让大模型设计算法时，结构和参数分开调优，提升搜索效率和解的质量。
TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Design
- 结构与参数分离优化，用树编辑距离保持多样性。
- 在9个组合优化问题上优于现有方法，解质量更高、成本更低。
- 适合想用大模型自动设计高效算法的研究者或工程师。
尽管大型语言模型已推动自动化启发式设计的发展，但将算法演化视为单一文本生成任务，忽略了离散算法结构与连续数值参数之间的耦合关系。因此，现有方法常因常数未校准而丢弃有潜力的算法，并因简单相似性度量导致过早收敛。为解决这些问题，我们提出TIDE（Tuning-Integrated Dynamic Evolution）框架，旨在将结构推理与参数优化解耦。TIDE采用嵌套架构：外层并行岛屿模型使用树相似性编辑距离驱动结构多样性；内层结合基于LLM的逻辑生成与差分突变算子进行参数调优。此外，基于UCB的调度器动态优先选择高产出提示策略以优化资源分配。在九个组合优化问题上的大量实验表明，TIDE发现的启发式算法在解质量上显著优于当前最优基线，同时实现更高的搜索效率和更低的计算成本。
原文摘要 · Abstract (English)
Although Large Language Models have advanced Automated Heuristic Design, treating algorithm evolution as a monolithic text generation task overlooks the coupling between discrete algorithmic structures and continuous numerical parameters. Consequently, existing methods often discard promising algorithms due to uncalibrated constants and suffer from premature convergence resulting from simple similarity metrics. To address these limitations, we propose TIDE, a Tuning-Integrated Dynamic Evolution framework designed to decouple structural reasoning from parameter optimization. TIDE features a nested architecture where an outer parallel island model utilizes Tree Similarity Edit Distance to drive structural diversity, while an inner loop integrates LLM-based logic generation with a differential mutation operator for parameter tuning. Additionally, a UCB-based scheduler dynamically prioritizes high-yield prompt strategies to optimize resource allocation. Extensive experiments across nine combinatorial optimization problems demonstrate that TIDE discovers heuristics that significantly outperform state-of-the-art baselines in solution quality while achieving improved search efficiency and reduced computational costs.
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。