Controlled Self-Evolution for Algorithmic Code Optimization

TL;DR

This paper introduces Controlled Self-Evolution (CSE), a novel method for algorithmic code optimization that improves exploration efficiency and solution quality through diversified initialization, feedback-guided genetic operations, and hierarchical experience memory.

Contribution

CSE combines diversified initialization, feedback-guided genetic operations, and hierarchical experience memory to enhance exploration and efficiency in algorithmic code optimization.

Findings

CSE outperforms all baselines on EffiBench-X.

CSE achieves higher early-generation efficiency.

CSE maintains continuous improvement throughout evolution.

Abstract

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.