一句话：提出 ReBL，利用 GPT-4 与反馈驱动提示从整份缺陷报告文本自动复现 Android 缺陷，无需 S2R 实体。
缺陷报告复现是软件开发中的难题，传统方法依赖从报告中抽取 Step to Reproduce（S2R）实体再做逐步匹配，灵活性差且主要针对崩溃报告。本文提出 ReBL，一种反馈驱动方法，直接以整份文本缺陷报告为输入，利用 GPT-4 及专门设计的提示增强上下文推理，并借助反馈迭代改进复现过程，从而同时支持崩溃与非崩溃功能性缺陷。作者在 96 份 Android 缺陷报告（73 份崩溃、23 份非崩溃）上评估，ReBL 成功复现 90.63%，平均每份仅需 74.98 秒，在成功率与速度上均优于三个现有工具。
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.
@inproceedings{paperbot8598,
title = {Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps},
author = {Dingbang Wang and Yu Zhao and Sidong Feng and Zhaoxu Zhang and William G. J. Halfond and Chunyang Chen and Xiaoxia Sun and Jiangfan Shi and Tingting Yu},
booktitle = {ISSTA},
year = {2024},
doi = {10.1145/3650212.3680341}
}