用多岛进化加速大模型编程优化，提升效率与稳定性。
TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution
- 让大模型一次生成多个候选程序并自评权重，动态调整探索强度。
- 在固定资源下，比现有方法发现更优代码，部分任务刷新记录。
- 适合需要高效迭代的自动化编程场景，如智能调试与优化。
基于大模型的程序演化可发现高质量代码，但其成本高且结果波动大，限制了可靠进展。本文提出TurboEvolve，一种多岛进化框架，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“语义化采样”机制，使大模型生成K个多样候选程序，并显式分配采样权重；同时设计在线调度器，根据进展动态调节K值——停滞时扩大探索，稳定时减少开销。为充分利用已有解池，进一步提出“种子池注入”策略：对种子聚类后跨岛分配，施加可控扰动并保留最优解，平衡多样性与精炼度。在多个程序优化基准上，TurboEvolve始终在较低预算下表现更优，并在若干任务中改进了已知最佳解。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。