An important advantage of cold-formed steel is the great flexibility of cross-sectional profiles and sizes available to structural steel designers. However, this flexibility makes the selection of the most economical section difficult for a particular situation. In this study. a micro Genetic Algorithm (mu-GA) is used to find an optimum cross-section of cold-formed steel beams. The mu-GA is one of the improved form of GAs, to reduce iteration and computing resources by using small populations. The design curves are generated for optimum values of the thickness and the web flat-depth-to-thickness ratio for unbraced beams under uniformly distributed load. As numerical results. the optimum design curves are presented for various load level. (C) 2004 Elsevier Ltd. All rights reserved.