A Monte Carlo method based on a density-of-states sampling is proposed for study of arbitrary statistical mechanical ensembles in a continuum. A random walk in the two-dimensional space of particle number and energy is used to estimate the density of states of the system; this density of states is continuously updated as the random walk visits individual states. The validity and usefulness of the method are demonstrated by applying it to the simulation of a Lennard-Jones fluid. Results for its thermodynamic properties, including the vapor-liquid phase coexistence curve, are shown to be in good agreement with high-accuracy literature data.