HiMeS: Hippocampus-inspired Memory System for Personalized AI Assistants

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Hailong, Li, Feifei, Que, Wenhui, Fan, Xingyu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917194190815232
author Li, Hailong
Li, Feifei
Que, Wenhui
Fan, Xingyu
author_facet Li, Hailong
Li, Feifei
Que, Wenhui
Fan, Xingyu
contents Large language models (LLMs) power many interactive systems such as chatbots, customer-service agents, and personal assistants. In knowledge-intensive scenarios requiring user-specific personalization, conventional retrieval-augmented generation (RAG) pipelines exhibit limited memory capacity and insufficient coordination between retrieval mechanisms and user-specific conversational history, leading to redundant clarification, irrelevant documents, and degraded user experience. Inspired by the hippocampus-neocortex memory mechanism, we propose HiMeS, an AI-assistant architecture that fuses short-term and long-term memory. Our contributions are fourfold: (1) A short-term memory extractor is trained end-to-end with reinforcement learning to compress recent dialogue and proactively pre-retrieve documents from the knowledge base, emulating the cooperative interaction between the hippocampus and prefrontal cortex. (2) A partitioned long-term memory network stores user-specific information and re-ranks retrieved documents, simulating distributed cortical storage and memory reactivation. (3) On a real-world industrial dataset, HiMeS significantly outperforms a cascaded RAG baseline on question-answering quality. (4) Ablation studies confirm the necessity of both memory modules and suggest a practical path toward more reliable, context-aware, user-customized LLM-based assistants.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06152
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HiMeS: Hippocampus-inspired Memory System for Personalized AI Assistants
Li, Hailong
Li, Feifei
Que, Wenhui
Fan, Xingyu
Artificial Intelligence
Large language models (LLMs) power many interactive systems such as chatbots, customer-service agents, and personal assistants. In knowledge-intensive scenarios requiring user-specific personalization, conventional retrieval-augmented generation (RAG) pipelines exhibit limited memory capacity and insufficient coordination between retrieval mechanisms and user-specific conversational history, leading to redundant clarification, irrelevant documents, and degraded user experience. Inspired by the hippocampus-neocortex memory mechanism, we propose HiMeS, an AI-assistant architecture that fuses short-term and long-term memory. Our contributions are fourfold: (1) A short-term memory extractor is trained end-to-end with reinforcement learning to compress recent dialogue and proactively pre-retrieve documents from the knowledge base, emulating the cooperative interaction between the hippocampus and prefrontal cortex. (2) A partitioned long-term memory network stores user-specific information and re-ranks retrieved documents, simulating distributed cortical storage and memory reactivation. (3) On a real-world industrial dataset, HiMeS significantly outperforms a cascaded RAG baseline on question-answering quality. (4) Ablation studies confirm the necessity of both memory modules and suggest a practical path toward more reliable, context-aware, user-customized LLM-based assistants.
title HiMeS: Hippocampus-inspired Memory System for Personalized AI Assistants
topic Artificial Intelligence
url https://arxiv.org/abs/2601.06152