In this study, an improved particle swarm optimization (PSO) algorithm, including 4 types of new velocity updating formulae (each is equal to the traditional PSO), was introduced. This algorithm was called the reverse direction supported particle swarm optimization (RDS-PSO) algorithm. The RDS-PSO algorithm has the potential to extend the diversity and generalization of traditional PSO by regulating the reverse direction information adaptively. To implement this extension, 2 new constants were added to the velocity update equation of the traditional PSO, and these constants were regulated through 2 alternative procedures, i.e. max--min-based and cosine amplitude-based diversity-evaluating procedures. The 4 most commonly used benchmark functions were used to test the general optimization performances of the RDS-PSO algorithm with 3 different velocity updates, RDS-PSO without a regulating procedure, and the traditional PSO with linearly increasing/decreasing inertia weight. All PSO algorithms were also implemented in 4 modes, and their experimental results were compared. According to the experimental results, RDS-PSO 3 showed the best optimization performance.