@inproceedings{li-etal-2026-sudokufill,
    title = "{S}udoku{F}ill: A Multi-Agent Progressive Filling Framework for Document-Level Scientific Information Extraction",
    author = "Li, Yang  and
      Wang, Yajiao  and
      Zhang, Yu  and
      Zhang, Yuanzhe  and
      Hu, Maodi  and
      Zhang, Mengting  and
      Sun, Xi  and
      Yue, Hua  and
      Zhang, Zhixiong",
    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.1657/",
    pages = "33112--33138",
    ISBN = "979-8-89176-395-1",
    abstract = "Scientific information extraction (SciIE) is a key bottleneck for turning unstructured papers into computable knowledge bases, yet most existing systems still follow a ``local extraction then global assembly'' paradigm. This workflow is inherently lossy: by extracting fields in isolation, it breaks global correlations and discards high-confidence signals that could otherwise be reused as internal supervision, forcing systems to repeatedly restart from scratch, especially in long, multimodal scientific documents. In this paper, We propose a different view: SciIE should be solved as a progressive filling problem, similar to solving a Sudoku,once a field is filled with high confidence, it should act as a constraint that guides the remaining uncertain fields. Based on this idea, we introduce SudokuFill, a multi-agent framework that maintains a Global Filling State and performs priority scheduling to establish reliable anchors first, then reuses them as internal supervision for iterative deliberation over harder fields. Evaluated on a specialized document-level adjuvant dataset, our framework achieves a SOTA score of 51.83{\%} on our benchmark. Crucially, SudokuFill enables a 7B model to outperform the vanilla GPT-4o, proving that structured architectural reasoning can effectively compensate for parameter scale."
}