@inproceedings{wang-etal-2026-deepmed,
    title = "{D}eep{M}ed: Building a Medical {D}eep{R}esearch Agent via Multi-hop {M}ed-Search Data and Turn-Controlled Agentic Training {\&} Inference",
    author = "Wang, Zihan  and
      Wang, Hao  and
      Feng, Shi  and
      Yang, Xiaocui  and
      Wang, Daling  and
      Zhang, Yiqun  and
      Lin, Jinghao  and
      Ji, Xiaozhong  and
      Yang, Haihua",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.904/",
    pages = "18160--18178",
    ISBN = "979-8-89176-395-1",
    abstract = "Medical reasoning models remain constrained by parametric knowledge and are thus susceptible to forgetting and hallucinations. DeepResearch (DR) models ground outputs in verifiable evidence from tools and perform strongly in general domains, but their direct transfer to medical field yields relatively limited gains. We attribute this to two gaps: task characteristic and tool-use scaling. Medical questions require evidence interpretation in a knowledge-intensive clinical context; while general DR models can retrieve information, they often lack clinical-context reasoning and thus ``find it but fail to use it,'' leaving performance limited by medical abilities. Moreover, in medical scenarios, blindly scaling tool-call can inject noisy context, derailing sensitive medical reasoning and prompting repetitive evidence-seeking along incorrect paths. Therefore, we propose DeepMed. For data, we deploy a multi-hop med-search QA synthesis method supporting the model to apply the DR paradigm in medical contexts. For training, we introduce a difficulty-aware turn-penalty to suppress excessive tool-call growth. For inference, we bring a monitor to help validate hypotheses within a controlled number of steps and avoid context rot. Overall, on seven medical benchmarks, DeepMed improves its base model by 9.79{\%} on average and outperforms larger medical reasoning and DR models."
}