Controlled Self-Evolution for Algorithmic Code Optimization
By: Tu Hu, Ronghao Chen, Shuo Zhang, Jianghao Yin, Mou Xiao Feng, Jingping Liu, Shaolei Zhang, Wenqi Jiang, Yuqi Fang, Sen Hu, Yi Xu, Huacan Wang
Published: 2026-01-12
View on arXiv →#cs.AI
Abstract
This paper proposes Controlled Self-Evolution (CSE) to enhance code generation through iterative generate-verify-refine cycles. It addresses inefficiencies in existing self-evolution methods for algorithmic code optimization by improving exploration efficiency and experience utilization, leading to more efficient and algorithmically optimal solutions.