@inproceedings{jin-etal-2026-slideagent,
    title = "{S}lide{A}gent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding",
    author = "Jin, Yiqiao  and
      Kaur, Rachneet  and
      Zeng, Zhen  and
      Ganesh, Sumitra  and
      Kumar, Srijan",
    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.677/",
    pages = "14858--14881",
    ISBN = "979-8-89176-390-6",
    abstract = "Multi-page visual documents such as manuals, brochures, presentations, and posters convey key information through layout, colors, icons, and cross-slide references. While multimodal large language models (MLLMs) offer opportunities in document understanding, current systems struggle with complex, multi-page visual documents, particularly in fine-grained reasoning over elements and pages. We introduce SlideAgent, a versatile agentic framework for understanding multi-modal, multi-page, and multi-layout documents, especially slide decks. SlideAgent employs specialized agents and decomposes reasoning into three specialized levels{--}global, page, and element{--}to construct a structured, query-agnostic representation that captures both overarching themes and detailed visual or textual cues. During inference, SlideAgent selectively activates specialized agents for multi-level reasoning and integrates their outputs into coherent, context-aware answers.Extensive experiments show that SlideAgent significantly improves accuracy over both proprietary (+7.9{\%}) and open-source models (+9.8{\%})."
}