Layer assignment is an important post-layout optimization technique in Very Large Scale Integrated-circuit (VLSI) layout automation. It re-assigns wire segments in a routing solution to appropriate layers ot achieve certain optimization objectives. This paper focuses on investigating the layer assignment problem with application to via minimization,which is known to be NP-complete. In this paper a knowledge-based genetic algorithm for the layer assignment problem is proposed, with the aim of utilizing domain- specific knowledge to speedup the process of evolution and to improve the quality of solutions.Experimental results show that this knowledge-based genetic algorithm can consistently produce the same or better results than a heuristic algorithm and a traditional genetic algorithm.