Chaotic ant swarm optimization (CASO) suffers from premature convergence frequently and low accuracy computation. Therefore, the CASO algorithm is analyzed from cognitive science, and a creative thinking (CT) based CASO(CTCASO) algorithm is proposed. Based on the four stages model in CT process, a framework of the CTCASO algorithm is designed, and the evolution model is adapted, which includes a CT model besides the memory model, and the cognitive model in CASO, to improve the optimization capability of ants. The CTCASO algorithm is applied to some wellknown benchmarks, and experimental results show that the CTCASO algorithm possesses more powerful search capabilities and robustness, meanwhile it does not introduce new parameters and computational complexity.