用规划与双向经验池，让自动启发式设计更智能高效。
RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience
- 引入规划器动态调度进化算子，按搜索状态触发优化。
- 构建双向经验池，积累正负经验提升搜索效率。
- 在经典组合优化任务中效果超越基线，节省计算资源。
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。尽管基于大语言模型（LLM）的方法展现出潜力，但多数依赖固定进化算子，难以有效积累和复用历史搜索经验。本文提出RefineEvo，一种新型进化框架，将AHD从静态试错过程转变为规划引导、经验驱动的系统。RefineEvo引入规划器（Planner）动态调度进化算子并根据当前搜索状态触发优化，同时通过反射器（Reflector）将有价值的经验提炼为包含正向洞察与负向教训的双向经验池（Bidirectional Experience Pool）。该协同框架使系统能随问题复杂度演化自适应调整搜索策略，并利用轨迹感知、情境条件化的见解指导生成。在多个经典组合优化基准测试中，RefineEvo持续优于强基线。尤其在保证更优解质量的同时提升令牌效率，实现更高效、更自主的启发式设计。
原文摘要 · Abstract (English)
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.
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。