Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps

TL;DR

ReBL is a feedback-driven, GPT-4-based approach that automatically reproduces Android bug reports more accurately and efficiently by leveraging the entire report text and innovative prompts, surpassing existing tools.

Contribution

This paper introduces ReBL, a novel GPT-4-powered method that improves bug report reproduction by avoiding traditional step-based entity matching, enhancing flexibility and accuracy.

Findings

ReBL successfully reproduced 90.63% of 96 bug reports.

ReBL averaged 74.98 seconds per report, faster than existing tools.

ReBL outperformed three baseline tools in success rate and speed.

Abstract

In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model (LLM), to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to Reproduce (S2R) entities. Instead, it leverages the entire textual bug report and employs innovative prompts to enhance GPT's contextual reasoning. This approach is more flexible and context-aware than the traditional step-by-step entity matching approach, resulting in improved accuracy and effectiveness. In addition to handling crash reports, ReBL has the capability of handling non-crash functional bug reports. Our evaluation of 96 Android bug reports (73 crash and 23 non-crash) demonstrates that ReBL successfully reproduced 90.63% of these reports, averaging only 74.98 seconds per bug report. Additionally, ReBL outperformed three existing tools in both success rate and speed.