The aerial Guidance-Attack Matching (GAM) focuses on the allocating of weapon units guidance units and targets in order to maximize the effectiveness of the multiple combat agents task coalition.The guidance-attack matching process of multiple combat agents based on integrated communication mode was analyzed a constrained optimization model was proposed for the problem and the nested genetic algorithm based on tabu policy was designed to solve the model.The outer-loop of GA was used to search for the optimum weapon-guidance matching and the inner-loop of GA used to search for the optimum weapon-target allocation.Considering the discrete characteristics of the problem the coding rules crossover operators mutation operators and tabu policy were designed.The experimental results show that the proposed algorithm can solve the three-dimensional variable GAM problem effectively.