Sim2Schedule: A Simulator-Guided LLM Framework for Autonomous Open-Pit Mine Scheduling

2026-06-08

AI Summary

This study addresses the high computational complexity of traditional mixed-integer linear programming (MILP) in open-pit mine scheduling and its limited adaptability to dynamic environments. The authors propose a novel zero-shot large language model (LLM) decision-making framework guided by a custom mine simulator that embeds geological–processing coupling constraints. This approach, for the first time, integrates an un-tuned LLM with a physically informed simulator to generate interpretable and feasible scheduling plans in a closed-loop setting without requiring any training data. Experimental results demonstrate that the method achieves 94%–99% of the net present value obtained by MILP across mine instances of varying scales, with computation time scaling linearly—significantly outperforming the exponential complexity of conventional MILP solvers. The work also introduces the first MILP benchmark incorporating real-world industrial constraints for rigorous evaluation.

Abstract

Open-pit mine scheduling is a critical process for maximizing economic return under complex geotechnical and operational constraints. While Mixed-Integer Linear Programming (MILP) provides mathematically optimal baselines, its exponential computational complexity and inability to adapt in real time limit its practical deployment in dynamic industrial environments. This work introduces a simulator-driven Large Language Model (LLM) scheduling framework in which the LLM acts as an autonomous decision-making agent, guided at each step by a custom simulator that encodes geotechnical precedence, extraction-processing coupling, and dynamic capacity constraints directly into the action generation mechanism. Operating entirely zero-shot within a closed, data-secure environment, the framework produces complete, interpretable extraction and processing schedules without cloud-based inference, domain-specific fine-tuning, or retraining. To provide a trustworthy performance benchmark, a novel MILP formulation is developed that incorporates realistic operational and geotechnical constraints. Evaluated across mining instances of varying scale and time periods, the LLM-based framework recovers between 94\% and 99\% of the MILP optimal NPV while scaling linearly in computation time. These results position simulator-constrained LLM agents as a practical and scalable alternative to classical optimization for long-horizon industrial scheduling under complex operational constraints.

Problem

• open-pit mine scheduling
• operational constraints
• geotechnical constraints
• computational complexity
• real-time adaptability

Innovation

• simulator-guided LLM
• autonomous scheduling
• open-pit mining
• zero-shot planning
• constraint integration