Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
Year: 2025
Type: preprint
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-retrieval 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 reasoning 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. The collection is available at https://github.com/DavidZWZ/Awesome-RAG-Reasoning.
Source: arXiv (Cornell University)
Authors: Li, Yangning, Zhang, Weizhi, Yang, Yuyao, Huang, Wei-Chieh, Wu, Yaozu, Luo, Junyu, Bei, Yuanchen, Zou, Henry Peng, Luo, Xiao, Zhao, Yusheng, Chan, Chunkit, Chen, Yankai, Deng, Zhongfen, Li, Yinghui, Zheng, Hai-Tao, Li, Dongyuan, Jiang, Renhe, Zhang, Ming, Song, Yangqiu, Yu, Philip S.
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6891897994