The last decade or so has seen dramatic developments in automated debugging, including fault localisation and automated program repair. This talk will look back at 10 years of my experience from working on automated debugging, starting from evolving Spectrum Based Fault Localisation, culminating to the latest work on failure reproduction using Large Language Models. We will look at how serendipitous encounters led to new ideas, how getting slightly outside your comfort zone can help you, and how best we can collaborate with industry in order to transfer our research.

Shin Yoo is a tenured Associate Professor in the School of Computing, Korea Advanced Institute of Science and Technology (KAIST) and leads the Computational Intelligence for Software Engineering (COINSE) group (https://coinse.kaist.ac.kr). He received his PhD from King’s College London in 2009. His research interests include search based software engineering, software testing, fault localisation, and genetic improvements. He received the ACM SIGEVO HUMIES Silver Medal in 2017 for the human competitive application of genetic programming to fault localisation research. He is currently an associate editor for Journal of Empirical Software Engineering and ACM Transactions on Software Engineering and Methodology. He regularly serves in program committees of international conferences in the area of software engineering and software testing. Additionally, he served as the Program Co-chair of International Symposium on Search Based Software Engineering (SSBSE) in 2014, the Program Co-chair of IEEE International Conference on Software Testing, Verification and Validation (ICST) in 2018, the Program Co-chair of ICSE New Ideas and Emerging Results (NIER) track in 2020, and the general chair of SSBSE 2022.