Abstract：In this paper，an improved adaptive genetic algorithm is presented in order to resolve the problem that traditional GA is prone to premature and is ineficient in application of the standard genetic algorithm to the Multi— modal Function optimization problems in the final stage．On the basis of evalution of several common premature index for the population，a new premature index is put forward．Then an improved adaptive genetic algorithm is presented．The simulation shows our new method has faster evolution speed and robustness，and reaches a general optimal solution．