用进化算法+大模型自动设计优化代码，效果超越现有开源方案。
CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization
- 结合大模型与岛屿式进化搜索，自动生成优化算法。
- 在9个任务中6项优于开源框架，成本降低近10倍。
- 适合需要自动算法设计的研究者和工程团队。
我们提出CodeEvolve，一个开源框架，将大语言模型与基于岛屿的进化搜索结合，实现端到端的算法发现与优化。该框架在CVT-MAP-Elites档案基础上，引入灵感交叉、元提示和深度精炼，并采用加权LLM集成，以解决复杂问题。在AlphaEvolve基准测试中，CodeEvolve在9个问题中的5个上达到或超过原报告结果；在相同条件下，优于开源框架OpenEvolve和ShinkaEvolve的6个任务。使用开放权重的Qwen3-Coder-30B作为主干模型时，其在两个CirclePackingSquare实例上的表现超越原报告结果，且成本仅为前沿闭源集成的约十分之一；在启发式设计任务中，无需微调即可保持与EoH相当的性能。消融实验表明，各组件间的协同作用而非单一操作驱动了整体性能提升。代码、实验数据及超参数指南已公开于https://github.com/inter-co/science-codeevolve。
原文摘要 · Abstract (English)
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.
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。