分析大模型辅助算法搜索的复杂性，揭示其多峰崎岖的特性。
Fitness Landscape of Large Language Model-Assisted Automated Algorithm Search
- 用图结构建模算法间转移，分析大模型搜索路径
- 六任务六模型测试显示组合优化任务最复杂，具显著多峰特征
- 不同算法相似度度量方法影响性能与操作行为，提供设计参考
将大语言模型（LLM）用于进化或迭代搜索框架，在自动化算法设计中展现出巨大潜力。然而，决定搜索行为的关键——适应度景观仍缺乏深入研究。本文采用基于图的方法，以算法为节点、转换关系为边，剖析大模型辅助算法搜索（LAS）的适应度景观。在六个算法设计任务和六个常用LLM上开展广泛评估。结果表明，LAS景观高度多峰且崎岖，尤其在组合优化任务中表现明显，且任务与模型间存在显著结构差异。此外，采用四种算法相似度度量方法，研究其与算法性能及操作行为的相关性。这些发现不仅深化了对LAS景观的理解，也为设计更高效的LAS方法提供了实用指导。
原文摘要 · Abstract (English)
Using Large Language Models (LLMs) in an evolutionary or other iterative search framework have demonstrated significant potential in automated algorithm design. However, the underlying fitness landscape, which is critical for understanding its search behavior, remains underexplored. In this paper, we illustrate and analyze the fitness landscape of LLM-assisted Algorithm Search (LAS) using a graph-based approach, where nodes represent algorithms and edges denote transitions between them. We conduct extensive evaluations across six algorithm design tasks and six commonly-used LLMs. Our findings reveal that LAS landscapes are highly multimodal and rugged, particularly in combinatorial optimization tasks, with distinct structural variations across tasks and LLMs. Moreover, we adopt four different methods for algorithm similarity measurement and study their correlations to algorithm performance and operator behaviour. These insights not only deepen our understanding of LAS landscapes but also provide practical insights for designing more effective LAS methods.
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。