Software is eating the world. However, the current software development process is still largely a manual, time-consuming, and error-prone process. In the era of big data and artificial intelligence, we aim to achieve intelligent software engineering, which builds intelligent models from software data (such as source code, execution logs, historical failures, performance counters, etc) to automate programming, testing, and maintenance tasks. Examples of these tasks include code summarization, code search, and log analytics, through which software development productivity can be improved and maintenance effort can be reduced. In recent years, various deep learning models, including large language models (LLMs), are utilized for intelligent software engineering. In this talk, I will introduce some recent work on intelligent software engineering, especially the LLM-based approaches. I will also briefly discuss several challenges in this promising field.

Hongyu Zhang is currently an associate professor at The University of Newcastle, Australia. Previously, he was a Lead Researcher at Microsoft Research Asia and an Associate Professor at Tsinghua University, China. He received his PhD degree from National University of Singapore in 2003. His research is in the area of Software Engineering, in particular, software analytics, testing, maintenance, and reuse. The main theme of his research is to improve software quality and productivity by mining software data. He has published more than 160 research papers in international journals and conferences, including TSE, TOSEM, ICSE, FSE, POPL, AAAI, IJCAI, KDD, ASE, ISSTA, ICSME, ICDM, and USENIX. He received three ACM Distinguished Paper awards. He has also served as a program committee member for many software engineering conferences. More information about him can be found at: https://sites.google.com/site/hongyujohn/ .