Graph based memory helps language agents remember personal user details
Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation
Artificial Intelligence
Summary
Language model agents are becoming assistants that need to remember personal details about users over time. The authors explain how using graphs—a way to connect pieces of information with relationships—can help store and organize these memories. This method not only keeps track of what the agent knows but also how facts are linked and updated. The authors review different ways to build, change, and use graph memories and highlight the challenges of making these memories reliable and helpful. Their work helps clarify how such memory systems can make these agents more personalized and adaptive.
Large Language ModelsPersonalizationGraph memoryMemory representationMemory retrievalMemory evolutionUser preferencesLong-term memoryMemory evaluation
Authors
Dac Duy Anh Nguyen, Zhangchi Qiu, Shigeng Chen, Alan Wee-Chung Liew
Abstract
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.