Graph Agent: Explicit Reasoning Agent for Graphs

TL;DR

The paper introduces Graph Agent, a novel reasoning framework combining LLMs, symbolic reasoning, and memory to enhance interpretability and performance in graph reasoning tasks, achieving state-of-the-art results.

Contribution

It presents an innovative approach that integrates symbolic reasoning with graph embeddings using LLMs for explicit, interpretable graph reasoning.

Findings

Achieved state-of-the-art accuracy on node classification and link prediction.

Provided human-interpretable explanations for reasoning processes.

Demonstrated adaptability across different graph reasoning tasks.

Abstract

Graph embedding methods such as Graph Neural Networks (GNNs) and Graph Transformers have contributed to the development of graph reasoning algorithms for various tasks on knowledge graphs. However, the lack of interpretability and explainability of graph embedding methods has limited their applicability in scenarios requiring explicit reasoning. In this paper, we introduce the Graph Agent (GA), an intelligent agent methodology of leveraging large language models (LLMs), inductive-deductive reasoning modules, and long-term memory for knowledge graph reasoning tasks. GA integrates aspects of symbolic reasoning and existing graph embedding methods to provide an innovative approach for complex graph reasoning tasks. By converting graph structures into textual data, GA enables LLMs to process, reason, and provide predictions alongside human-interpretable explanations. The effectiveness of the GA was evaluated on node classification and link prediction tasks. Results showed that GA reached state-of-the-art performance, demonstrating accuracy of 90.65%, 95.48%, and 89.32% on Cora, PubMed, and PrimeKG datasets, respectively. Compared to existing GNN and transformer models, GA offered advantages of explicit reasoning ability, free-of-training, easy adaption to various graph reasoning tasks