A new MOX Report entitled “Multi-Agent Digital Twins for strategic decision-making using Active Inference” by Mancinelli, F. M.; Torzoni, M.; Maisto, D.; Donnarumma, F.; Corigliano, A.; Pezzulo, G.; Manzoni, A. has appeared in the MOX Report Collection.
Check it out here: https://www.mate.polimi.it/biblioteca/add/qmox/34-2026.pdf
Abstract: Active Inference is an emerging framework providing a quantitative account of behavioral processes in neuroscience and a principled approach to decision-making under uncertainty. Its application to agency problems is natural, offering an autopoietic interpretation of action while addressing classical challenges such as the exploration-exploitation trade-off. Recently, Active Inference has been applied to digital twin scenarios for adaptive and predictive modeling of complex systems. In this work, we extend Active Inference to multi-agent digital twins in which agents interact within a shared environment while maintaining decentralized generative models. Our multi-agent framework features two innovations: (i) contextual inference to improve adaptability in dynamic environments, and (ii) the integration of streaming machine learning within agents’ generative structures, enabling tunable goal-oriented behavior while preserving efficiency an! d scalabi lity. The framework is illustrated through a Cournot competition example, providing a digital twin representation of a socio-economic system and highlighting its potential for coordinated decision-making in multi-agent contexts.
