Mobile-Agent-V: Learning Mobile Device Operation Through Video-Guided Multi-Agent Collaboration

Junyang Wang, xuhaiyang, Xi Zhang, Ming, Ji Zhang, Fei Huang, Jitao Sang

Mobile-Agent-V: Learning Mobile Device Operation Through Video-Guided Multi-Agent Collaboration: 14 upvotes on Hugging Face Daily Papers, #13 of 33 papers on 2025-02-25. Day-by-day upvote history.

The rapid increase in mobile device usage necessitates improved automation for seamless task management. However, many AI-driven frameworks struggle due to insufficient operational knowledge. Manually written knowledge helps but is labor-intensive and inefficient. To address these challenges, we introduce Mobile-Agent-V, a framework that leverages video guidance to provide rich and cost-effective operational knowledge for mobile automation. Mobile-Agent-V enhances task execution capabilities by leveraging video inputs without requiring specialized sampling or preprocessing. Mobile-Agent-V integrates a sliding window strategy and incorporates a video agent and deep-reflection agent to ensure that actions align with user instructions. Through this innovative approach, users can record task processes with guidance, enabling the system to autonomously learn and execute tasks efficiently. Experimental results show that Mobile-Agent-V achieves a 30% performance improvement compared to existing frameworks.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.