---
id: 20260917-T0-05
title: "检索驱动的记忆再巩固，让LLM长期代理越用越聪明"
title_en: "Retrieval-Driven Memory Reconsolidation Improves Long-Term LLM Agents"
url: https://ai.daily.yangsir.net/daily/20260917-T0-05
issue_date: 2026-09-17
publish_date: 2026-09-16T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2609.16053
---

# 检索驱动的记忆再巩固，让LLM长期代理越用越聪明

一项新研究提出检索驱动的记忆再巩固方法，用于提升LLM代理在长期交互中的记忆能力。现有记忆系统通常只在新信息到来时更新记忆，把检索当作记忆访问的终点，而非记忆更新的驱动力。该方法将检索本身作为触发记忆再巩固的信号，使代理能在反复调用中动态调整记忆内容。这有望让LLM代理在长时间对话和任务中保持更准确、更相关的记忆。

## English Version

**Retrieval-Driven Memory Reconsolidation Improves Long-Term LLM Agents**

A new paper proposes retrieval-driven memory reconsolidation to improve long-term memory in LLM agents. Existing systems typically update memory only when new information arrives, treating retrieval as the endpoint rather than a driver of memory updates. This approach uses retrieval itself as a trigger for reconsolidation, letting agents dynamically adjust stored memories through repeated access. It could help LLM agents maintain more accurate, relevant memory over extended interactions and tasks.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2609.16053)

**详情页**：https://ai.daily.yangsir.net/daily/20260917-T0-05

---

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