Large Language Models (LLMs) have emerged as powerful tools capable of accomplishing a broad spectrum of tasks. Their abilities span numerous areas, and one area where they have made a significant impact is in the domain of code generation. In this context, we view LLMs as mutation and crossover tools. Meanwhile, Quality-Diversity (QD) algorithms are known to discover diverse and robust solutions. By merging the code-generating abilities of LLMs with the diversity and robustness of QD solutions, we introduce LLMatic, a Neural Architecture Search (NAS) algorithm. While LLMs struggle to conduct NAS directly through prompts, LLMatic uses a procedural approach, leveraging QD for prompts and network architecture to create diverse and highly performant networks. We test LLMatic on the CIFAR-10 image classification benchmark, demonstrating that it can produce competitive networks with just $2,000$ searches, even without prior knowledge of the benchmark domain or exposure to any previous top-performing models for the benchmark.

翻译：大型语言模型（LLMs）已成为能够完成广泛任务集的强大工具。其能力涵盖多个领域，尤其在代码生成领域产生了显著影响。在此背景下，我们将LLMs视为变异与交叉工具。同时，质量-多样性（QD）算法以发现多样且鲁棒的解决方案而闻名。通过结合LLMs的代码生成能力与QD解决方案的多样性及鲁棒性，我们提出了LLMatic——一种神经架构搜索（NAS）算法。尽管LLMs难以直接通过提示进行NAS，但LLMatic采用程序化方法，利用QD优化提示与网络架构，从而生成多样且高性能的网络。我们在CIFAR-10图像分类基准上测试了LLMatic，结果表明，即使缺乏基准领域先验知识或未接触过该基准上的任何先前最优模型，该方法仅需2,000次搜索即可生成具有竞争力的网络。