Does a team of coding agents beat one agent?
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
A controlled trial on six real features found that a planner–coder–reviewer team of Codex agents passed 25.7% of hidden acceptance tests, against 56.8% for one agent alone at lower cost. The main cause was a lossy hand-off from planner to coder.