System of Systems Engineering (SoSE) studies how independent constituent sys-tems interact to generate emergent capabilities. However, it is challenging linking the studyoperations and SoSE to software implementation and agent-based simulations. This paperconsiders communication as the primary architectural concern and examines how softwarearchitectures can improve SoS modelling and simulation. In particular, by relating soft-ware architectures to Observe–Orient–Decide–Act (OODA) loops, which are a promisingstructure for aligning communication, decision logic, and agent interactions with modularand traceable agent architectures. The goal of this work is to explore how communicationwithin SoS architectures can be better structured, represented, and analysed through soft-ware engineering and agent-based modelling frameworks in the context of hierarchical andcooperative operational environments, where information exchange directly influences sys-tem performance and emergent outcomes.

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 trace-ability, and comparative evaluation of emergence, coordination, and operational perfor-mance. 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 andArtificial Intelligence (AI) integration at the decision layer. A wildfire suppression scenariois used for the study, modelling firefighting crews, aircraft, helicopters, bulldozers, and anincident commander as OODA-driven agents. Results show that OODA-based agents exhibitcoherent and traceable team behaviours, adaptive task switching, and communication-drivencoordination, supporting the study of emergence and interoperability in SoS operations. TheDecision stage is designed for future improvements in the form of learning-based AI and LargeLanguage Models to enhance autonomy and operational fidelity.