AI RESEARCH
TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution
arXiv CS.AI
•
ArXi:2604.18607v1 Announce Type: cross LLM-driven program evolution can discover high-quality programs, but its cost and run-to-run variance hinder reliable progress. We propose TurboEvolve, a multi-island evolutionary framework that improves sample efficiency and robustness under fixed evaluation budgets. Inspired by the multiple-offspring strategy in evolutionary algorithms, TurboEvolve