Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings

The paper introduces DEEVO, a debate-driven evolutionary framework for optimizing prompts for large language models without relying on predefined metrics, addressing challenges in subjective and complex tasks. DEEVO leverages Elo-based evaluation, debate feedback, and strategic genetic operations to outperform manual and existing automated prompt optimization methods, advancing the field of adaptive prompt engineering.