[Submitted on 29 Sep 2026 (v1), last revised 13 Oct 2026 (this version, v2)]
Abstract:Large language models (LLMs) have become the foundation of personalized assistants, but maintaining persistent user memory across long-term interactions remains challenging. Existing memory systems often focus on storage, retrieval, or consolidation, while memory writing remains less controlled: transient requests, duplicate statements, and outdated user states may enter memory and later be retrieved for personalization. In this paper, we present AMU: Admission and Memory Update for Personalized Conversations, an SLM-guided (Small language model guided) structured framework for writing-time memory control. AMU uses structured memory filtering to decide what should enter memory and SLM-guided storage management to determine whether an admitted record should be stored separately, discarded as a duplicate, or fused as an update. We evaluate AMU in a controlled memory writing and retrieval setting. Experimental results show that AMU maintains cleaner and more retrievable personalized memories.
Submission history
From: Tao Hwang [view email]
[v1] Tue, 29 Sep 2026 08:12:09 UTC (1,399 KB)
[v2] Tue, 13 Oct 2026 07:19:55 UTC (1,399 KB)
