---
id: 20260929-T0-10
title: "团队记忆分层管理：LLM Agent中有效性感知检索新方法"
title_en: "Not All Memories Are Equal: Hierarchical Memory for LLM Agent Retrieval"
url: https://ai.daily.yangsir.net/daily/20260929-T0-10
issue_date: 2026-09-29
publish_date: 2026-09-28T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2609.30289
---

# 团队记忆分层管理：LLM Agent中有效性感知检索新方法

arXiv新论文提出一种面向LLM Agent的分层协作记忆方法，解决团队协作场景中记忆异构且持续演化的问题。团队记忆包含集体决策、协议和当前共识，个体记忆则保存成员特定观察、执行轨迹和交互记录，两者在有效性和检索优先级上并不相同。该方法强调“并非所有记忆都同等重要”，通过有效性感知的检索机制提升Agent在协作任务中的信息利用效率。这对构建长期运行、多Agent协作的智能系统具有实际参考价值。

## English Version

**Not All Memories Are Equal: Hierarchical Memory for LLM Agent Retrieval**

A new arXiv paper proposes hierarchical collaborative memory for LLM agents, addressing heterogeneous and evolving memory in team collaboration. Team memory captures collective decisions, protocols, and consensus, while individual memory preserves member-specific observations, execution traces, and interactions, with differing validity and retrieval priority. The method stresses that 'not all memories are equal' and uses validity-aware retrieval to improve information use in collaborative agent tasks. It offers practical reference for building long-running, multi-agent intelligent systems.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2609.30289)

**详情页**：https://ai.daily.yangsir.net/daily/20260929-T0-10

---

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