3 papers
cs.SE2026
The End of Code Review: Coding Agents Supersede Human Inspection
Martin Monperrus
Code review has been the primary quality gate in software development since Fagan formalised code inspection in 1976. For five decades, having a human examine and comment on a coll…
cs.SE2026
The Grand Software Supply Chain of AI Systems
Carmine Cesarano, Martin Monperrus
AI systems rest on software with low integrity mechanisms, leaving AI systems exposed across every stage from data acquisition to final inference. This paper makes the AI supply ch…
cs.SE2026
Bootstrapping Coding Agents: The Specification Is the Program
Martin Monperrus
A coding agent can bootstrap itself. Starting from a 926-word specification and a first implementation produced by an existing agent (Claude Code), a newly generated agent re-imple…