Fill in the Blank: Context-aware Automated Text Input Generation for Mobile GUI Testing

TL;DR

This paper introduces QTypist, a novel LLM-based approach for generating context-aware, semantic text inputs to improve automated mobile GUI testing coverage and bug detection.

Contribution

It presents a prompt-based data tuning method for LLMs and demonstrates significant improvements in testing coverage and bug discovery in mobile apps.

Findings

QTypist achieves an 87% passing rate on 106 apps, 93% higher than baselines.

Integration of QTypist increases app activity coverage by 42% and page coverage by 52%.

QTypist helps reveal 122% more bugs than raw testing tools.

Abstract

Automated GUI testing is widely used to help ensure the quality of mobile apps. However, many GUIs require appropriate text inputs to proceed to the next page which remains a prominent obstacle for testing coverage. Considering the diversity and semantic requirement of valid inputs (e.g., flight departure, movie name), it is challenging to automate the text input generation. Inspired by the fact that the pre-trained Large Language Model (LLM) has made outstanding progress in text generation, we propose an approach named QTypist based on LLM for intelligently generating semantic input text according to the GUI context. To boost the performance of LLM in the mobile testing scenario, we develop a prompt-based data construction and tuning method which automatically extracts the prompts and answers for model tuning. We evaluate QTypist on 106 apps from Google Play and the result shows that the passing rate of QTypist is 87%, which is 93% higher than the best baseline. We also integrate QTypist with the automated GUI testing tools and it can cover 42% more app activities, 52% more pages, and subsequently help reveal 122% more bugs compared with the raw tool.