The influence of tactical evolution on agents’ operational effectiveness in an air-to-ground attack (ATGA) mission is investigated. Firstly, the penetration-attack mission of 20-drones-swarm vs 10 air defense systems is modeled and a distributed decision making model for ATGA mission is constructed for the swarm. The decision making model contains several fuzzy inference systems(FISs), which consist of membership functions and inference rules, both presented in the form of “tactical genes”. Then “tactical genes” are optimized by offline evolutionary computing, and a substantial enhancement of agents’ operational effectiveness is witnessed in experimental results. Based on a high performance computing cluster and evolutionary computing framework, the idea that tactical genes can be optimized in an online manner is proved. Finally, experimental results show that shorter evolution period brings higher operational effectiveness.