@inproceedings{takeshita-etal-2026-a11y,
    title = "A11y-Compressor: A Framework for Enhancing the Efficiency of {GUI} Agent Observations through Visual Context Reconstruction and Redundancy Reduction",
    author = "Takeshita, Michito  and
      Kawada, Takuro  and
      Ohashi, Takumi  and
      Kitada, Shunsuke  and
      Iyatomi, Hitoshi",
    editor = "T.Y.S.S., Santosh  and
      Rodriguez, Juan Diego  and
      de Gibert, Ona",
    booktitle = "Proceedings of the 64th Annual Meeting 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.acl-srw.50/",
    pages = "563--580",
    ISBN = "979-8-89176-393-7",
    abstract = "AI agents that interact with graphical user interfaces (GUIs) require effective observation representations for reliable grounding.The accessibility tree is a commonly used text-based format that encodes UI element attributes, but it suffers from redundancy and lacks structural information such as spatial relationships among elements.We propose A11y-Compressor, a framework that transforms linearized accessibility trees into compact and structured representations.Our implementation, Compressed-a11y, applies a lightweight and structured transformation pipeline with modal detection, redundancy reduction, and semantic structuring.Experiments on the OSWorld benchmark show that Compressed-a11y reduces input tokens to 22{\%} of the original while improving task success rates by 5.1 percentage points on average."
}