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.

翻译：基于多模态大语言模型（MLLM）的移动设备智能体正成为一项热门的应用。本文介绍了Mobile-Agent，一个自主多模态移动设备智能体。Mobile-Agent首先利用视觉感知工具准确识别并定位应用程序前端界面中的视觉元素和文本元素。基于感知到的视觉上下文，它能自主规划并分解复杂的操作任务，通过逐步操作来导航移动应用。与以往依赖应用程序XML文件或移动系统元数据的解决方案不同，Mobile-Agent以视觉为中心的方式，使其能够在多种移动操作环境中具备更强的适应性，从而消除了针对特定系统进行定制的需求。为了评估Mobile-Agent的性能，我们引入了Mobile-Eval，一个用于评估移动设备操作的基准测试。基于Mobile-Eval，我们对Mobile-Agent进行了全面的评估。实验结果表明，Mobile-Agent达到了显著的准确率和完成率。即使面对诸如多应用操作等具有挑战性的指令，Mobile-Agent仍然能够完成任务要求。代码和模型将在https://github.com/X-PLUG/MobileAgent开源。