Diverse LLM debates beat simple averaging on four tests
Groups of large language models can improve answers by deliberating, not just by averaging independent responses, giving practitioners a stronger way to aggregate model judgments. The paper tests a three-stage discussion setup across visual estimation, ML-paper review, malicious-behavior detection, and sports forecasting. Deliberation reduced collective error and improved individuals afterward, but only when the group mixed model families: clones of one model gained nothing.