Shayan Noei

Agent-involved code reviews speed up decision-making but compromise on quality, challenging the assumption that faster reviews equate to better outcomes.

AI code review agents may scale defect screening, but their suggestions are adopted less often and, when adopted, can actually *worsen* code quality, underscoring the critical need for human oversight.

LLMs can learn to code *much* better when they collaborate as agents, persistently learning from past fixes and error patterns under the supervision of a "Mentor Agent."