RoPoLL: Robust Panel of LLM Judges
International Conference on Machine Learning (ICML), 2026 · Workshop on Statistical Frameworks for Uncertainty in Agentic Systems (AgenticUQ)
Shows that averaging an LLM jury is unboundedly biased once any judge fails systematically, and replaces the average with a geometric-median aggregator that has the optimal 1/2 breakdown point. A 3-judge 38B panel beats a 675B judge by 1.31x under 30% corruption.