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 introduces verbalized Sampling, prompting the LLM to emit K diverse candidates with explicit self-assigned sampling weights, and an online scheduler that adapts K to expand exploration under stagnation and reduce overhead during steady progress. To exploit existing solution pools, we further propose "seed-pool injection," which clusters seeds and assigns them across islands with controlled perturbations and elitist preservation to balance diversity and refinement. Across multiple program-optimization benchmarks, TurboEvolve consistently achieves stronger performance at lower budgets and improves best-known solutions on several tasks.

翻译：LLM驱动的程序进化能够发现高质量程序，但其高昂成本与运行间方差阻碍了可靠进展。我们提出TurboEvolve，一种多岛屿进化框架，在固定评估预算下提升样本效率与鲁棒性。受进化算法中多后代策略启发，TurboEvolve引入了语言化采样机制，促使LLM生成K个多样候选解并附带显式自分配采样权重；同时设计在线调度器，根据停滞期自适应扩大K以增强探索，在稳定进展期则减少开销。为利用现有解池，我们进一步提出"种子池注入"方法，通过聚类种子并在岛屿间分配，结合可控扰动与精英保留策略，平衡多样性与精化能力。在多个程序优化基准上，TurboEvolve以更低预算持续实现更优性能，并在多项任务中改进了已知最优解。