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

Yangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu +15 more
7/13/2025
cs.CLcs.AI

Official code: DavidZWZ/Awesome-RAG-Reasoning (459 stars, MIT, last commit 2026-01-25).

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.

View on arXivView PDF

Code Implementations(1)

DavidZWZ/Awesome-RAG-ReasoningOfficial100%
MIT

[EMNLP 2025] Awesome RAG Reasoning Resources

45943Jun 18, 20258 months agoMIT
agentagentic-aiagentic-ragllmllms+5 more

Similar Papers

RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning

90% match2025

A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning

89% match2024

RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems

89% match2025

How Much Can RAG Help the Reasoning of LLM?

89% match2024

Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models

88% match1 repo1472024

MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning

88% match2025

Cite this paper

@article{li2025towards,
  title  = {Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs},
  author = {Yangning Li and Weizhi Zhang and Yuyao Yang and Wei-Chieh Huang and Yaozu Wu and Junyu Luo and Yuanchen Bei and Henry Peng Zou and Xiao Luo and Yusheng Zhao and Chunkit Chan and Yankai Chen and Zhongfen Deng and Yinghui Li and Hai-Tao Zheng and Dongyuan Li and Renhe Jiang and Ming Zhang and Yangqiu Song and Philip S. Yu},
  year   = {2025},
  eprint = {2507.09477},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.09477v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.09477.svg)](https://codeofpaper.com/paper/2507.09477)

Discussion