Modular OODA-Based Agents for Scalable and Adaptive AI in System-of-Systems Modelling and Simulation

Abstract

Abstract. Agent-Based Modelling and Simulation (ABMS) is widely used in System-of-Systems (SoS) studies to represent constituent systems operating in dynamic environments. However, the absence of standardised agent architectures hinders scalability, behaviour traceability, and comparative evaluation of emergence, coordination, and operational performance. This work introduces a modular agent design based on Observe–Orient–Decide–Act (OODA) loops as a framework for SoS simulations, enabling transparent information flow and Artificial Intelligence (AI) integration at the decision layer. A wildfire suppression scenario is used for the study, modelling firefighting crews, aircraft, helicopters, bulldozers, and an incident commander as OODA-driven agents. Results show that OODA-based agents exhibit coherent and traceable team behaviours, adaptive task switching, and communication-driven coordination, supporting the study of emergence and interoperability in SoS operations. The Decision stage is designed for future improvements in the form of learning-based AI and Large Language Models to enhance autonomy and operational fidelity.