Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
Abstract
This survey integrates reasoning and retrieval in Large Language Models to improve factuality and multi-step inference, highlighting Synergized RAG-Reasoning frameworks and outlining future research directions.
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.
Community
Despite both enhancing LLMs, π naive RAG and π§ pure reasoning have historically developed independently within separate communities, each with distinct baselines and corresponding limitations. Our survey, accompanied by the GitHub repository, bridges these two domains by compiling essential resources, including papers, datasets, and open-source implementations, for researchers and practitioners. π π π
π₯ π₯ π₯ The github repo is available at https://github.com/DavidZWZ/Awesome-RAG-Reasoning.
π€ As a more agent-focused extension, we highlight the paradigm shift in information searchβfrom traditional web search to Agentic Deep Research, where autonomous agents iteratively search, reason, and synthesize information to tackle complex tasks.
π Paper: https://arxiv.org/abs/2506.18959
π GitHub: https://github.com/DavidZWZ/Awesome-Deep-Research
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper