UITARS prompt for visual grounding only

[tcnguyen]

Currently the prompt need a task description and action history. If I want to use UITARS for visual grounding only, is this possible? What is the prompt you used for visual grounding benchmarking? Thank you.

[JjjFangg]

Here are an example of visual grounding task.

"""You are a GUI agent. You are given a task and your action history, with screenshots. You need to perform the next action to complete the task. \n\n## Output Format\n\nAction: ...\n\n\n## Action Space\nclick(start_box='<|box_start|>(x1,y1)<|box_end|>')\n\n## User Instruction\n{instruction} """

[tcnguyen]

@JjjFangg Thank you!