|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
pipeline_tag: image-text-to-text |
|
|
tags: |
|
|
- multimodal |
|
|
- gui |
|
|
--- |
|
|
|
|
|
# MobiMind-Decider-7B Model |
|
|
|
|
|
This is the Decider Model of [MobiAgent](https://github.com/IPADS-SAI/MobiAgent) with 7B parameters, as presented in the paper [MobiAgent: A Systematic Framework for Customizable Mobile Agents](https://huggingface.co/papers/2509.00531), capable of high-level GUI interaction decision in GUI agent task execution. |
|
|
|
|
|
## Paper Abstract |
|
|
|
|
|
With the rapid advancement of Vision-Language Models (VLMs), GUI-based mobile agents have emerged as a key development direction for intelligent mobile systems. However, existing agent models continue to face significant challenges in real-world task execution, particularly in terms of accuracy and efficiency. To address these limitations, we propose MobiAgent, a comprehensive mobile agent system comprising three core components: the MobiMind-series agent models, the AgentRR acceleration framework, and the MobiFlow benchmarking suite. Furthermore, recognizing that the capabilities of current mobile agents are still limited by the availability of high-quality data, we have developed an AI-assisted agile data collection pipeline that significantly reduces the cost of manual annotation. Compared to both general-purpose LLMs and specialized GUI agent models, MobiAgent achieves state-of-the-art performance in real-world mobile scenarios. |
|
|
|
|
|
## About MobiAgent |
|
|
|
|
|
**MobiAgent** is a powerful mobile agent system including: |
|
|
|
|
|
* **An agent model family**: MobiMind |
|
|
* **An agent acceleration framework**: AgentRR |
|
|
* **An agent benchmark**: MobiFlow |
|
|
|
|
|
**System Architecture:** |
|
|
|
|
|
<div align="center"> |
|
|
<p align="center"> |
|
|
<img src="https://raw.githubusercontent.com/IPADS-SAI/MobiAgent/main/assets/arch.png" width="100%"/> |
|
|
</p> |
|
|
</div> |
|
|
|
|
|
## Evaluation Results |
|
|
|
|
|
<table> |
|
|
<tr> |
|
|
<td><img src="https://raw.githubusercontent.com/IPADS-SAI/MobiAgent/main/assets/result1.png" width="100%"/></td> |
|
|
<td><img src="https://raw.githubusercontent.com/IPADS-SAI/MobiAgent/main/assets/result2.png" width="100%"/></td> |
|
|
<td><img src="https://raw.githubusercontent.com/IPADS-SAI/MobiAgent/main/assets/result3.png" width="100%"/></td> |
|
|
</tr> |
|
|
</table> |
|
|
|
|
|
## Usage |
|
|
|
|
|
Deploy model inference service with vLLM: |
|
|
|
|
|
```bash |
|
|
vllm serve IPADS-SAI/MobiMind-Decider-7B |
|
|
``` |
|
|
|
|
|
For more usage details, e.g., execute GUI tasks with ADB or our Android App, please refer to our [repo](https://github.com/IPADS-SAI/MobiAgent)! |
