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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Minghao, Zhu, Xi, Xue, Haochen, Zhang, Chong, Lin, Shuhang, Huang, Jingyuan, Ye, Ziyi, Zhang, Yongfeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917025828306944
author Guo, Minghao
Zhu, Xi
Xue, Haochen
Zhang, Chong
Lin, Shuhang
Huang, Jingyuan
Ye, Ziyi
Zhang, Yongfeng
author_facet Guo, Minghao
Zhu, Xi
Xue, Haochen
Zhang, Chong
Lin, Shuhang
Huang, Jingyuan
Ye, Ziyi
Zhang, Yongfeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00429
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReaGAN: Node-as-Agent-Reasoning Graph Agentic Network
Guo, Minghao
Zhu, Xi
Xue, Haochen
Zhang, Chong
Lin, Shuhang
Huang, Jingyuan
Ye, Ziyi
Zhang, Yongfeng
Computation and Language
Machine Learning
Multiagent Systems
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.
title ReaGAN: Node-as-Agent-Reasoning Graph Agentic Network
topic Computation and Language
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2508.00429