Integrated large language models and digital twin-based decision support in closed-loop supply chain operations: green steel transition case study

The green steel transition requires corporates to operate closed-loop supply chains (CLSCs) that involve operational decisions under heterogeneous data. Although decision models have shifted CLSC operations towards advanced analytics and optimisation, challenges remain in automatically interpreting natural-language requests, enabling data-driven reasoning, and communicating outcomes for actionable decision-making. Motivated by recent progress in large language models (LLMs), we propose an intelligent digital twin-based decision-support method (LMiDTSC) to automatically interpret, reason, and address CLSC operational tasks, and synchronise physical and digital CLSC resources. We develop a knowledge graph, a benchmark, and an accurate query-explanation consistency (AQEC) metric to operate the method and evaluate its effectiveness in supporting decisions on steel distribution and scrap collection. Across focal operational tasks, LMiDTSC outperforms baselines (e.g. GPT-5.2) by 82.73% in AQEC, while its fine-tune outperforms backbones using proprietary models by 93.17% in AQEC. This study advances decision support systems and AI-enabled operations research by integrating LLMs and digital twins for computerised decisions in CLSC operations. This study suggests supply chain practitioners should consider high-performing LLMs for complex operational tasks and exercise caution in scaling in-context learning prompts. Finally, policymakers can accelerate the implementation of such integrated decision support systems by promoting industrial symbiosis and workforce training.