MobiAgent: A Systematic Framework for Customizable Mobile Agents
This work addresses challenges in intelligent mobile systems for users needing reliable task execution, though it appears incremental as it builds on existing agent models.
The paper tackles the problem of low accuracy and efficiency in GUI-based mobile agents by proposing MobiAgent, a comprehensive system with agent models, an acceleration framework, and a benchmarking suite, which achieves state-of-the-art performance in real-world mobile scenarios.
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.