受控自演化：面向演算法程式碼最佳化

摘要

自我演化方法透過迭代式的「生成-驗證-精煉」循環來增強程式碼生成能力，然而現有方法存在探索效率低下的問題，難以在有限預算內發現具備更優複雜度的解決方案。這種低效性源於三方面：初始化解偏差使演化過程陷入次優解區域、缺乏反饋引導的隨機操作失控，以及跨任務經驗利用不足。為突破這些瓶頸，我們提出可控自我演化框架，其包含三個核心組件：多樣化規劃初始化生成結構迥異的演算法策略以實現廣闊解空間覆蓋；遺傳演化以反饋驅動機制取代隨機操作，實現定向突變與組合式交叉；階層化演化記憶在任務間與任務內層級同步捕獲成功與失敗經驗。在EffiBench-X基準上的實驗表明，無論採用何種大型語言模型基座，CSE均能穩定超越所有基線方法。此外，CSE從演化早期即展現更高效率，並在整個演化過程中保持持續改進。程式碼已開源於：https://github.com/QuantaAlpha/EvoControl。

English

Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discover solutions with superior complexity within limited budgets. This inefficiency stems from initialization bias trapping evolution in poor solution regions, uncontrolled stochastic operations lacking feedback guidance, and insufficient experience utilization across tasks. To address these bottlenecks, we propose Controlled Self-Evolution (CSE), which consists of three key components. Diversified Planning Initialization generates structurally distinct algorithmic strategies for broad solution space coverage. Genetic Evolution replaces stochastic operations with feedback-guided mechanisms, enabling targeted mutation and compositional crossover. Hierarchical Evolution Memory captures both successful and failed experiences at inter-task and intra-task levels. Experiments on EffiBench-X demonstrate that CSE consistently outperforms all baselines across various LLM backbones. Furthermore, CSE achieves higher efficiency from early generations and maintains continuous improvement throughout evolution. Our code is publicly available at https://github.com/QuantaAlpha/EvoControl.

受控自演化：面向演算法程式碼最佳化

Controlled Self-Evolution for Algorithmic Code Optimization

摘要

Support