GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| GUI Navigation | AITW (test) | Install Success Rate46.14 | 27 | |
| GUI Grounding | ScreenSpot 1.0 (full) | Mobile Text Acc0.226 | 6 | |
| Mobile GUI action matching | AITW instruction-wise (test) | Overall Error50.5 | 5 | |
| UI Task Completion | AITW | Overall Task Time50.5 | 5 |