We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmic discovery. CodeEvolve integrates inspiration-based crossover, meta-prompting, and depth-based refinement on top of a CVT-MAP-Elites archive and a weighted LLM ensemble to generate optimized solutions for complex problems. On the AlphaEvolve benchmark suite, CodeEvolve matches or surpasses the reported AlphaEvolve results on 5 of 9 problems and, under matched conditions, outperforms the open-source frameworks OpenEvolve and ShinkaEvolve on 6 of 9. With the open-weight Qwen3-Coder-30B backbone, it surpasses the reported AlphaEvolve score on both CirclePackingSquare instances at roughly an order of magnitude lower cost than a frontier closed-source ensemble, and remains competitive with EoH on heuristic-design tasks without retuning. Ablations show that the interaction between CodeEvolve's components, rather than any single operator, drives these results. We release the framework, experimental data, and practical hyperparameter guidelines at https://github.com/inter-co/science-codeevolve.

翻译：我们提出CodeEvolve，这是一个开源框架，将大语言模型与基于岛屿的进化搜索相结合，用于端到端的算法发现。CodeEvolve在CVT-MAP-Elites存档与加权LLM集成的基础上，融入了基于灵感的交叉、元提示以及深度细化，从而为复杂问题生成优化解。在AlphaEvolve基准套件上，CodeEvolve在9个问题中的5个上达到或超越了已报告的AlphaEvolve结果，且在匹配条件下，在9个问题中的6个上优于开源框架OpenEvolve与ShinkaEvolve。以开放权重的Qwen3-Coder-30B作为骨干网络，它在两个CirclePackingSquare实例上均超越了已报告的AlphaEvolve得分，成本约为前沿闭源集成的十分之一，并且在无需重新调参的情况下，在启发式设计任务上保持与EoH的竞争力。消融实验表明，驱动这些结果的并非单一算子，而是CodeEvolve各组件之间的相互作用。我们已在https://github.com/inter-co/science-codeevolve 发布该框架、实验数据及实用的超参数指南。