G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design
He Wang
🧬 Overview G-LNS (Generative Large Neighborhood Search) represents a breakthrough in automated algorithm design, leveraging Large Language Models to automatically create Large Neighborhood Search operators for combinatorial optimization problems. Unlike traditional approaches that restrict designs to fixed heuristic forms, G-LNS enables structural algorithmic innovation through the co-evolution of tightly coupled destroy and repair operator pairs. Developed by researchers from Northeastern Unive