ARPO_UITARS1.5_7B
Trained with ARPO (Agentic Replay Policy Optimization) on OSWorld benchmark
[Paper] • [Code] • [Logs]
Model Summary
ARPO_UITARS1.5_7B is fine-tuned from UI-Tars-1.5-7B using Agentic Replay Policy Optimization (ARPO) on the OSWorld benchmark for GUI agents.
📊 Performance
| Model | OSWorld (128 Tasks) | OSWorld Overall |
|---|---|---|
| UI-Tars-1.5 | 68.7% | 23.5% |
| UI-Tars-1.5 + GRPO | 72.9% | 26.0% |
| UI-Tars-1.5 + ARPO (Ours) | 83.9% | 29.9% |
Evaluation setting: max 15 steps per trajectory.
📝 Citation
If you use this model in your work, please cite:
@article{lu2025arpo,
title={ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay},
author={Fanbin Lu and Zhisheng Zhong and Shu Liu and Chi-Wing Fu and Jiaya Jia},
journal={arxiv},
year={2025}
}