Automatic Programming, as the name suggests, achieves automation in software development. It is currently a topic of high technical and societal relevance, owing to the rise of generative AI. While disruptive innovations promising automated coding exist today, automatically generated code often carries with it a lesser degree of trust. The core challenge often comes a lack of understanding and extraction of developer intent, and using this intent in the automated coding. In this talk, we will first explore how symbolic program analysis methods can help extract developer intent from incomplete specifications such as a test-suite. These techniques SemFix and Angelix, allowed us to achieve automated program repair, where we rectify errors or vulnerabilities in code at scale. We will share past experiences in fixing vulnerabilities based on a single available test or exploit. We then discuss more recent works, where the correctness criterion guiding the repair is not provided by tests, but rather a bug report in natural language. We will discuss our Large Language Model agents AutoCodeRover and SpecRover, and discuss how the overall research goal of code intent extraction has influenced the design of these agents. AutoCodeRover was a spinoff from NUS which has been acquired by SonarSource in February 2025, with the goal of fixing vulnerabilities found by static analysis. We will conclude the talk with a discussion on how agentic AI may be shifting the balance in programming with trust in coding and code security becoming more important than programming at scale.

Abhik Roychoudhury is a Provost’s Chair Professor of Computer Science at the National University of Singapore, where he has been working since 2001 after receiving his Ph.D. in Computer Science from the State University of New York at Stony Brook in 2000. Abhik’s research focuses on software testing and analysis, software security and trust-worthy software construction. His research was honored with IEEE TCSE New Directions Award in 2022 (jointly with Cristian Cadar) for contributions to symbolic execution, as well as with International Conference on Software Engineering (ICSE) 2023 Most Influential Paper Award for an ICSE 2013 paper suggesting semantic approaches towards program repair. His former doctoral students have been placed all over the world as academics (University College London, Max-Planck Institute, University of Melbourne and other places). He has chaired the major conferences in software engineering as Program co-chair of ICSE 2024, General Chair of FSE 2022 in Singapore, and Program chair of ISSTA 2016. His research group is known for contributions to automatic programming, program repair, fuzzing and symbolic execution. Abhik is the Editor-in-Chief of ACM Transactions on Software Engineering and Methodology (TOSEM), and the current chair of the FSE Steering Committee. He is a Fellow of the ACM.