We present MM-Navigator, a GPT-4V-based agent for the smartphone graphical user interface (GUI) navigation task. MM-Navigator can interact with a smartphone screen as human users, and determine subsequent actions to fulfill given instructions. Our findings demonstrate that large multimodal models (LMMs), specifically GPT-4V, excel in zero-shot GUI navigation through its advanced screen interpretation, action reasoning, and precise action localization capabilities. We first benchmark MM-Navigator on our collected iOS screen dataset. According to human assessments, the system exhibited a 91\% accuracy rate in generating reasonable action descriptions and a 75\% accuracy rate in executing the correct actions for single-step instructions on iOS. Additionally, we evaluate the model on a subset of an Android screen navigation dataset, where the model outperforms previous GUI navigators in a zero-shot fashion. Our benchmark and detailed analyses aim to lay a robust groundwork for future research into the GUI navigation task. The project page is at https://github.com/zzxslp/MM-Navigator.

翻译：我们提出了MM-Navigator，一种基于GPT-4V的智能手机图形用户界面（GUI）导航智能体。MM-Navigator能够像人类用户一样与智能手机屏幕进行交互，并确定后续操作以完成给定指令。我们的研究结果表明，大型多模态模型（LMMs），特别是GPT-4V，通过其先进的屏幕理解、动作推理和精确的动作定位能力，在零样本GUI导航中表现出色。我们首先在收集的iOS屏幕数据集上对MM-Navigator进行了基准测试。根据人工评估，该系统在生成合理的动作描述方面达到了91%的准确率，在iOS上执行单步指令的正确动作方面达到了75%的准确率。此外，我们还在Android屏幕导航数据集的一个子集上对模型进行了评估，该模型以零样本方式超越了之前的GUI导航器。我们的基准测试和详细分析旨在为未来GUI导航任务的研究奠定坚实基础。项目页面位于https://github.com/zzxslp/MM-Navigator。