Review is the control point for AI-authored code: teams set the sign of AI’s effect through reviewer expertise and process design, not the technology itself.
A task-level evaluation of ai agents in open-source projects,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2representative citing papers
AI coding tools divide into collaborators that initiate most PRs and assistants that support human-led ones, yet humans retain merge authority across all five tools examined.
citing papers explorer
-
3100 Opinions on Code Review in an AI World: Building Causal Theory from Practitioner Discourse
Review is the control point for AI-authored code: teams set the sign of AI’s effect through reviewer expertise and process design, not the technology itself.
-
Collaborator or Assistant? How AI Coding Agents Partition Work Across Pull Request Lifecycles
AI coding tools divide into collaborators that initiate most PRs and assistants that support human-led ones, yet humans retain merge authority across all five tools examined.