Datasets:
video_id string | step int32 | system string | user string | assistant string | image image |
|---|---|---|---|---|---|
video_001 | 0 | You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task.
CRITICAL: You MUST ONLY use these EXACT function names and signatures:
<c... | Please generate the next move according to the UI screenshot and expected workflow.
Expected Workflow:
Complete the following workflow:
Step 1: open_url(url="https://www.linkedin.com/")
Step 2: click(element_description="Start a post button")
Step 3: type_text(element_description="post text area", text="Are you passi... | <think>
Step 2: Start a post button (from DOM ground truth with perfect frame alignment)
</think>
<code>
click(0.036, 0.014, " 0a53ac55")
</code> | |
video_001 | 1 | You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task.
CRITICAL: You MUST ONLY use these EXACT function names and signatures:
<c... | Please generate the next move according to the UI screenshot and expected workflow.
Expected Workflow:
Complete the following workflow:
Step 1: open_url(url="https://www.linkedin.com/")
Step 2: click(element_description="Start a post button")
Step 3: type_text(element_description="post text area", text="Are you passi... | <think>
Step 4: Post button (from DOM ground truth with perfect frame alignment)
</think>
<code>
click(0.231, 0.072, "aria")
</code> |
UI Automation Dataset (Multi-Video)
2 examples from 1 videos - UI automation tasks from screen recordings.
Dataset Structure
Each entry contains:
- video_id: Sequential ID for each video (video_001, video_002, etc.)
- step: Step number within that video (0, 1, 2, ...)
- system: System prompt for the GUI agent
- user: Task instruction + previous actions
- assistant: Model's reasoning and action
- image: Screenshot of the UI state
Usage
from datasets import load_dataset
ds = load_dataset("KMH158-QLU/recruiter_perfect2")
# Access by video
for video_id in set(ds['train']['video_id']):
video_data = ds['train'].filter(lambda x: x['video_id'] == video_id)
print(f"Video {video_id}: {len(video_data)} steps")
# Or iterate all examples
for item in ds['train']:
print(f"{item['video_id']} - Step {item['step']}: {item['assistant'][:50]}...")
Growing Dataset
This dataset supports multiple videos. Each video gets a unique ID (video_001, video_002, etc.). New videos are automatically appended with the next available ID.
- Downloads last month
- 11