Sim2Schedule: A Simulator-Guided LLM Framework for Autonomous Open-Pit Mine Scheduling
Researchers have developed a novel framework called Sim2Schedule that utilizes Large Language Models (LLMs) for autonomous open-pit mine scheduling. This system integrates an LLM with a custom simulator to generate extraction and processing schedules, operating without cloud-based inference or retraining. The framework achieves 94% to 99% of the optimal Net Present Value (NPV) compared to traditional Mixed-Integer Linear Programming (MILP) methods, while demonstrating linear scalability in computation time. This approach offers a practical and adaptable alternative for complex industrial scheduling problems. AI
IMPACT Offers a scalable and adaptable alternative to traditional optimization for complex industrial scheduling.