From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms

从存储到体验：大语言模型智能体记忆机制演进综述

Abstract: Large Language Model (LLM)-based agents have fundamentally reshaped artificial intelligence by integrating external tools and planning capabilities. While memory mechanisms have emerged as the architectural cornerstone of these systems, current research remains fragmented, oscillating between operating system engineering and cognitive science. This theoretical divide prevents a unified view of technological synthesis and a coherent evolutionary perspective.

摘要： 基于大语言模型（LLM）的智能体通过集成外部工具和规划能力，从根本上重塑了人工智能。尽管记忆机制已成为这些系统的架构基石，但目前的研究仍处于碎片化状态，在操作系统工程与认知科学之间摇摆不定。这种理论上的割裂阻碍了对技术综合的统一认识以及连贯演进视角的形成。

To bridge this gap, this survey proposes a novel evolutionary framework for LLM agent memory mechanisms, formalizing the development process into three stages: Storage (trajectory preservation), Reflection (trajectory refinement), and Experience (trajectory abstraction). We first formally define these three stages before analyzing the three core drivers of this evolution: the necessity for long-range consistency, the challenges in dynamic environments, and the ultimate goal of continual learning.

为了弥合这一差距，本综述提出了一种全新的大语言模型智能体记忆机制演进框架，将发展过程形式化为三个阶段：存储（轨迹保存）、反思（轨迹优化）和体验（轨迹抽象）。我们首先对这三个阶段进行了正式定义，随后分析了推动这一演进的三个核心驱动力：对长程一致性的需求、动态环境带来的挑战，以及持续学习的最终目标。

Furthermore, we specifically explore two transformative mechanisms in the frontier Experience stage: proactive exploration and cross-trajectory abstraction. By synthesizing these disparate views, this work offers robust design principles and a clear roadmap for the development of next-generation LLM agents.

此外，我们重点探讨了处于前沿“体验”阶段的两种变革性机制：主动探索与跨轨迹抽象。通过综合这些不同的观点，本研究为下一代大语言模型智能体的开发提供了稳健的设计原则和清晰的路线图。