人工智能时代中的记忆机制

摘要

记忆已成为并仍将是基于基础模型的智能体核心能力。随着智能体记忆研究迅速扩展并吸引空前关注，该领域也日益呈现碎片化态势。现有归属于智能体记忆范畴的研究工作在动机、实现方式和评估协议上往往存在显著差异，而定义松散的记忆术语激增进一步模糊了概念清晰度。传统分类法（如长/短期记忆）已难以涵盖当代智能体记忆系统的多样性。本文旨在勾勒当前智能体记忆研究的最新图景。我们首先清晰界定智能体记忆的范畴，并将其与大型语言模型记忆、检索增强生成（RAG）及上下文工程等相关概念进行区分。随后通过形式、功能与动态性这三个统一视角审视智能体记忆：从形式维度识别出令牌级记忆、参数化记忆与潜空间记忆三大主流实现方式；从功能维度提出细粒度分类法，区分事实记忆、经验记忆与工作记忆；从动态性维度分析记忆如何随时间形成、演化与检索。为支撑实际开发，我们系统梳理了记忆基准测试与开源框架。在整合现有成果基础上，前瞻性阐述了记忆自动化、强化学习融合、多模态记忆、多智能体记忆及可信性等新兴研究方向。期望本综述不仅能作为现有工作的参考指南，更能为将记忆重新构想为未来智能体设计一等公民的概念基础。

English

Memory has emerged, and will continue to remain, a core capability of foundation model-based agents. As research on agent memory rapidly expands and attracts unprecedented attention, the field has also become increasingly fragmented. Existing works that fall under the umbrella of agent memory often differ substantially in their motivations, implementations, and evaluation protocols, while the proliferation of loosely defined memory terminologies has further obscured conceptual clarity. Traditional taxonomies such as long/short-term memory have proven insufficient to capture the diversity of contemporary agent memory systems. This work aims to provide an up-to-date landscape of current agent memory research. We begin by clearly delineating the scope of agent memory and distinguishing it from related concepts such as LLM memory, retrieval augmented generation (RAG), and context engineering. We then examine agent memory through the unified lenses of forms, functions, and dynamics. From the perspective of forms, we identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory. From the perspective of functions, we propose a finer-grained taxonomy that distinguishes factual, experiential, and working memory. From the perspective of dynamics, we analyze how memory is formed, evolved, and retrieved over time. To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks. Beyond consolidation, we articulate a forward-looking perspective on emerging research frontiers, including memory automation, reinforcement learning integration, multimodal memory, multi-agent memory, and trustworthiness issues. We hope this survey serves not only as a reference for existing work, but also as a conceptual foundation for rethinking memory as a first-class primitive in the design of future agentic intelligence.

人工智能时代中的记忆机制

Memory in the Age of AI Agents

摘要

Support