发表机构
C$^2$DL, Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing; University of Chinese Academy of Sciences, Nanjing（C2DL，自动化研究所，中国科学院; 人工智能学院，中国科学院大学，北京; 中国科学院大学，南京）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对自动启发式设计中基于LLM方法的不足，提出RefineEvo框架，通过规划器和反射器，结合双向经验池动态调度进化算子，在经典组合优化基准测试中表现出色，提升了解质量和令牌效率。
AI 中文摘要
自动启发式设计（AHD）已成为解决组合优化问题的变革性方法。基于大语言模型（LLM）的方法虽有前景，但依赖固定进化算子，难以积累和重用历史搜索经验。本文提出RefineEvo，将AHD从静态试错过程转变为规划引导、经验驱动系统。它引入规划器动态调度进化算子并触发优化，引入反射器提炼经验存入双向经验池。实验表明RefineEvo优于强基线，能提升解质量和令牌效率，实现更高效自主的启发式设计。
英文摘要
Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving combinatorial optimization problems. While recent Large Language Model (LLM)-based methods have shown promise, they predominantly rely on fixed evolutionary operators and struggle to effectively accumulate and reuse historical search experience. This paper proposes RefineEvo, a novel evolutionary framework that transforms AHD from a static trial-and-error process into a planning-guided, experience-driven system. RefineEvo introduces a Planner to dynamically schedule evolutionary operators and trigger refinement based on the current search state, and a Reflector to distill valuable lessons into a Bidirectional Experience Pool containing both positive insights and negative pitfalls. This synergistic framework enables the system to adapt its search tools to the evolving complexity of the problem and leverage trajectory-aware, situation-conditioned insights to guide generation. Experiments on several classic combinatorial optimization benchmarks demonstrate that RefineEvo consistently outperforms strong baselines. In particular, RefineEvo delivers superior solution quality while improving token efficiency, enabling more efficient and autonomous heuristic design.
