Multi-Agent Digital Twins for Strategic Decision-Making using Active Inference
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911592193458176 |
|---|---|
| author | Mancinelli, Francesco Maria Torzoni, Matteo Maisto, Domenico Donnarumma, Francesco Corigliano, Alberto Pezzulo, Giovanni Manzoni, Andrea |
| author_facet | Mancinelli, Francesco Maria Torzoni, Matteo Maisto, Domenico Donnarumma, Francesco Corigliano, Alberto Pezzulo, Giovanni Manzoni, Andrea |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12657 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Digital Twins for Strategic Decision-Making using Active Inference Mancinelli, Francesco Maria Torzoni, Matteo Maisto, Domenico Donnarumma, Francesco Corigliano, Alberto Pezzulo, Giovanni Manzoni, Andrea Computational Engineering, Finance, and Science 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. |
| title | Multi-Agent Digital Twins for Strategic Decision-Making using Active Inference |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2604.12657 |