AI RESEARCH
Adaptive Vision-Language Model Routing for Computer Use Agents
arXiv CS.CL
•
ArXi:2603.12823v1 Announce Type: new Computer Use Agents (CUAs) translate natural-language instructions into Graphical User Interface (GUI) actions such as clicks, keystrokes, and scrolls by relying on a Vision-Language Model (VLM) to interpret screenshots and predict grounded tool calls. However, grounding accuracy varies dramatically across VLMs, while current CUA systems typically route every action to a single fixed model regardless of difficulty.