Awesome

<div align="center"> <h3>Mobile-Agent: The Powerful Mobile Device Operation Assistant Family<h3> <div align="center"> <a href="https://huggingface.co/spaces/junyangwang0410/Mobile-Agent"><img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm-dark.svg" alt="Open in Spaces"></a> <a href="https://modelscope.cn/studios/wangjunyang/Mobile-Agent-v2"><img src="assets/Demo-ModelScope-brightgreen.svg" alt="Demo ModelScope"></a> <a href="https://arxiv.org/abs/2401.16158"><img src="https://img.shields.io/badge/Arxiv-2401.16158-b31b1b.svg?logo=arXiv" alt=""></a> <a href="https://arxiv.org/abs/2406.01014 "><img src="https://img.shields.io/badge/Arxiv-2406.01014-b31b1b.svg?logo=arXiv" alt=""></a> </div> <p align="center"> <a href="https://trendshift.io/repositories/7423" target="_blank"><img src="https://trendshift.io/api/badge/repositories/7423" alt="MobileAgent | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> </p> </div> <div align="center"> <a href="README.md">English</a> | <a href="README_zh.md">简体中文</a> | <a href="README_ja.md">日本語</a> <hr> </div>

📺Demo

Mobile-Agent-v3 (Note: The video is not accelerated)

YouTube

Bilibili

PC-Agent

Chrome and DingTalk

https://github.com/user-attachments/assets/b890a08f-8a2f-426d-9458-aa3699185030

Word

https://github.com/user-attachments/assets/37f0a0a5-3d21-4232-9d1d-0fe845d0f77d

Mobile-Agent-v2

https://github.com/X-PLUG/MobileAgent/assets/127390760/d907795d-b5b9-48bf-b1db-70cf3f45d155

Mobile-Agent

https://github.com/X-PLUG/MobileAgent/assets/127390760/26c48fb0-67ed-4df6-97b2-aa0c18386d31

📢News

🔥🔥[9.26] Mobile-Agent-v2 has been accepted by The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024).
🔥[8.23] We proposed PC-Agent, a PC operation assistant supporting both Mac and Windows platforms.
🔥[7.29] Mobile-Agent won the best demo award at the The 23rd China National Conference on Computational Linguistics (CCL 2024). On the CCL 2024, we displayed the upcoming Mobile-Agent-v3. It has smaller memory overhead (8 GB), faster reasoning speed (10s-15s per operation), and all uses open source models. Video demo, please see the last section 📺Demo.
[6.27] We proposed Demo that can upload mobile phone screenshots to experience Mobile-Agent-V2 in Hugging Face and ModelScope. You don’t need to configure models and devices, and you can experience it immediately.
[6. 4] Modelscope-Agent has supported Mobile-Agent-V2, based on Android Adb Env, please check in the application.
[6. 4] We proposed Mobile-Agent-v2, a mobile device operation assistant with effective navigation via multi-agent collaboration.
[3.10] Mobile-Agent has been accepted by the ICLR 2024 Workshop on Large Language Model (LLM) Agents.

📱Version

Mobile-Agent-v3
Mobile-Agent-v2 - Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
Mobile-Agent - Autonomous Multi-Modal Mobile Device Agent with Visual Perception

⭐Star History

📑Citation

If you find Mobile-Agent useful for your research and applications, please cite using this BibTeX:

@article{wang2024mobile2,
  title={Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration},
  author={Wang, Junyang and Xu, Haiyang and Jia, Haitao and Zhang, Xi and Yan, Ming and Shen, Weizhou and Zhang, Ji and Huang, Fei and Sang, Jitao},
  journal={arXiv preprint arXiv:2406.01014},
  year={2024}
}

@article{wang2024mobile,
  title={Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception},
  author={Wang, Junyang and Xu, Haiyang and Ye, Jiabo and Yan, Ming and Shen, Weizhou and Zhang, Ji and Huang, Fei and Sang, Jitao},
  journal={arXiv preprint arXiv:2401.16158},
  year={2024}
}