The primary objective of military air combat simulators is to equip pilots with the tactical skills necessary for real-world operations. To achieve this, the simulation of adversary forces (“red forces”) in a realistic and valid simulation environment is essential for the training of military personnel. Typically, simulators cover mainly one domain and focus on understanding one's own weapon systems. Examples include flight simulators for training fighter pilots, UAV operator simulators and vehicle simulators [1]. Consequently, adversary behavior is often depicted rudimentarily and rule-based, lacking the detail and adaptability necessary for effective training of fighter pilots and for validating tactics [2]. For optimal training, a cross-domain, verified, and validated simulator must accurately represent both own and adversary weapon systems with all their components. Training and tactics validation also requires challenging opponents with explainable, situation-adaptive, tactically intelligent behavior [3, 4]. Our concept is based on mapping the opponent as agent based CGF (Computer Generated Forces) with behavior based on explainable AI methods to tackle this task. While there are promising approaches for CGF in Air-to-Air BVR (Beyond Visual Range) scenarios at our institute [5–8], this paper focuses on the extension of the existing simulation framework and adapting the concept of the behavior model to the Air Defense domain. Along with that, necessary components of an IADS (Integrated Air Defense System) are identified and approaches on how they can be implemented in a comprehensive simulation environment are given. Use cases for competitive modeling and simulation of GBADS (Ground Based Air Defense Systems) include training pilots in missions e.g. SEAD (Suppression of Enemy Air Defense), evaluating tactics, and exploring future concepts (“blue forces”).