AI RESEARCH
BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design
arXiv CS.AI
•
ArXi:2604.12898v1 Announce Type: new Large Language Model-based Hyper Heuristic (LHH) has recently emerged as an efficient way for automatic heuristic design. However, most existing LHHs just perform well in optimizing a single function within a pre-defined solver. Their single-layer evolution makes them not effective enough to write a competent complete solver. While some variants incorporate hyperparameter tuning or attempt to generate complex code through iterative local modifications, they still lack a high-level algorithmic modeling, leading to limited exploration efficiency.