ReaGAN: Node-as-Agent-Reasoning Graph Agentic Network

TL;DR

ReaGAN introduces an agent-based graph neural network that enables nodes to make autonomous decisions and access global semantic information, improving learning efficiency especially in few-shot scenarios.

Contribution

The paper presents ReaGAN, a novel framework combining node-level decision-making with retrieval-augmented mechanisms to enhance graph learning capabilities.

Findings

ReaGAN performs well in few-shot learning without fine-tuning.

Nodes can independently plan actions based on internal memory.

Global semantic retrieval improves information propagation.

Abstract

Graph Neural Networks (GNNs) have achieved remarkable success in graph-based learning by propagating information among neighbor nodes via predefined aggregation mechanisms. However, such fixed schemes often suffer from two key limitations. First, they cannot handle the imbalance in node informativeness -- some nodes are rich in information, while others remain sparse. Second, predefined message passing primarily leverages local structural similarity while ignoring global semantic relationships across the graph, limiting the model's ability to capture distant but relevant information. We propose Retrieval-augmented Graph Agentic Network (ReaGAN), an agent-based framework that empowers each node with autonomous, node-level decision-making. Each node acts as an agent that independently plans its next action based on its internal memory, enabling node-level planning and adaptive message propagation. Additionally, retrieval-augmented generation (RAG) allows nodes to access semantically relevant content and build global relationships in the graph. ReaGAN achieves competitive performance under few-shot in-context settings using a frozen LLM backbone without fine-tuning, showcasing the potential of agentic planning and local-global retrieval in graph learning.