This paper proposes a novel hybrid algorithm named Adaptive Cat Swarm Optimization (ACSO). It combines the benefits of two swarm intelligence algorithms, CSO and APSO, and presents better search results. Firstly, some strategies are implemented to improve the performance of the proposed hybrid algorithm. The tracing radius of the cat group is limited, and the random number parameter r is adaptive adjusted. In addition, a scaling factor update method, called a memory factor y, is introduced into the proposed algorithm. They can be learnt very well so as to jump out of local optimums and speed up the global convergence. Secondly, by comparing the proposed algorithm with PSO, APSO, and CSO, 23 benchmark functions are verified by simulation experiments, which consists of unimodal, multimodal, and fixed-dimension multimodal. The results show the effectiveness and efficiency of the innovative hybrid algorithm. Lastly, the proposed ACSO is utilized to solve the Vehicle Routing Problem (VRP). Experimental findings also reveal the practicability of the ACSO through a comparison with certain existing methods.