AI RESEARCH
AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
arXiv CS.AI
•
ArXi:2605.08756v1 Announce Type: new Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs). Recent works show that large language models (LLMs), when integrated into well-designed frameworks (i.e., LLM-AHD), can autonomously discover high-performing heuristics. However, existing LLM-AHD frameworks typically treat LLMs as passive generators within fixed workflows, where the model generates heuristics from manually designed, limited context.