Firefly Optimization Algorithm (FA) is a novel heuristic stochastic algorithm based on swarm intelligence, which is inspired by the fireflies biochemical and collective behavior. Due to the increment of attractiveness and the fixed step factor, the optimizing results are easily repeated oscillation on the position of local or global extreme value point, and the optimizing accuracy is reduced. Accordingly, this paper puts forward chaos firefly optimization algorithm (CFA), the improved algorithm can improve the diversity of population and the ergodicity of optimization, increase the ability of getting rid of trapped into local minima point. Chaos firefly optimization algorithm is used for the identification of chaotic system parameter; the results show the high accuracy of the algorithm parameter identification.