CLCVJan 29, 2024

Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception

arXiv:2401.16158v2293 citationsh-index: 28Has Code
Originality Incremental advance
AI Analysis

This addresses the need for adaptable mobile automation tools for users and developers, though it is incremental as it builds on existing multimodal language models.

The paper tackles the problem of autonomous mobile device operation by introducing Mobile-Agent, which uses visual perception to navigate apps without relying on system-specific metadata, achieving high accuracy and completion rates in evaluations.

Mobile device agent based on Multimodal Large Language Models (MLLM) is becoming a popular application. In this paper, we introduce Mobile-Agent, an autonomous multi-modal mobile device agent. Mobile-Agent first leverages visual perception tools to accurately identify and locate both the visual and textual elements within the app's front-end interface. Based on the perceived vision context, it then autonomously plans and decomposes the complex operation task, and navigates the mobile Apps through operations step by step. Different from previous solutions that rely on XML files of Apps or mobile system metadata, Mobile-Agent allows for greater adaptability across diverse mobile operating environments in a vision-centric way, thereby eliminating the necessity for system-specific customizations. To assess the performance of Mobile-Agent, we introduced Mobile-Eval, a benchmark for evaluating mobile device operations. Based on Mobile-Eval, we conducted a comprehensive evaluation of Mobile-Agent. The experimental results indicate that Mobile-Agent achieved remarkable accuracy and completion rates. Even with challenging instructions, such as multi-app operations, Mobile-Agent can still complete the requirements. Code and model will be open-sourced at https://github.com/X-PLUG/MobileAgent.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes