Leveraging Large Language Models for Enhanced Digital Twin Modeling: Trends, Methods, and Challenges

TL;DR

This paper addresses the challenge of advancing digital twins through the integration of large language models (LLMs). It introduces a unified description-prediction-prescription framework and a taxonomy of LLM functionalities to enhance descriptive, predictive, and prescriptive modeling within digital twins, including data collection, generation, analysis, scenario design, and generative control. A case study demonstrates an LLM-powered enterprise digital twin system for optimizing a software development process, illustrating automatic modeling and workflow optimization with human-friendly explanations. The authors discuss challenges such as data heterogeneity, model updates, interaction efficiency, and safety, and offer directions for tooling, data fusion, incremental updates, and retrieval-augmented generation to enable scalable, trustworthy LLM-enhanced digital twins. Overall, the work provides a structured, actionable roadmap for researchers and practitioners aiming to deploy LLM-enabled digital twin systems in complex industrial settings.

Abstract

Digital twin technology is a transformative innovation driving the digital transformation and intelligent optimization of manufacturing systems. By integrating real-time data with computational models, digital twins enable continuous monitoring, simulation, prediction, and optimization, effectively bridging the gap between the physical and digital worlds. Recent advancements in communication, computing, and control technologies have accelerated the development and adoption of digital twins across various industries. However, significant challenges remain, including limited data for accurate system modeling, inefficiencies in system analysis, and a lack of explainability in the interactions between physical and digital systems. The rise of large language models (LLMs) offers new avenues to address these challenges. LLMs have shown exceptional capabilities across diverse domains, exhibiting strong generalization and emergent abilities that hold great potential for enhancing digital twins. This paper provides a comprehensive review of recent developments in LLMs and their applications to digital twin modeling. We propose a unified description-prediction-prescription framework to integrate digital twin modeling technologies and introduce a structured taxonomy to categorize LLM functionalities in these contexts. For each stage of application, we summarize the methodologies, identify key challenges, and explore potential future directions. To demonstrate the effectiveness of LLM-enhanced digital twins, we present an LLM-enhanced enterprise digital twin system, which enables automatic modeling and optimization of an enterprise. Finally, we discuss future opportunities and challenges in advancing LLM-enhanced digital twins, offering valuable insights for researchers and practitioners in related fields.

Figures (11)

• Figure 1: Foundamental architecture of digital twins.
• Figure 2: Number of papers published per year over the past ten years.
• Figure 3: Architecture of the ACP approach.
• Figure 4: Architecture of the description-prediction-prescription framework.
• Figure 5: Tasks that can be enhanced by LLMs, where LLMs play different roles in enhancing descriptive, predictive, prescriptive modeling.