This repository contains the code and data for the paper OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis.
We are uploading the data and checkpoints. Due to bandwidth limitations, this will take some time. Stay tuned!
We introduce OS-Genesis, an interaction-driven pipeline for synthesizing high-quality and diverse GUI agent trajectory data without human supervision or predefined tasks. By leveraging reverse task synthesis and a trajectory reward model, OS-Genesis enables effective end2end training of GUI agents.
For details and operations of the training, please refer to the InternVL2 documentation and Qwen2-VL.
To evaluate the AndroidControl Benchmark, please follow the steps below:
-
Clone the GitHub Repository:
git clone https://github.com/OS-Copilot/OS-Genesis.git
-
Inference:
cd OS-Genesis/evaluation/android_control bash run_ac_inference.sh $dataset $checkpoint
-
Evaluation:
pyhton ac_eval.py
Model Name | Base Model | Training Data | HF Link |
---|---|---|---|
OS-Genesis-4B-AC | InternVL2-4B | OS-Genesis-ac-training-data | 🤗 link |
OS-Genesis-7B-AC | Qwen2-VL-7B-Instruct | OS-Genesis-ac-training-data | 🤗 link |
OS-Genesis-8B-AC | InternVL2-8B | OS-Genesis-ac-training-data | 🤗 link |
Model Name | Base Model | Training Data | HF Link |
---|---|---|---|
OS-Genesis-4B-AW | InternVL2-4B | OS-Genesis-aw-training-data | 🤗 link |
OS-Genesis-7B-AW | Qwen2-VL-7B-Instruct | OS-Genesis-aw-training-data | 🤗 link |
OS-Genesis-8B-AW | InternVL2-8B | OS-Genesis-aw-training-data | 🤗 link |
Model Name | Base Model | Training Data | HF Link |
---|---|---|---|
OS-Genesis-4B-WA | InternVL2-4B | OS-Genesis-web-training-data | 🤗 link |
OS-Genesis-7B-WA | Qwen2-VL-7B-Instruct | OS-Genesis-web-training-data | 🤗 link |
OS-Genesis-8B-WA | InternVL2-8B | OS-Genesis-web-training-data | 🤗 link |
We have collected some questions from emails, Hugging Face, and WeChat communications. Please check the FAQ 🤖
🫶 If you are interested in our work or find this repository / our data helpful, please consider using the following citation format when referencing our paper:
@article{sun2024genesis,
title={OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis},
author={Sun, Qiushi and Cheng, Kanzhi and Ding, Zichen and Jin, Chuanyang and Wang, Yian and Xu, Fangzhi and Wu, Zhenyu and Jia, Chengyou and Chen, Liheng and Liu, Zhoumianze and others},
journal={arXiv preprint arXiv:2412.19723},
year={2024}
}