Recent breakthroughs in large language models (LLMs), particularly in reasoning capabilities, have propelled Retrieval-Augmented Generation (RAG) to unprecedented levels. By synergizing retrieval mechanisms with advanced reasoning, LLMs can now tackle increasingly complex problems. This paper presents a systematic review of the collaborative interplay between RAG and reasoning, clearly defining "reasoning" within the RAG context. It construct a comprehensive taxonomy encompassing multi-dimensional collaborative objectives, representative paradigms, and technical implementations, and analyze the bidirectional synergy methods. Additionally, we critically evaluate current limitations in RAG assessment, including the absence of intermediate supervision for multi-step reasoning and practical challenges related to cost-risk trade-offs. To bridge theory and practice, we provide practical guidelines tailored to diverse real-world applications. Finally, we identify promising research directions, such as graph-based knowledge integration, hybrid model collaboration, and RL-driven optimization. Overall, this work presents a theoretical framework and practical foundation to advance RAG systems in academia and industry, fostering the next generation of RAG solutions.
View on arXiv@article{gao2025_2504.15909,
title={ Synergizing RAG and Reasoning: A Systematic Review },
author={ Yunfan Gao and Yun Xiong and Yijie Zhong and Yuxi Bi and Ming Xue and Haofen Wang },
journal={arXiv preprint arXiv:2504.15909},
year={ 2025 }
}