Algorithm Selection for Automated Program Repair

Automated Program Repair (APR) is the grand challenge in software engineering research. Many APR methods have shown promising results in fixing bugs with minimal, or even no human intervention. Despite many studies introducing various APR techniques, much remains to be learned, however, about what makes a particular technique work well (or not) for a specific software system. The effectiveness of APR techniques is likely to be problem-dependent, hence we need to understand what are the problem characteristics that impact their effectiveness in order to help practitioners select the most appropriate technique for their software system. In this project, we will develop AI-based methods for selecting the appropriate APR technique to fix a particular bug. The aim is to improve the effectiveness of APR techniques and make them more user-friendly.