发表机构
School of ICT Griffith University（格里菲斯大学信息与通信技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述从生命周期视角系统梳理基于图的LLM智能体个性化记忆，涵盖表示、演化、检索与评估，旨在阐明图记忆如何支持自适应、可控且以用户为中心的智能体。
AI 中文摘要
大语言模型（LLM）智能体正从单会话工具演变为长期个人助理，必须跨任务、跨情境、跨交互适应个体用户。这一转变使记忆成为个性化的核心需求，因为用户偏好、目标、约束、关系及过往经验是逐步积累的，且往往随时间变化。基于图的个性化记忆通过显式关系、时间上下文和证据链接，为建模此类用户信息提供了结构化方式。此类表示不仅能建模智能体对用户的记忆内容，还能建模记忆之间如何连接、修订和检索，以支持个性化决策。然而，现有工作分散在个性化智能体和通用图记忆框架中，难以从整体上理解设计空间。本综述提出了面向LLM智能体的基于图个性化记忆的生命周期视角。我们围绕记忆表示、记忆演化、记忆检索和记忆评估组织现有研究。我们进一步比较关键设计选择，讨论当前评估实践，以及构建可靠长期个性化智能体所面临的开放挑战。本综述旨在阐明基于图的记忆如何支持自适应、可控且以用户为中心的LLM智能体。
英文摘要
Large Language Model (LLM) agents are evolving from single-session tools toward long-term personal assistants that must adapt to individual users across tasks, contexts, and interactions. This shift makes memory a core requirement for personalization, since user preferences, goals, constraints, relationships, and past experiences are accumulated gradually and often change over time. Graph-based personalized memory provides a structured way to model such user information through explicit relations, temporal context, and evidence links. Such representations can model not only what an agent remembers about a user but also how memories are connected, revised, and retrieved to support personalized decisions. However, existing work remains fragmented across personalized agents and generic graph memory frameworks, making it difficult to understand the design space as a whole. This survey develops a lifecycle-oriented view of graph-based personalized memory for LLM agents. We organize existing studies around memory representation, memory evolution, memory retrieval, and memory evaluation. We further compare key design choices, discuss current evaluation practices, and open challenges in building reliable long-term personalized agents. This survey aims to clarify how graph-based memory can support adaptive, controllable, and user-centric LLM agents.
CommentsAccepted by ICKG 2026
