AgentGUI: An Interface for Observing and Steering Long-Running AI Agents

Researchers introduced AgentGUI, a locally hosted graphical interface for observing and steering long-running AI agents across multiple concurrent sessions, achieving a 38% faster identification of key elements from agent traces in a controlled user study (p = 0.023). The tool's automated drift prevention feature raised task completion rates by up to 34 percentage points for small local agents across a 0.8B–9B model ladder (N=50 runs per model). AgentGUI is publicly available via its project website and open-source repository.

arXiv:2607.26300v1 Announce Type: new Abstract: AI agents are increasingly adept at tackling complex, long-running tasks. With the rapid surge of autonomous capabilities, human oversight is systematically lagging behind due to limited human-centered interfacing. Aiming to address this, we introduce AgentGUI, a user-friendly, locally hosted GUI for seamlessly observing and steering AI agents amid multiple concurrent, long-running sessions. AgentGUI features 1 rich agent trajectory visualizations, 2 effective manual and automated steering, and 3 integration with and coordination between open-source and frontier agent frameworks. A controlled user study demonstrates statistically significant reduction in the time it takes to identify key elements from agent traces 38% faster, p = 0.023 . In a preliminary experiment, AgentGUI's automated drift prevention feature raises the task completion rate of small local agents by as high as 34pp across a 0.8B--9B model ladder N=50 runs per model . AgentGUI is publicly available through its project website https://agent-gui-project.github.io and open-source repository https://github.com/eth-medical-ai-lab/agent-gui , along with a demo video https://youtube.com/watch?v=GSDyxN1gTF0 .