Digital Twins (DTs) are an emerging technology that promises to reduce CPU time and enable multi-query analyses for a variety of multi-scale and multi-physics problems. As such, coupling solution techniques often serve a critical role in both the development and online deployment of DTs. One source of improvement in computational efficiency is the invocation of data-driven methods. However, they are still largely used as stand-alone simulation tools and their coupling to conventional methods and other data-driven methods for multi-scale, multi-physics simulations remain underdeveloped both mathematically and algorithmically. The goal of this session is to bring together researchers working on mathematical and software challenges involved in the rigorous and agile coupling of arbitrary combinations of data-driven and conventional methods. In scope and of interest to this minisymposium are traditional coupling techniques between full-order models as well as coupling techniques between surrogate subdomain models, both intrusive and non-intrusive. Additionally, coupling techniques between either full- or reduced- order models that treat the interface coupling operator itself as a surrogate are additionally of interest, as well as software that supports the efficient implementation of these various methods.