Optimization

G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design

🧬 Revolutionary framework that uses Large Language Models to automatically design Large Neighborhood Search operators for combinatorial optimization. Through synergy-aware co-evolution of destroy and repair operators, achieves near-optimal solutions with reduced computational budgets on TSP and CVRP benchmarks.

Automated Algorithmic Discovery for Scientific Computing through LLM-Guided Evolutionary Search: A Case Study in Gravitational-Wave Detection

A framework for automated discovery of gravitational-wave detection algorithms, combining LLM guidance with Evolutionary Monte Carlo Tree Search, enabling efficient and creative pipeline discovery.