ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Yikuan, Zhu, Jifeng, Tang, Lanrui, Huang, Chen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914095906684928
author Hu, Yikuan
Zhu, Jifeng
Tang, Lanrui
Huang, Chen
author_facet Hu, Yikuan
Zhu, Jifeng
Tang, Lanrui
Huang, Chen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13193
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
Hu, Yikuan
Zhu, Jifeng
Tang, Lanrui
Huang, Chen
Information Retrieval
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.
title ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
topic Information Retrieval
url https://arxiv.org/abs/2510.13193