Recent advances in data-driven evolutionary algorithms (EAs) have demonstrated the potential of leveraging historical data to improve optimization accuracy and adaptability. Despite these advancements, existing methods remain reliant on handcrafted process-level operators. In contrast, Evolutionary Generative Optimization (EvoGO) is a fully data-driven framework designed from the objective level, enabling autonomous learning of the entire search process. EvoGO streamlines the evolutionary optimization process into three stages: data preparation, model training, and population generation. The data preparation stage constructs a pairwise dataset to enrich training diversity without incurring additional evaluation costs. During model training, a tailored generative model learns to transform inferior solutions into superior ones. In the population generation stage, EvoGO replaces traditional reproduction operators with a scalable and parallelizable generative mechanism. Extensive experiments on numerical benchmarks, classical control problems, and high-dimensional robotic tasks demonstrate that EvoGO consistently converges within merely 10 generations and substantially outperforms a wide spectrum of optimization approaches, including traditional EAs, Bayesian optimization, and reinforcement learning based methods. Code is available at: https://github.com/EMI-Group/evogo

翻译：数据驱动进化算法的最新进展已展现出利用历史数据提升优化精度与适应性的潜力。尽管取得了这些进展，现有方法仍依赖于人工设计的过程级算子。相比之下，进化生成优化（EvoGO）是一个从目标层面设计的完全数据驱动框架，能够自主学习整个搜索过程。EvoGO将进化优化流程简化为三个阶段：数据准备、模型训练和种群生成。数据准备阶段构建配对数据集以增强训练多样性，且无需额外评估成本。在模型训练阶段，定制的生成模型学习将劣质解转化为优质解。在种群生成阶段，EvoGO以可扩展且可并行化的生成机制取代传统的繁殖算子。在数值基准测试、经典控制问题和高维机器人任务上的大量实验表明，EvoGO仅需10代即可持续收敛，并显著优于包括传统进化算法、贝叶斯优化和基于强化学习方法在内的广泛优化方法。代码发布于：https://github.com/EMI-Group/evogo