Researchers Highlight Need for New Benchmarks to Assess AI Models That Can Navigate Smartphones

cover
11 Dec 2024

Authors:

(1) An Yan, UC San Diego, ayan@ucsd.edu;

(2) Zhengyuan Yang, Microsoft Corporation, zhengyang@microsoft.com with equal contributions;

(3) Wanrong Zhu, UC Santa Barbara, wanrongzhu@ucsb.edu;

(4) Kevin Lin, Microsoft Corporation, keli@microsoft.com;

(5) Linjie Li, Microsoft Corporation, lindsey.li@mocrosoft.com;

(6) Jianfeng Wang, Microsoft Corporation, jianfw@mocrosoft.com;

(7) Jianwei Yang, Microsoft Corporation, jianwei.yang@mocrosoft.com;

(8) Yiwu Zhong, University of Wisconsin-Madison, yzhong52@wisc.edu;

(9) Julian McAuley, UC San Diego, jmcauley@ucsd.edu;

(10) Jianfeng Gao, Microsoft Corporation, jfgao@mocrosoft.com;

(11) Zicheng Liu, Microsoft Corporation, zliu@mocrosoft.com;

(12) Lijuan Wang, Microsoft Corporation, lijuanw@mocrosoft.com.

Editor’s note: This is the part 12 of 13 of a paper evaluating the use of a generative AI to navigate smartphones. You can read the rest of the paper via the table of links below.

6 Discussion

Future benchmarks for device-control. For future benchmarks, more dynamic interaction environments are needed. Even humans can make mistakes sometimes, and in this case, it is important that the evaluation benchmark would allow the model to explore and return to previous status when a mistake is made and realized by the model. It is also interesting to explore how to automatically evaluate success rates for this task, e.g., by using LMMs (Zhang et al., 2023). Another direction is to build GUI navigation datasets with different devices and diverse contents, e.g., personal computers and iPads.

Figure 7: Examples of true negative cases where GPT4V makes mistakes. “+” denotes human annotation, “↗” shows the trace of scrolling, and “+” is GPT-4V prediction.

Error correction. A pretrained LMM may make mistakes due to data or algorithm bias. For example, if the agent fails to complete tasks in certain novel settings, how do we correct its errors to avoid mistakes in the future? Moreover, it would be interesting to study this in a continual learning setting, where the agent keeps interacting with new environments and receives new feedback continually.

Model distillation. Using a large-scale model such as GPT-4V for GUI navigation is costly. In the future, it would be interesting to explore model distillation (Polino et al., 2018) for this task, to obtain a much smaller model with competitive navigation performance, which may achieve lower latency and higher efficiency

This paper is available on arxiv under CC BY 4.0 DEED license.