# Multi-agent LLM debate

The work introduces an auditable protocol for homogeneous three-agent LLM debate that decomposes final accuracy into preserved, collapse, correction, and unrepaired transitions with collapse onset and signed intervention utility, identifies 253 collapses across 6,925 MMLU-Pro debates, and shows via replay that a leave-one-model-out probe-gated freeze prevents 29 collapses while losing 108 corrections under equal weights, so collapse prevention alone can recommend the wrong policy.

The work introduces an auditable protocol for homogeneous three-agent LLM debate that decomposes final accuracy into preserved, collapse, correction, and unrepaired transitions with collapse onset and signed intervention utility, identifies 253 collapses across 6,925 MMLU-Pro debates, and shows via replay that a leave-one-model-out probe-gated freeze prevents 29 collapses while losing 108 corrections under equal weights, so collapse prevention alone can recommend the wrong policy.