---
id: 20260709-T0-08
title: "NapMem：让LLM主动导航记忆而非被动检索，提升个性化对话"
title_en: "NapMem: LLM Learns to Navigate Memory as Action Space for Personalized Dialog"
url: https://ai.daily.yangsir.net/daily/20260709-T0-08
issue_date: 2026-07-09
publish_date: 2026-07-08T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2607.05794
---

# NapMem：让LLM主动导航记忆而非被动检索，提升个性化对话

NapMem 提出一种新框架，将长期用户记忆从被动检索接口转变为 LLM 可主动导航的结构化操作空间。传统记忆系统让模型只能消费预选知识，NapMem 则允许模型在多个记忆片段中自主选择、组合和操作信息，从而在个性化对话中更精准地调用用户历史。实验证明该方法在长程个性化任务上表现更优。

## English Version

**NapMem: LLM Learns to Navigate Memory as Action Space for Personalized Dialog**

NapMem transforms long-term user memory from passive retrieval to an active, structured action space for LLMs. Unlike traditional systems where models consume pre-selected evidence, NapMem lets agents navigate, combine, and manipulate memory fragments autonomously. This enables more accurate personalization in conversational AI, with superior results on long-term personalization tasks.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2607.05794)

**详情页**：https://ai.daily.yangsir.net/daily/20260709-T0-08

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*