Trusted Automatic Programming

Speaker: Prof. Abhik Roychoudhury
National University of Singapore

Title: Trusted Automatic Programming

Date: Monday, 14 April 2025

Time: 2:30pm - 3:30pm

Venue: Room 2504 (via lift 25/26), HKUST

Abstract:

Automatic Programming, as the name suggests, achieves automation in software development. It is currently a topic of high technical and societal relevance, since it may affect how software is built, maintained and used in the future. 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.

Biography:

Abhik Roychoudhury is Provost's Chair Professor of Computer Science at the National University of Singapore (NUS), where he leads a research team on Trustworthy and Secure Software (TSS). He is also Senior Scientific Advisor at SonarSource, subsequent to the acquisition of his spinoff AutoCodeRover on AI-based coding.

Abhik received his PhD in Computer Science from the Stony Brook University in 2000, and has been a faculty member at NUS School of Computing since 2001. His research group at NUS is known for foundational contributions to software testing and analysis. Specifically the team has made contributions to automatic programming and automated program repair, as well as to fuzz testing for finding security vulnerabilities in software systems. These works have been honored with various awards including an International Conference on Software Engineering (ICSE) Most Influential Paper Award (Test-of-time award) for program repair, IEEE New Directions Award 2022 (jointly with Cristian Cadar) for contributions to symbolic execution (for test generation and program repair).

Abhik was the inaugural recipient of the NUS Outstanding Graduate Mentor Award 2024. Doctoral students graduated from his research team have taken up faculty positions in many academic institutions including Max Planck Institute, NUS, University College London, University of Melbourne, Peking University and Concordia University. He has served the software engineering research community in various capacities including as chair of the major conferences of the field, ICSE and FSE. Currently, he serves as chair of the FSE steering committee. He is a member of the editorial board of Communications of the ACM. He is the current Editor-in-Chief of the ACM Transactions on Software Engineering and Methodology (TOSEM). Abhik is a Fellow of the ACM.