@inproceedings{hu-etal-2026-flowsearch,
    title = "{F}low{S}earch: Advancing Deep Research with Dynamic Structured Knowledge Flow",
    author = "Hu, Yusong  and
      Ma, Runmin  and
      Fan, Yue  and
      Shi, Jinxin  and
      Cao, Zongsheng  and
      Zhou, Yuhao  and
      Yuan, Jiakang  and
      Zhang, Shuaiyu  and
      Feng, Shiyang  and
      Yan, Xiangchao  and
      Zhang, Shufei  and
      Zhang, Wenlong  and
      Bai, Lei  and
      Zhang, Bo",
    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.971/",
    pages = "21212--21245",
    ISBN = "979-8-89176-390-6",
    abstract = "Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-step dependencies, which presents substantial challenges for agentic systems. To address this, we propose FlowSearch, a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning. FlowSearch is capable of strategically planning and expanding the knowledge flow to enable parallel exploration and hierarchical task decomposition, while also adjusting the knowledge flow in real time based on feedback from intermediate reasoning outcomes and insights. FlowSearch achieves competitive performance on both general and scientific benchmarks, including GAIA, HLE, GPQA and TRQA, demonstrating its effectiveness in multi-disciplinary research scenarios and its potential to advance scientific discovery. The code will be available."
}