Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects

TL;DR

This paper reviews recent progress in integrating graph structures with large language model agents to improve planning, memory, and multi-agent coordination, and discusses future research directions in this emerging field.

Contribution

It provides a comprehensive overview and categorization of GLA methods, analyzing how graphs enhance various agentic functions and outlining key future challenges.

Findings

Graphs improve planning and memory in LLM agents.

Graph learning algorithms enhance multi-agent coordination.

Future directions include scalable and multimodal GLA systems.

Abstract

Autonomous agents based on large language models (LLMs) have demonstrated impressive capabilities in a wide range of applications, including web navigation, software development, and embodied control. While most LLMs are limited in several key agentic procedures, such as reliable planning, long-term memory, tool management, and multi-agent coordination, graphs can serve as a powerful auxiliary structure to enhance structure, continuity, and coordination in complex agent workflows. Given the rapid growth and fragmentation of research on Graph-augmented LLM Agents (GLA), this paper offers a timely and comprehensive overview of recent advances and also highlights key directions for future work. Specifically, we categorize existing GLA methods by their primary functions in LLM agent systems, including planning, memory, and tool usage, and then analyze how graphs and graph learning algorithms contribute to each. For multi-agent systems, we further discuss how GLA solutions facilitate the orchestration, efficiency optimization, and trustworthiness of MAS. Finally, we highlight key future directions to advance this field, from improving structural adaptability to enabling unified, scalable, and multimodal GLA systems. We hope this paper can serve as a roadmap for future research on GLA and foster a deeper understanding of the role of graphs in LLM agent systems.