GMAgent: A Graph-oriented Multi-agent Collaboration Framework for Text-attributed Graph Analysis

TMLR Paper4884 Authors

Abstract: Text-Attributed Graphs (TAGs) are crucial for modeling interconnected data in numerous real-world applications. Graph Neural Networks (GNNs) excel at efficiently capturing global structural information across TAGs, while Large Language Models (LLMs) offer strong capabilities in local semantic understanding. Despite the recent development of integrating GNNs and LLMs for TAG analysis, these approaches often fail to fully exploit their complementary strengths by relying primarily on a single architecture. Furthermore, LLM-based multi-agent collaboration systems have shown promising potential across diverse fields. However, their integration with GNNs for graph analytical tasks remains underexplored. To this end, we introduce GMAgent, a novel graph-oriented multi-agent collaboration framework that effectively and flexibly interacts between diverse GNN-based and LLM-based graph agents, facilitating comprehensive TAG analysis. First, we deploy multiple GNNs as graph agents to perform conflict evaluation, identifying conflict scenarios for further multi-agent collaboration. Then, we repurpose LLMs as graph agents via graph-driven instruction tuning and adopt a role-play expert recruiting strategy, thereby generating LLM graph experts' initial analyses for conflict scenarios. Finally, we conduct a graph-oriented multi-agent collaboration to effectively and efficiently guide collaborative self-reflection on graph experts and the final answer selection. Extensive experimental results on five datasets demonstrate significant improvements, showcasing the potential of our GMAgent in improving the effectiveness, interoperability, and flexibility of comprehensive TAG analysis.

Submission Length: Long submission (more than 12 pages of main content)

Assigned Action Editor: ~Chuxu_Zhang2

Submission Number: 4884