AI RESEARCH
Generalizable Heuristic Generation Through LLMs with Meta-Optimization
arXiv CS.AI
•
ArXi:2505.20881v2 Announce Type: replace-cross Heuristic design with large language models (LLMs) has emerged as a promising approach for tackling combinatorial optimization problems (COPs). However, existing approaches often rely on manually predefined evolutionary computation (EC) heuristic-optimizers and single-task