The objective of this study is to obtain the optimum design for reinforced concrete beams in terms of cross section dimensions and reinforcement details using a fine tuned Artificial Bee Colony (ABC) Algorithm while still satisfying the constraints of the ACI Code (2008) ( ACI Committee 318, 2008). The ABC algorithm used in this paper has been slightly modified to include a Variable Changing Percentage (VCP) that further improves its performance when dealing with members consisted of multiple variables. The objective function is the total cost of the beam which includes the cost of concrete, formwork and reinforcing steel bars. The design variables used are beam width, beam height, number and diameter of reinforcing bars and top cutoff reinforcing bars as well as the diameter of stirrups , and design constraints can include strain, stress and sizing constraints. The optimal design is performed by using the Sequential Quadratic Programming algorithm. All computational implementation was made in MATLAB® computational environment. The emphasis is particularly placed on the practical applicability of the optimization technique in engineering practice. Graphical results are shown for optimal sizing of a reinforced concrete beam of rectangular cross section for different bending moments. For validating of the proposed model the results are compared with those found in literature and usual practice of beam construction.