從儲存到體驗：大型語言模型智能體記憶機制的演化綜述

摘要

基於大型語言模型（LLM）的代理透過整合外部工具與規劃能力，從根本上重塑了人工智慧領域。儘管記憶機制已成為此類系統的架構基石，但目前的研究仍顯得零散，在作業系統工程與認知科學之間搖擺不定。這種理論上的分歧阻礙了技術綜效的統一視角及連貫的演化觀點。為填補此一缺口，本調查提出一個新穎的LLM代理記憶機制演化框架，將發展過程形式化為三個階段：儲存（軌跡保存）、反思（軌跡精煉）與經驗（軌跡抽象化）。我們首先正式定義這三個階段，接著分析驅動此演化的三大核心動力：長程一致性的必要性、動態環境中的挑戰，以及持續學習的最終目標。此外，我們特別探討前沿「經驗」階段中的兩種轉化機制：主動探索與跨軌跡抽象化。透過整合這些分歧觀點，本研究為下一代LLM代理的開發提供了穩健的設計原則與清晰的路線圖。

English

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. 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. 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.

從儲存到體驗：大型語言模型智能體記憶機制的演化綜述

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

摘要

Support