ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
Yikuan Hu, Jifeng Zhu, Lanrui Tang, Chen Huang
Abstract
Knowledge graphs (KGs), with their structured representation capabilities, offer promising avenue for enhancing Retrieval Augmented Generation (RAG) systems, leading to the development of KG-RAG systems. Nevertheless, existing methods often struggle to achieve effective synergy between system effectiveness and cost efficiency, leading to neither unsatisfying performance nor excessive LLM prompt tokens and inference time. To this end, this paper proposes REMINDRAG, which employs an LLM-guided graph traversal featuring node exploration, node exploitation, and, most notably, memory replay, to improve both system effectiveness and cost efficiency. Specifically, REMINDRAG memorizes traversal experience within KG edge embeddings, mirroring the way LLMs "memorize" world knowledge within their parameters, but in a train-free manner. We theoretically and experimentally confirm the effectiveness of REMINDRAG, demonstrating its superiority over existing baselines across various benchmark datasets and LLM backbones. Our code is available at https://github.com/kilgrims/ReMindRAG.
BibTeX
@inproceedings{
hu2025remindrag,
title={ReMind{RAG}: Low-Cost {LLM}-Guided Knowledge Graph Traversal for Efficient {RAG}},
author={Yikuan Hu and Jifeng Zhu and Lanrui Tang and Chen Huang},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=JnKfAqLJb4}
}