Graph memory helps language assistants remember and adapt over time
Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation
Artificial Intelligence
Summary
Keeping track of what someone says and does is important for language assistants to be helpful over long periods. The authors surveyed how memory can be organized as a graph, which connects bits of user information with links and timelines. This structure can show how memories relate, change, and get looked up later to tailor the assistant’s responses. They also compared different ways to build and evaluate these memory graphs, pointing out challenges and options for future improvements.
What this means in practice
- •For software developers: Create personalized assistants that adapt to individual users by managing memory as connected and evolving information graphs.
- •For customer support teams: Improve long-term user interaction by structuring past conversations and preferences into retrievable graph memories.
A survey. It maps existing work.
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.