发表机构
Hanoi University of Science and Technology; George Mason University（河内科学技术大学; 乔治·梅森大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对LLMs与进化计算集成用于自动启发式设计时的模式崩溃问题，提出多目标QDEvo框架，结合质量多样性优化与LLM驱动启发式搜索，通过实验证明该框架能发现高性能、高效且语义多样的启发式方法，优于现有方法。
AI 中文摘要
大语言模型（LLMs）与进化计算的集成已成为组合优化中自动启发式设计的强大范例。然而，现有方法存在模式崩溃问题，收敛到缺乏语义多样性的同质群体，无法探索完整算法空间。我们提出质量多样性进化（QDEvo），这是一个多目标框架，将质量多样性优化与基于LLM的启发式搜索集成，利用预训练代码嵌入维护语义多样算法的无界存档，并纳入分层自我反思以指导进化过程。在标准基准和实际工业应用中的大量实验表明，QDEvo在超体积和反向世代距离指标上显著优于现有方法。我们的框架能够发现高性能、计算高效且语义多样的启发式方法，为从业者提供解决复杂优化问题的丰富方案组合。
英文摘要
The integration of Large Language Models (LLMs) with evolutionary computation has emerged as a powerful paradigm for automated heuristic design in combinatorial optimization. However, existing approaches suffer from mode collapse, converging to homogeneous populations that lack semantic diversity and fail to explore the full algorithmic space. We propose Quality-Diversity Evolution (QDEvo), a multi-objective framework that integrates Quality-Diversity optimization with LLM-driven heuristic search, maintaining an unbounded archive of semantically diverse algorithms using pre-trained code embeddings and incorporating hierarchical self-reflection to guide the evolutionary process. Extensive experiments across standard benchmarks and real-world industrial applications demonstrate that QDEvo significantly outperforms state-of-the-art methods in both Hypervolume and Inverted Generational Distance metrics. Our framework enables the discovery of heuristics that are simultaneously high-performing, computationally efficient, and semantically diverse, providing practitioners with a rich portfolio of solutions for complex optimization problems.
Comments4 pages; Accepted as poster at GECCO 2026
