Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval

TL;DR

This survey reviews how graphs are integrated with Large Language Models to improve reasoning, retrieval, and decision-making across various applications, categorizing methods and providing practical guidance.

Contribution

It offers a structured overview of graph-LLM integration strategies, categorizing methods by purpose, graph modality, and approach, to guide future research and application.

Findings

Categorizes graph-LLM integration methods by purpose, modality, and strategy.

Maps techniques across domains like healthcare, cybersecurity, and robotics.

Highlights strengths and limitations of each integration approach.

Abstract

Generative AI, particularly Large Language Models, increasingly integrates graph-based representations to enhance reasoning, retrieval, and structured decision-making. Despite rapid advances, there remains limited clarity regarding when, why, where, and what types of graph-LLM integrations are most appropriate across applications. This survey provides a concise, structured overview of the design choices underlying the integration of graphs with LLMs. We categorize existing methods based on their purpose (reasoning, retrieval, generation, recommendation), graph modality (knowledge graphs, scene graphs, interaction graphs, causal graphs, dependency graphs), and integration strategies (prompting, augmentation, training, or agent-based use). By mapping representative works across domains such as cybersecurity, healthcare, materials science, finance, robotics, and multimodal environments, we highlight the strengths, limitations, and best-fit scenarios for each technique. This survey aims to offer researchers a practical guide for selecting the most suitable graph-LLM approach depending on task requirements, data characteristics, and reasoning complexity.