让AI代码优化更高效，自动发现更优解法。
Controlled Self-Evolution for Algorithmic Code Optimization
- 用结构化初始化扩大搜索范围，避免陷入劣解。
- 结合反馈引导进化，早期生成就更优且持续提升。
- 记录成功与失败经验，跨任务共享优化知识。
自进化方法通过迭代的‘生成-验证-优化’循环提升代码生成质量，但现有方法在有限预算下探索效率低，难以发现复杂度更低的优秀解。这主要源于初始策略偏差导致进化困于低质量解区域、随机操作缺乏反馈引导、以及跨任务经验利用不足。为此，我们提出受控自进化（CSE），包含三个核心组件：多样化规划初始化生成结构各异的算法策略以覆盖更广解空间；遗传进化用反馈驱动的变异和组合替代随机操作，实现精准优化；层次化进化记忆在任务间与任务内记录成功与失败经验。在EffiBench-X上的实验表明，CSE在不同LLM模型下均优于所有基线，且从早期生成即展现更高效率，并持续改进。代码已公开于https://github.com/QuantaAlpha/EvoControl。
原文摘要 · Abstract (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.
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。