Tag
The paper proposes HybridCUA, a method that combines GUI and CLI interactions for computer-use agents, using a two-stage training framework with supervised fine-tuning and reinforcement learning to improve task accuracy and cross-platform generalizability.
This paper introduces CUActSpot, a multimodal benchmark for evaluating computer-use agents, and a renderer-based data synthesis pipeline. The proposed Phi-Ground-Any-4B model outperforms open-source models under 32B parameters.