Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs

TL;DR

This survey reviews recent advances in RAG-Reasoning systems in LLMs, emphasizing the integration of reasoning and retrieval to improve complex inference, performance, and trustworthiness.

Contribution

It provides a unified perspective on RAG-Reasoning frameworks, categorizes methods and datasets, and outlines future research directions for more effective and trustworthy systems.

Findings

Emerging agentic RAG frameworks achieve state-of-the-art results.

Retrieval of different knowledge types enhances complex inference.

Unified reasoning-retrieval perspective improves system effectiveness.

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.