In this paper, we propose a knowledge-based method for generating CNC torch path for laser cutting of the outlines of planar shapes. The proposed method consists of two main phases: laser cutting knowledge construction and CNC torch path generation using the knowledge. In the first phase, cutting experiments are conducted on various operating parameters, and then empirical data are stored and analyzed to make up the knowledge of laser cutting. With this knowledge, we can inquire what a kerf width is for specific operating parameters. In the second phase, using the knowledge of laser cutting, CNC torch path is generated for cutting the outlines of the given planar shapes. This phase is basically based on the offset generation of each outline by a sequence of arc splines, where the offset distance is the same as the half of the kerf width determined from the constructed knowledge. The proposed method based on laser cutting knowledge makes full use of arc interpolators in CNC torch path generation. The method can efficiently reduce the number of path segments while keeping the torch path within the desired accuracy.