In response to the increasing complexity of Multi-Domain Operations (MDO), this paper presents a cognitive wargaming architecture integrating AI agents for scenario generation, simulation control, and decision support. Grounded in the DOMINION framework and enhanced by the “AI Agents as Knowledge Navigators” concept, the system enables human-machine teaming across land, maritime, air, space, cyber, and information domains. It supports training and planning through adaptive simulations that reflect doctrinal reasoning and dynamic threat landscapes. The architecture applies transformer-based NLP, reinforcement learning, and knowledge graphs to synthesize doctrinal content and mission data in real-time. A featured scenario demonstrates maritime interdiction under electronic warfare stress, where AI agents adjust tactics and generate recommendations through automated red/blue teaming. Compatibility with NATO’s C2Sim and simulation engines—such as Command: Modern Operations—ensures interoperability with existing M&S infrastructure. This approach contributes to NATO’s objectives in agility, interconnectivity, and cognitive preparedness by turning knowledge management into an operational capability. The framework supports scalable wargaming from training to operational experimentation and is suitable for both physical and virtual environments.

AI-Driven Wargaming Framework for Multi-Domain Readiness and Decision Support

Paolo Gemelli;laura Pagani;
2025-01-01

Abstract

In response to the increasing complexity of Multi-Domain Operations (MDO), this paper presents a cognitive wargaming architecture integrating AI agents for scenario generation, simulation control, and decision support. Grounded in the DOMINION framework and enhanced by the “AI Agents as Knowledge Navigators” concept, the system enables human-machine teaming across land, maritime, air, space, cyber, and information domains. It supports training and planning through adaptive simulations that reflect doctrinal reasoning and dynamic threat landscapes. The architecture applies transformer-based NLP, reinforcement learning, and knowledge graphs to synthesize doctrinal content and mission data in real-time. A featured scenario demonstrates maritime interdiction under electronic warfare stress, where AI agents adjust tactics and generate recommendations through automated red/blue teaming. Compatibility with NATO’s C2Sim and simulation engines—such as Command: Modern Operations—ensures interoperability with existing M&S infrastructure. This approach contributes to NATO’s objectives in agility, interconnectivity, and cognitive preparedness by turning knowledge management into an operational capability. The framework supports scalable wargaming from training to operational experimentation and is suitable for both physical and virtual environments.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/1316316
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact