A Survey on the Memory Mechanism of Large Language Model based Agents
Zeyu Zhang1{}^{1}, Xiaohe Bo1{}^{1}, Chen Ma1{}^{1}, Rui Li1{}^{1}, Xu Chen1{}^{1}, Quanyu Dai2{}^{2}, Jieming Zhu2{}^{2}, Zhenhua Dong2{}^{2}, Ji-Rong Wen1{}^{1} 1{}^{1}Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China 2{}^{2}Huawei Noah’s Ark Lab, China
Abstract
Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. Compared with original LLMs, LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems that need long-term and complex agent-environment interactions. The key component to support agent-environment interactions is the memory of the agents. While previous studies have proposed many promising memory mechanisms, they are scattered in different papers, and there lacks a systematical review to summarize and compare these works from a holistic perspective, failing to abstract common and effective designing patterns for inspiring future studies. To bridge this gap, in this paper, we propose a comprehensive survey on the memory mechanism of LLM-based agents. In specific, we first discuss “what is” and “why do we need” the memory in LLM-based agents. Then, we systematically review previous studies on how to design and evaluate the memory module. In addition, we also present many agent applications, where the memory module plays an important role. At last, we analyze the limitations of existing work and show impor
中文速览
大型语言模型（LLM）驱动的智能体（agent）要在真实环境中持续学习和行动，离不开一个核心能力——记忆（memory），但学术界此前对这一机制的研究散落在各处，缺乏系统性的梳理。这篇综述从"记忆是什么、为什么需要它、怎么设计和评估它"三个问题出发，把现有工作整理成清晰的分类体系，涵盖记忆的信息来源、存储形式和读写操作三个维度，同时归纳了直接评估与借助具体任务间接评估两类方法。研究还梳理了角色扮演、社交模拟、个人助手、开放世界游戏、代码生成、推荐系统和专家系统等七类典型应用场景，展示了记忆模块在实践中的关键作用。这是目前首篇专门针对LLM智能体记忆机制的综述，为后续研究提供了统一的概念框架和设计参考，有助于推动智能体向真正的通用人工智能（AGI）方向迈进。
原文 arXiv:2404.13501;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2404.13501v1