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 GeAR, 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 GeAR'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.
@article{arxiv.2412.18431,
title = {GeAR: Graph-enhanced Agent for Retrieval-augmented Generation},
author = {Zhili Shen and Chenxin Diao and Pavlos Vougiouklis and Pascual Merita and Shriram Piramanayagam and Enting Chen and Damien Graux and Andre Melo and Ruofei Lai and Zeren Jiang and Zhongyang Li and YE QI and Yang Ren and Dandan Tu and Jeff Z. Pan},
journal= {arXiv preprint arXiv:2412.18431},
year = {2025}
}