Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval
For researchers in AI and ML, this survey clarifies when and how to integrate graphs with LLMs, but it is an incremental contribution as it synthesizes existing work without introducing new methods or results.
This survey provides a structured overview of design choices for integrating graphs with LLMs, categorizing methods by purpose, graph modality, and integration strategy across multiple domains. It offers a practical guide for selecting appropriate graph-LLM approaches based on task requirements.
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.