Based on model-based methods, a recent class of stochastic search methods for nonlinear deterministic optimization, we propose a new algorithm for simulation optimization over continuous space. The idea is to reformulate the original simulation optimization problem into another optimization problem over the parameter space of the sampling distribution in model-based methods, and then use a direct gradient search on the parameter space to update the sampling distribution. To improve the computational efficiency, we further develop a two-timescale updating scheme that updates the parameter on a slow timescale and estimates the quantities involved in the parameter updating on a fast timescale. We provide numerical experiments to illustrate the performance of our algorithms.