Researchers have developed a new approach to understand relationships between groups of variables in complex systems. Their method uses variational inference to simultaneously identify both the clusters and causal structures within these systems. This is useful for applications like brain imaging and climate modeling, where interactions among groups are more meaningful than individual variable relationships. The authors demonstrate their approach on synthetic and real data sets. --- Why it matters: This matters because it provides a new tool for understanding complex systems, which can inform the development of more accurate models in fields like neuroscience and environmental science. Source: https://arxiv.org/abs/2608.22212