GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation
This addresses the problem of automating smartphone interactions for users or developers, but it is incremental as it applies an existing large multimodal model to a new task.
The researchers tackled smartphone GUI navigation by developing MM-Navigator, a GPT-4V-based agent that achieved 91% accuracy in generating reasonable action descriptions and 75% accuracy in executing correct actions for single-step instructions on iOS, outperforming previous methods on Android in a zero-shot setting.
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.