2 papers
cs.SE2026
Understanding Dominant Themes in Reviewing Agentic AI-authored Code
Md. Asif Haider, Thomas Zimmermann
While prior work has examined the generation capabilities of Agentic AI systems, little is known about how reviewers respond to AI-authored code in practice. In this paper, we pres…
cs.SE2024
Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation
Md. Asif Haider, Ayesha Binte Mostofa, Sk. Sabit Bin Mosaddek +2
Generating accurate code review comments remains a significant challenge due to the inherently diverse and non-unique nature of the task output. Large language models pretrained on…