How Smart Is Your GUI Agent? A Framework for the Future of Software Interaction
This work addresses the problem of ambiguous agent capabilities and risks for researchers and developers in human-computer interaction and AI, though it is incremental as it builds on existing concepts without introducing new methods or data.
The paper tackles the lack of clarity in defining GUI agent autonomy by proposing the GUI Agent Autonomy Levels (GAL) framework, a six-level system to explicitly categorize autonomy and benchmark progress toward trustworthy software interaction.
GUI agents are rapidly becoming a new interaction to software, allowing people to navigate web, desktop and mobile rather than execute them click by click. Yet ``agent'' is described with radically different degrees of autonomy, obscuring capability, responsibility and risk. We call for conceptual clarity through GUI Agent Autonomy Levels (GAL), a six-level framework that makes autonomy explicit and helps benchmark progress toward trustworthy software interaction.