Bibliographic Details
| Title: |
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis |
| Authors: |
Sun, Qiushi, Cheng, Kanzhi, Ding, Zichen, Jin, Chuanyang, Wang, Yian, Xu, Fangzhi, Wu, Zhenyu, Jia, Chengyou, Chen, Liheng, Liu, Zhoumianze, Kao, Ben, Li, Guohao, He, Junxian, Qiao, Yu, Wu, Zhiyong |
| Publication Year: |
2024 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Human-Computer Interaction |
| More Details: |
Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability. Despite their utility in advancing digital automation, a critical bottleneck persists: collecting high-quality trajectory data for training. Common practices for collecting such data rely on human supervision or synthetic data generation through executing pre-defined tasks, which are either resource-intensive or unable to guarantee data quality. Moreover, these methods suffer from limited data diversity and significant gaps between synthetic data and real-world environments. To address these challenges, we propose OS-Genesis, a novel GUI data synthesis pipeline that reverses the conventional trajectory collection process. Instead of relying on pre-defined tasks, OS-Genesis enables agents first to perceive environments and perform step-wise interactions, then retrospectively derive high-quality tasks to enable trajectory-level exploration. A trajectory reward model is then employed to ensure the quality of the generated trajectories. We demonstrate that training GUI agents with OS-Genesis significantly improves their performance on highly challenging online benchmarks. In-depth analysis further validates OS-Genesis's efficiency and its superior data quality and diversity compared to existing synthesis methods. Our codes, data, and checkpoints are available at \href{https://qiushisun.github.io/OS-Genesis-Home/}{OS-Genesis Homepage}.
Comment: Work in progress |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2412.19723 |
| Accession Number: |
edsarx.2412.19723 |
| Database: |
arXiv |
