# MobiAgent **Repository Path**: github-rocks/MobiAgent ## Basic Information - **Project Name**: MobiAgent - **Description**: The Intelligent GUI Agent for Mobile Phones - **Primary Language**: Unknown - **License**: Apache-2.0 - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2026-04-02 - **Last Updated**: 2026-04-08 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README
MobiAgent

MobiAgent: A Systematic Framework for Customizable Mobile Agents

| Paper | Huggingface | App |

English | 中文

--- ## About **MobiAgent** is a powerful and customizable mobile agent system including: * **An agent model family**: MobiMind * **An agent acceleration framework**: AgentRR * **An agent benchmark**: MobiFlow **System Architecture:**

## News - `[2025.8.30]`🔥 We've open-sourced the MobiAgent! ## Evaluation Results

## Demo Mobile App Demo:
AgentRR Demo (Left: first task; Right: subsequent task)
## Project Structure - `agent_rr/` - Agent Record & Replay framework - `collect/` - Data collection, annotation, processing and export tools - `runner/` - Agent executor that connects to phone via ADB, executes tasks, and records execution traces - `MobiFlow/` - Agent evaluation benchmark based on milestone DAG - `app/` - MobiAgent Android app - `deployment/` - Service deployment for MobiAgent mobile application ## Quick Start ### Use with MobiAgent APP If you would like to try MobiAgent directly with our APP, please download it in [Download Link](https://github.com/IPADS-SAI/MobiAgent/releases/tag/v1.0) and enjoy yourself! ### Use with Python Scripts If you would like to try MobiAgent with python scripts which leverage Android Debug Bridge (ADB) to control your phone, please follow these steps: #### Environment Setup Create virtual environment, e.g., using conda: ```bash conda create -n MobiMind python=3.10 conda activate MobiMind ``` Simplest environment setup (in case you want to run the agent runner alone, and do not want heavy dependencies like torch to be installed): ```bash # Install simplest dependencies pip install -r requirements_simple.txt ``` Full environment setup (in case you want to run the full pipeline): ```bash pip install -r requirements.txt # Download OmniParser model weights for f in icon_detect/{train_args.yaml,model.pt,model.yaml} ; do huggingface-cli download microsoft/OmniParser-v2.0 "$f" --local-dir weights; done # If you need GPU acceleration for OCR, install paddlepaddle-gpu according to your CUDA version # For details, refer to https://www.paddlepaddle.org.cn/install/quick, for example CUDA 11.8: python -m pip install paddlepaddle-gpu==3.1.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/ ``` #### Mobile Device Setup - Download and install [ADBKeyboard](https://github.com/senzhk/ADBKeyBoard/blob/master/ADBKeyboard.apk) on your Android device - Enable Developer Options on your Android device and allow USB debugging - Connect your phone to the computer using a USB cable #### Model Deployment After downloading the `decider`, `grounder`, and `planner` models, use vLLM to deploy model inference services: ```bash vllm serve IPADS-SAI/MobiMind-Decider-7B --port vllm serve IPADS-SAI/MobiMind-Grounder-3B --port vllm serve Qwen/Qwen3-4B-Instruct --port ``` #### Launch Agent Runner Write the list of tasks that you would like to test in `runner/mobiagent/task.json`, then launch agent runner: ```bash python -m runner.mobiagent.mobiagent --service_ip --decider_port --grounder_port --planner_port ``` Parameters: - `--service_ip`: Service IP (default: `localhost`) - `--decider_port`: Decider service port (default: `8000`) - `--grounder_port`: Grounder service port (default: `8001`) - `--planner_port`: Planner service port (default: `8002`) The runner automatically controls the device and invoke agent models to complete the pre-defined tasks. ## Detailed Sub-module Usage For detailed usage instructions, see the `README.md` files in each sub-module directory. ## Citation If you find MobiAgent useful in your research, please feel free to cite our [paper](https://arxiv.org/abs/2509.00531): ``` @misc{zhang2025mobiagentsystematicframeworkcustomizable, title={MobiAgent: A Systematic Framework for Customizable Mobile Agents}, author={Cheng Zhang and Erhu Feng and Xi Zhao and Yisheng Zhao and Wangbo Gong and Jiahui Sun and Dong Du and Zhichao Hua and Yubin Xia and Haibo Chen}, year={2025}, eprint={2509.00531}, archivePrefix={arXiv}, primaryClass={cs.MA}, url={https://arxiv.org/abs/2509.00531}, } ``` ## Acknowledgements We gratefully acknowledge the open-source projects like MobileAgent, UI-TARS, and Qwen-VL, etc. We also thank the National Innovation Institute of High-end Smart Appliances for their support of this project. ## Star History [![Star History Chart](https://api.star-history.com/svg?repos=IPADS-SAI/MobiAgent&type=Date)](https://www.star-history.com/#IPADS-SAI/MobiAgent&Date)