How Smart Is Your GUI Agent? A Framework for the Future of Software Interaction
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). First posted on arXiv 12 Feb 2026.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024GUI Agents: A Survey
- 2024The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use
- 2025GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration
- 2026OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution
- 2026Software Engineering for and with GUI Agent
- 2025Computer-Use Agents as Judges for Generative User Interface
- 2025Mobile-Agent-v3: Fundamental Agents for GUI Automation
- 2026WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments