@inproceedings{huang-etal-2026-deep,
    title = "Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety",
    author = "Huang, Wei-Chieh  and
      Zou, Henry Peng  and
      Wu, Yaozu  and
      Li, Dongyuan  and
      Chen, Yankai  and
      Zhang, Weizhi  and
      Li, Yangning  and
      Zangari, Angelo  and
      Guo, Jizhou  and
      Miao, Chunyu  and
      Fang, Liancheng  and
      He, Langzhou  and
      Li, Yinghui  and
      Jiang, Renhe  and
      Yu, Philip S.",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2010/",
    pages = "43403--43446",
    ISBN = "979-8-89176-390-6",
    abstract = "Deep research frameworks have shown promising capabilities in synthesizing comprehensive reports from web sources. While deep research possesses significant potential to address complex issues through planning and research cycles, existing frameworks are deficient in sufficient evaluation procedures and stage-specific protections. They typically treat evaluation as exact match accuracy of question-answering, but overlook crucial aspects of report quality such as credibility, coherence, breadth, depth, and safety. This oversight may result in hazardous or malicious sources being integrated into the final report. To address this, we introduce DeepResearchGuard, a framework featuring four-stage safeguards with open-domain evaluation, and DRSafeBench, a novel stage-wise safety benchmark. Evaluating across GPT-4o, o4-mini, Gemini-2.5-flash, DeepSeek-v3, and GPT-5, DeepResearchGuard improves defense success rates by an absolute 16.53{\%} while reducing over-refusal rates to approximately 6{\%}. Through extensive experiments, we show that DeepResearchGuard enables comprehensive open-domain evaluation and stage-aware defenses that effectively block harmful content propagation, while systematically improving report quality without excessive over-refusal rates."
}