.github.io/tags/agent-memory/Agent MemoryHugo Blox Builder (https://hugoblox.com)en-usThu, 01 Oct 2026 00:00:00 +0000https://ahren09.github.io/media/icon_hu_eee6347cbdb2cc3f.pnghttps://ahren09.github.io/tags/agent-memory/https://ahren09.github.io/publication/preprint26_sourcelearn/Thu, 01 Oct 2026 00:00:00 +0000https://ahren09.github.io/publication/preprint26_sourcelearn/<h2 id="overview">Overview</h2> <p>SourceLearn studies how an LLM agent can progressively learn from a persistent authoritative source. It maintains a source model that represents how knowledge is structured, interpreted, and applied. Self-directed learning revisits incompletely understood material, while task-guided learning identifies recurring representational needs. Both mechanisms reconstruct persistent updates from the original source.</p> <h2 id="links">Links</h2> <ul> <li> </li> <li> </li> <li> </li> </ul>