Kyle Qiao

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents

This paper proposes ToolCUA, an end-to-end agent designed to learn optimal GUI-Tool path selection through a staged training paradigm, and introduces an Interleaved GUI-Tool Trajectory Scaling Pipeline that repurposes abundant static GUI trajectories and synthesizes a grounded tool library, enabling diverse GUI-Tool tr...