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

2025-07-12

AI Summary

To address the limitations of retrieval-augmented generation (RAG) in multi-step reasoning and the factual unreliability and hallucination tendencies of pure reasoning models, this paper proposes RAG-Reasoning—a unified framework introducing a novel three-stage synergistic paradigm: (1) reasoning-enhanced RAG for targeted retrieval, (2) retrieval-enhanced reasoning for grounded factual support, and (3) agent-based iterative interaction for reflective refinement. The framework integrates multi-step reasoning, dynamic knowledge injection, agent-driven decision-making, and multimodal adaptation. It achieves state-of-the-art performance on multiple knowledge-intensive benchmarks—including HotpotQA, FEVER, and Musique. We publicly release Awesome-RAG-Reasoning, a curated open-source repository systematizing the technical landscape. This work significantly improves large language models’ factual accuracy, logical coherence, and trustworthiness in complex reasoning tasks, establishing a human-centered paradigm for deep, reliable reasoning systems.

Technology Category

• Knowledge Representation and Reasoning: Reasoning with Beliefs
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Enhancing RAG with multi-step reasoning for complex problems
• Reducing hallucinations in reasoning-oriented approaches with retrieved knowledge
• Developing synergistic RAG-reasoning frameworks for better performance

Innovation

• Advanced reasoning optimizes RAG stages
• Retrieved knowledge supplies missing premises
• Agentic LLMs interleave search and reasoning