Abstract. The increasing need for cross sections far from the valley of stability poses a challenge for nuclear reaction models. So far, predictions of cross sections have relied on more or less phenomenological approaches, depending on parameters adjusted to available experimental data or deduced from systematic expressions. While such predictions are expected to be reliable for nuclei not too far from the experimentally known regions, it is clearly preferable to use more fundamental approaches, based on sound physical principles, when dealing with very exotic nuclei. Thanks to the high computer power available today, all the ingredients required to model a nuclear reaction can now be (and have been) microscopically (or semi-microscopically) determined starting from the information provided by a nucleon-nucleon effective interaction. This concerns nuclear masses, optical model potential, nuclear level densities, photon strength functions, as well as fission barriers. All these nuclear model ingredients, traditionally given by phenomenological expressions, now have a microscopic counterpart implemented in the TALYS nuclear reaction code. We are thus now able to perform fully microscopic cross section calculations. The quality of these ingredients and the impact of using them instead of the usually adopted phenomenological parameters will be discussed. Perspectives for the coming years will be drawn on the improvements one can expect.