DEI: Diversity in Evolutionary Inference for Quality-Diversity Search
Researchers have developed DEI, a distributed Quality-Diversity search framework that leverages heterogeneous large language models as mutation operators. This approach enhances evolutionary inference by utilizing the distinct creative priors of different LLMs, leading to greater behavioral novelty compared to homogeneous methods. When applied to the Core War domain, a heterogeneous ensemble of models like GPT-5.4-mini and Claude Sonnet 4.6 significantly outperformed a single-node baseline and a homogeneous ensemble in terms of QD-Score and coverage. AI
IMPACT Demonstrates that model diversity, not just parallelism, is key to gains in distributed LLM-based search, potentially improving optimization tasks.