Note AGUVIS is a unified pure vision-based framework for autonomous GUI agents that can operate across various platforms (web, desktop, mobile). Unlike previous approaches that rely on textual representations, AGUVIS leverages unified purely vision-based observations and a consistent action space to ensure better generalization across different platforms.

Note AGUVIS data collection stage 1 computer/mobile grounding data.

Note AGUVIS data collection stage 2 computer/mobile/desktop trajectory data.