GeAR: Graph-enhanced Agent for Retrieval-augmented Generation
Zhili Shen, Chenxin Diao, Pavlos Vougiouklis, Pascual Merita, Shriram Piramanayagam, Enting Chen, Damien Graux, Andre Melo
Abstract
Retrieval-augmented Generation (RAG) relies on effective retrieval capabilities, yet traditional sparse and dense retrievers inherently struggle with multi-hop retrieval scenarios. In this paper, we introduce G\small{E}\normalsize{AR}, a system that advances RAG performance through two key innovations: (i) an efficient graph expansion mechanism that augments any conventional base retriever, such as BM25, and (ii) an agent framework that incorporates the resulting graph-based retrieval into a multi-step retrieval framework. Our evaluation demonstrates G\small{E}\normalsize{AR}‘s superior retrieval capabilities across three multi-hop question answering datasets. Notably, our system achieves state-of-the-art results with improvements exceeding 10% on the challenging MuSiQue dataset, while consuming fewer tokens and requiring fewer iterations than existing multi-step retrieval systems. The project page is available at https://gear-rag.github.io.
BibTeX
@inproceedings{shen-etal-2025-gear,
title = "{G}e{AR}: Graph-enhanced Agent for Retrieval-augmented Generation",
author = "Shen, Zhili and
Diao, Chenxin and
Vougiouklis, Pavlos and
Merita, Pascual and
Piramanayagam, Shriram and
Chen, Enting and
Graux, Damien and
Melo, Andre and
Lai, Ruofei and
Jiang, Zeren and
Li, Zhongyang and
Qi, Ye and
Ren, Yang and
Tu, Dandan and
Pan, Jeff Z.",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.624/",
doi = "10.18653/v1/2025.findings-acl.624",
pages = "12049--12072",
ISBN = "979-8-89176-256-5"
}