Summary
Many industries use detailed schedules and plans built from math, but they struggle to update these when unexpected events occur in everyday operations. This paper introduces GenOR-Twin, a system that uses AI language models to translate messy logs and human reports into formal rules that update mathematical planning models on the fly. This means schedules and plans can adjust in real-time to disruptions without losing mathematical guarantees. The system also keeps the digital model and real-world data synchronized, so decisions reflect current conditions. The authors show this works across six different types of scheduling and optimization problems.
What this means in practice
- •For operations planners: Automatically update optimization models in real time when disruptions occur, improving schedule reliability during ongoing operations.
- •For supply chain managers: Incorporate human qualitative reports directly into digital twin models to better adapt supply chains to variable conditions.
Authors
Rahimeh Neamatian Monemi, Shahin Gelareh, Lubin Cui, Nelson Maculan
Abstract
We introduce GenOR-Twin, a neuro-symbolic framework that bridges the translation gap between unstructured operational logs and rigorous mathematical optimization. Our architecture uniquely positions Large Language Models as semantic translators rather than direct solvers, ensuring that the system retains the feasibility guarantees of exact combinatorial methods. { \color{red}We design a dynamic constraint injection mechanism (the runtime translation of qualitative disruption events into formal mathematical constraints) that allows the system to structurally modify the optimization problem's feasibility region in real-time based on qualitative human inputs. The resulting bidirectional coupling---where operational observations update the virtual model state and optimized decisions are reflected back into the Knowledge Graph---satisfies the synchronization requirement of a proper Digital Twin. The framework features an adaptive decision policy} that automatically selects between low-complexity schedule repair and full re-optimization by analyzing the available system slack. Finally, we demonstrate the generalization of this approach across six distinct optimization domains, {\color{red}turning static models into resilient systems that adapt to the operational uncertainty and variability of real-world environments.}