SOURCE-LINKED INTELLIGENCE
STP-GUI: Spatially-Aware Token Pruning for Efficient Web-GUI Agents
With the rapid development of vision-language models (VLMs), Web-GUI agents have achieved promising performance in interacting with real-world interfaces through screenshot-based grounding. However, high-resolution screenshots and multi-turn histories introduce excessive visual tokens, causing substantial inference overhead. Existing token pruning methods, mainly designed for natural images, often select tokens independently based on importance scores, which can fragment the local visual structures required for recognizing small GUI elements such as buttons, icons, and hyperlinks. In this work
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-14T15:53:48.000Z
First collected: 2026-10-15T15:42:31.647Z. This is not the publication date.