G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design
He Wang Research Associate Knowledge increases by sharing but not by saving
Highlights First framework to co-evolve destroy and repair operators for Large Neighborhood Search using LLMs Synergy Matrix explicitly models operator interactions during evolutionary process Dual-population architecture maintains separate populations for destroy and repair operators Generative design produces executable code rather than just parameter tuning Strong generalization to unseen problem instances and distributions Near-optimal solutions on TSP and CVRP benchmarks with reduced comput
Tags