From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space
Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a consumer of pre-selected evidence. We introduce NapMem, a framework for learning to use long-term user m...
ArXiv CS.AI
Source
Generated insight by OnAirToday AI
This research moves beyond simply accessing user history to actively navigating it, treating memory as a structured action space. This approach allows conversational agents to leverage long-term user memory more effectively for personalization by selecting and inspecting relevant information at different granularities.
Get the day's AI news in one short email. Free.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.