Generative AI in Automated Code Review and Bug Detection: A Literature Review

Code review is a critical but time-consuming stage of the software development lifecycle, and large language models are increasingly being used to assist with it. This paper reviews recent literature on code review and bug detection, developer trust and workflow, and real-world applications of generative AI in this space. We find that while LLM-based tools show promise in flagging bugs and reducing reviewer workload, concerns remain around their reliability and the gap between technical capability and everyday developer adoption. We conclude with open challenges for future research, including the long-term impact of AI-assisted review on developers' own skills.