@inproceedings{li-etal-2025-survey,
    title = "A Survey of {RAG}-Reasoning Systems in Large Language Models",
    author = "Li, Yangning  and
      Zhang, Weizhi  and
      Yang, Yuyao  and
      Huang, Wei-Chieh  and
      Wu, Yaozu  and
      Luo, Junyu  and
      Bei, Yuanchen  and
      Zou, Henry Peng  and
      Luo, Xiao  and
      Zhao, Yusheng  and
      Chan, Chunkit  and
      Chen, Yankai  and
      Deng, Zhongfen  and
      Li, Yinghui  and
      Zheng, Hai-Tao  and
      Li, Dongyuan  and
      Jiang, Renhe  and
      Zhang, Ming  and
      Song, Yangqiu  and
      Yu, Philip S.",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.648/",
    doi = "10.18653/v1/2025.findings-emnlp.648",
    pages = "12120--12145",
    ISBN = "979-8-89176-335-7",
    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-search 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 thought 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."
}