Update README.md

README.md

@@ -1,3 +1,55 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: apache-2.0
+pipeline_tag: image-text-to-text
+tags:
+- multimodal
+- gui
+base_model:
+- Qwen/Qwen3-VL-4B-Instruct
+---
+# MobiMind-Mixed-4B-1031 Model
+
+This is the Mixed Model of [MobiAgent](https://github.com/IPADS-SAI/MobiAgent) which is trained on the basis of [Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct), having the abilities of both the [MobiMind-Decider](https://huggingface.co/IPADS-SAI/MobiMind-Decider-7B/) and the [MobiMind-Grounder](https://huggingface.co/IPADS-SAI/MobiMind-Grounder-3B/) presented in the paper [MobiAgent: A Systematic Framework for Customizable Mobile Agents](https://huggingface.co/papers/2509.00531). 
+
+## 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
+# Requirements: vllm >= 0.11.0
+vllm serve IPADS-SAI/MobiMind-Mixed-4B-1031
+```
+
+It simultaneously serves as the Decider and the Grounder, i.e., the requests for **both tasks** can be routed to this model.
+
+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)!