Keynote: From Hallucinations to Helpful Agents: Advancing Trustworthy Automation in Code Review

Patanamon Thongtanunam, University of Melbourne

Abstract. Large language models (LLMs) have demonstrated strong capabilities across software engineering tasks, including code review, and are increasingly embedded in commercial development workflows. Yet, code review is a critical quality and security gate, and reliance on LLMs raises fundamental questions about reliability and risk. This keynote synthesises a multi-year research agenda that investigates where and why LLM-based review automation could break down—and how it can be redesigned to better support developers. Grounded in large-scale mining of software repositories and empirical studies, the talk discusses hallucinations, data quality, and security blind spots in code review automation, and argues for a shift from surface-level text generation toward accountable, goal-driven, and agentic review systems that developers can trust.

Patanamon Thongtanunam (or Pick) is an ARC DECRA Fellow and a lecturer at the School of Computing and Information System, The University of Melbourne. She received the D.E. degree (2016) in Information Science from Nara Institute of Science and Technology, Japan. Her primary research goals are directed towards uncovering empirical evidence and extracting knowledge from data recorded in software repositories by using statistical analysis. The foundation for her PhD thesis has been published at International Conference on Software Engineering (ICSE), International Conference on Mining Software Repositories (MSR), and International Conference on Software Analysis, Evolution, and Reengineering (SANER). More about Patanamon and her work is available online at http://patanamon.com/.