Multi-Agent Digital Twins for Strategic Decision-Making using Active Inference
For researchers in multi-agent systems and digital twins, this provides a principled framework for decentralized decision-making under uncertainty, though the contribution is incremental.
The paper extends Active Inference to multi-agent digital twins, introducing contextual inference and streaming ML for adaptive, scalable decision-making. Demonstrated on a Cournot competition example, it shows potential for coordinated strategic decisions in socio-economic systems.
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 and scalability. 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.