用大模型生成优化启发式，让复杂调度更灵活高效
REMoH: A Reflective Evolution of Multi-objective Heuristics approach via Large Language Models
- 结合遗传算法与大模型，自动生成多样且高质量的启发式规则
- 在三个标准数据集上表现优于或媲美顶尖方法，建模工作量更低
- 适合需要快速适配新场景的工业优化问题研究者
多目标优化在复杂决策任务中至关重要。传统算法虽有效，但常需大量问题定制建模，难以适应非线性结构。近期大语言模型（LLMs）在可解释性、自适应性和推理能力方面取得进展。本文提出反射式多目标启发式演化框架（REMoH），将NSGA-II与基于LLM的启发式生成相结合。关键创新在于引入反射机制，通过聚类和搜索空间反射引导生成多样化、高质量的启发式规则，提升收敛速度并保持解的多样性。在柔性作业车间调度问题（FJSSP）上，使用Dauzere、Barnes和Brandimarte三个实例数据集进行深度对比实验，结果表明，REMoH在减少建模投入的同时，性能达到或超越现有先进方法，验证了LLM在增强传统优化中的潜力，为多目标场景提供更高灵活性、可解释性和鲁棒性。
原文摘要 · Abstract (English)
Multi-objective optimization is fundamental in complex decision-making tasks. Traditional algorithms, while effective, often demand extensive problem-specific modeling and struggle to adapt to nonlinear structures. Recent advances in Large Language Models (LLMs) offer enhanced explainability, adaptability, and reasoning. This work proposes Reflective Evolution of Multi-objective Heuristics (REMoH), a novel framework integrating NSGA-II with LLM-based heuristic generation. A key innovation is a reflection mechanism that uses clustering and search-space reflection to guide the creation of diverse, high-quality heuristics, improving convergence and maintaining solution diversity. The approach is evaluated on the Flexible Job Shop Scheduling Problem (FJSSP) in-depth benchmarking against state-of-the-art methods using three instance datasets: Dauzere, Barnes, and Brandimarte. Results demonstrate that REMoH achieves competitive results compared to state-of-the-art approaches with reduced modeling effort and enhanced adaptability. These findings underscore the potential of LLMs to augment traditional optimization, offering greater flexibility, interpretability, and robustness in multi-objective scenarios.
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。