AI-Driven Software Engineering

Software applications permeate all aspects of human activity today and have grown in code size and complexity. This trend translates into higher costs for developing and maintaining modern software systems and also negatively impacts the quality of the developed software.

To reduce the manual effort involved in developing, testing, and maintaining software systems, we are designing and developing innovative automation tools and solutions for a wide range of software engineering tasks working in concert with human software developers. Our solutions combine efficient, scalable program analysis with machine-learnt models designed to capture the human software-development expertise and experience represented in previously completed software development projects. These new tools, when implemented and in effect, will imbue an average or typical software developer with the coding skills of an expert developer, thereby enabling the scalable development and deployment of robust, high-quality software.

Publications

1. Shin Hwei Tan, Hiroaki Yoshida, Mukul R. Prasad, and Abhik Roychoudhury. 2016. Anti-patterns in Search-based Program Repair. In Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering (FSE 2016). ACM, New York, NY, USA, 727-738.
2. Hiroaki Yoshida, Susumu Tokumoto, Mukul R. Prasad, Indradeep Ghosh, and Tadahiro Uehara. 2016. FSX: Fine-grained Incremental Unit Test Generation for C/C++ Programs. In Proceedings of the 25th International Symposium on Software Testing and Analysis (ISSTA 2016). ACM, New York, NY, USA, 106-117.
3. Guodong Li, Esben Andreasen, and Indradeep Ghosh. 2014. SymJS: Automatic Symbolic Testing of JavaScript Web Applications. In Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering (FSE 2014). ACM, New York, NY, USA, 449-459.
4. Casper S. Jensen, Mukul R. Prasad, and Anders Møller. 2013. Automated Testing with Targeted Event Sequence Generation. In Proceedings of the 2013 International Symposium on Software Testing and Analysis (ISSTA 2013). ACM, New York, NY, USA, 67-77.
5. Shauvik Roy Choudhary, Mukul R. Prasad, and Alessandro Orso. 2013. X-PERT: Accurate Identification of Cross-browser Issues in Web Applications. In Proceedings of the 2013 International Conference on Software Engineering (ICSE '13). IEEE Press, Piscataway, NJ, USA, 702-7