Abstract:

Algorithm design plays a fundamental role across many fields including mathematical optimization, machine learning, and science discovery. Recent advances in large language models (LLMs) are creating new opportunities to automate and accelerate this traditionally human-driven process. In this talk, I will first provide an overview of automated algorithm design with LLMs. I will then introduce Evolution of Heuristics (EoH), an evolutionary framework that combines LLMs with evolutionary search to automatically discover and improve algorithms. I will also discuss recent advances and applications across different domains, and conclude with key challenges and future research directions toward more general and autonomous algorithm design.