MobiMind-Mixed-7B Model

This is the Mixed Model of MobiAgent with 7B parameters, having the abilities of both the MobiMind-Decider and the MobiMind-Grounder presented in the paper MobiAgent: A Systematic Framework for Customizable Mobile Agents.

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:

Evaluation Results

Usage

Deploy model inference service with vLLM:

vllm serve IPADS-SAI/MobiMind-Mixed-7B

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!