@inproceedings{xu-etal-2025-rar2,
    title = "{RAR}$^2$: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval",
    author = "Xu, Kaishuai  and
      Hou, Wenjun  and
      Cheng, Yi  and
      Li, Wenjie",
    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.1110/",
    doi = "10.18653/v1/2025.findings-emnlp.1110",
    pages = "20386--20396",
    ISBN = "979-8-89176-335-7",
    abstract = "Large Language Models (LLMs) have shown promising performance on diverse medical benchmarks, highlighting their potential in supporting real-world clinical tasks. Retrieval-Augmented Generation (RAG) has emerged as a key approach for mitigating knowledge gaps and hallucinations by incorporating external medical information. However, RAG still struggles with complex medical questions that require intensive reasoning, as surface-level input often fails to reflect the true knowledge needs of the task. Existing methods typically focus on refining queries without explicitly modeling the reasoning process, limiting their ability to retrieve and integrate clinically relevant knowledge. In this work, we propose RAR$^2$, a joint learning framework that improves both Reasoning-Augmented Retrieval and Retrieval-Augmented Reasoning. RAR$^2$ constructs a thought process to uncover implicit knowledge requirements and uses it to guide retrieval and answer generation. We build a training dataset of mixed preference pairs and apply Direct Preference Optimization (DPO) to train the model. Moreover, we design two test-time scaling strategies to explore the boundaries of our framework. Experiments demonstrate the effectiveness of RAR$^2$ across several biomedical question answering datasets, outperforming RAG baselines with or without fine-tuning."
}