Continuously Updating Digital Twins using Large Language Models

Harry Amad, Nicolás Astorga, Mihaela Van Der Schaar
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1343-1366, 2025.

Abstract

Digital twins are models of real-world systems that can simulate their dynamics in response to potential actions. In complex settings, the state and action variables, and available data and knowledge relevant to a system can constantly change, requiring digital twins to continuously update with these changes to remain relevant. Current approaches struggle in this regard, as they require fixed, well-defined modelling environments, and they cannot adapt to novel variables without re-designs, or incorporate new information without re-training. To address this, we frame digital twinning as an in-context learning problem using large language models, enabling seamless updates to the twin at inference time. We develop CALM-DT, a Context-Adaptive Language Model-based Digital Twin that can accurately simulate across diverse state-action spaces using in-context learning alone by utilising fine-tuned encoders for sample retrieval. We empirically demonstrate CALM-DT’s competitive performance with existing digital twin approaches, and its unique ability to adapt to changes in its modelling environment without parameter updates.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-amad25a, title = {Continuously Updating Digital Twins using Large Language Models}, author = {Amad, Harry and Astorga, Nicol\'{a}s and Van Der Schaar, Mihaela}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {1343--1366}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/amad25a/amad25a.pdf}, url = {https://proceedings.mlr.press/v267/amad25a.html}, abstract = {Digital twins are models of real-world systems that can simulate their dynamics in response to potential actions. In complex settings, the state and action variables, and available data and knowledge relevant to a system can constantly change, requiring digital twins to continuously update with these changes to remain relevant. Current approaches struggle in this regard, as they require fixed, well-defined modelling environments, and they cannot adapt to novel variables without re-designs, or incorporate new information without re-training. To address this, we frame digital twinning as an in-context learning problem using large language models, enabling seamless updates to the twin at inference time. We develop CALM-DT, a Context-Adaptive Language Model-based Digital Twin that can accurately simulate across diverse state-action spaces using in-context learning alone by utilising fine-tuned encoders for sample retrieval. We empirically demonstrate CALM-DT’s competitive performance with existing digital twin approaches, and its unique ability to adapt to changes in its modelling environment without parameter updates.} }
Endnote
%0 Conference Paper %T Continuously Updating Digital Twins using Large Language Models %A Harry Amad %A Nicolás Astorga %A Mihaela Van Der Schaar %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-amad25a %I PMLR %P 1343--1366 %U https://proceedings.mlr.press/v267/amad25a.html %V 267 %X Digital twins are models of real-world systems that can simulate their dynamics in response to potential actions. In complex settings, the state and action variables, and available data and knowledge relevant to a system can constantly change, requiring digital twins to continuously update with these changes to remain relevant. Current approaches struggle in this regard, as they require fixed, well-defined modelling environments, and they cannot adapt to novel variables without re-designs, or incorporate new information without re-training. To address this, we frame digital twinning as an in-context learning problem using large language models, enabling seamless updates to the twin at inference time. We develop CALM-DT, a Context-Adaptive Language Model-based Digital Twin that can accurately simulate across diverse state-action spaces using in-context learning alone by utilising fine-tuned encoders for sample retrieval. We empirically demonstrate CALM-DT’s competitive performance with existing digital twin approaches, and its unique ability to adapt to changes in its modelling environment without parameter updates.
APA
Amad, H., Astorga, N. & Van Der Schaar, M.. (2025). Continuously Updating Digital Twins using Large Language Models. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:1343-1366 Available from https://proceedings.mlr.press/v267/amad25a.html.

Related Material