Debate Is Not Sampling

Abstract

The modal ceiling of test-time scaling does not transfer to multi-round debate: on 9,600 public traces three-agent debate beats the round-0 modal-hit rate on weak models and corrects 31–45% of problems where all agents started wrong. The correlation ceiling does transfer: inter-agent correlation rises every round and the panel is one effective voter by round 3. Pre-registered, zero inference cost.