A Survey of RAG-Reasoning Systems in Large Language Models
Yangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu, Junyu Luo, Yuanchen Bei, Henry Peng Zou
Abstract
Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts. This survey synthesizes both strands under a unified reasoning-search perspective. We first map how advanced reasoning optimizes each stage of RAG (Reasoning-Enhanced RAG). Then, we show how retrieved knowledge of different type supply missing premises and expand context for complex inference (RAG-Enhanced Reasoning). Finally, we spotlight emerging Synergized RAG-Reasoning frameworks, where (agentic) LLMs iteratively interleave search and thought to achieve state-of-the-art performance across knowledge-intensive benchmarks. We categorize methods, datasets, and open challenges, and outline research avenues toward deeper RAG-Reasoning systems that are more effective, multimodally-adaptive, trustworthy, and human-centric.
BibTeX
@inproceedings{emnlp2025_asurveyofragreas,
title = {A Survey of RAG-Reasoning Systems in Large Language Models},
author = {Yangning Li and Weizhi Zhang and Yuyao Yang and Wei-Chieh Huang and Yaozu Wu and Junyu Luo and Yuanchen Bei and Henry Peng Zou and Xiao Luo and Yusheng Zhao and Chunkit Chan and Yankai Chen and Zhongfen Deng and Yinghui Li and Hai-Tao Zheng and Dongyuan Li and Renhe Jiang and Ming Zhang and Yangqiu Song and Philip S. Yu},
booktitle = {EMNLP 2025},
year = {2025}
}