超越平均性能：大语言模型辅助进化搜索中的动态实例聚类与专用算法设计
Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search
浏览论文内容
中文总结 AI 辅助
针对现有LES方法仅优化平均性能导致尾部鲁棒性弱的问题，提出DyCA框架，通过动态实例聚类分解混合目标，在四项算法设计任务上提升尾部鲁棒性15.2%、整体性能7.1%。
中文摘要 AI 辅助
大语言模型辅助进化搜索（LES）已成为自动化算法设计的强大范式。然而，现有LES方法主要针对平均性能优化，固有地将搜索精力导向对该指标贡献最大的实例，而其他实例则得不到充分支持，导致尾部鲁棒性较弱、实际应用可靠性有限。为解决这一局限，我们提出动态实例聚类与专用算法设计（DyCA），这是一种LES框架，具备无特征、感知结构的机制，可在异构实例分布下构建可靠的算法组合。DyCA将实例聚类视为搜索过程中协同演化的组件，复用累积的评估数据作为无特征信号，逐步划分具有相似算法响应模式的实例。识别出的聚类将混合目标分解为一组感知结构的子目标，从而为专用算法设计提供更细粒度、更具适应性的引导。在四项异构实例的算法设计任务上的实验结果表明，DyCA的性能优于当前最优的LES基线，其尾部鲁棒性平均提升15.2%，整体性能提升7.1%，同时保持了具有竞争力的头部性能。
英文摘要
Large Language Model-assisted Evolutionary Search (LES) has emerged as a powerful paradigm for automated algorithm design. However, existing LES methods primarily optimize for average performance, inherently directing search effort toward instances that contribute most to this metric while leaving others poorly served, resulting in weak tail robustness and limited real-world reliability. To address this limitation, we propose Dynamic Instance Clustering and Specialized Algorithm Design (DyCA), an LES framework with a feature-free, structure-aware mechanism for constructing reliable algorithm portfolios under heterogeneous instance distributions. DyCA treats instance clustering as a co-evolving component within the search process, reusing accumulated evaluation data as feature-free signals to progressively partition instances with similar algorithmic response patterns. The uncovered clusters decompose the mixed objective into a set of structure-aware sub-objectives, thereby enabling finer-grained and more adaptive guidance for specialized algorithm design. Experimental results across four algorithm design tasks with heterogeneous instances demonstrate that DyCA outperforms state-of-the-art LES baselines, improving tail robustness by an average of 15.2\% and overall performance by 7.1\% while maintaining competitive head performance.
