A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction
Michito Takeshita, Takuro Kawada, Takumi Ohashi, Shunsuke Kitada, Hitoshi Iyatomi
TLDR
A11y-Compressor enhances GUI agent efficiency by compressing accessibility trees, reducing tokens by 78% and boosting task success.
Key contributions
- Transforms redundant accessibility trees into compact, structured GUI observations.
- A11y-Compressor uses modal detection, redundancy reduction, and semantic structuring.
- Reduces input tokens by 78% while improving GUI agent task success by 5.1%.
Why it matters
Effective GUI observation representations are crucial for reliable AI agents. This paper introduces a novel framework that significantly improves efficiency and performance by structuring and compressing existing accessibility data. This advancement makes GUI agents more robust and practical.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.