Forest regeneration at large-scales is one of the main paths to achieving the ongoing ambitious restoration commitments. Thus, the identification of the main drivers of this process in agricultural landscapes is critical to understand the drivers determining restoration success. A growing number of studies have explored the biophysical and, less often, the socioeconomic drivers of forest regeneration using remote sensing approaches, but have not directly considered the influence of farmers' decisions in spatial prediction models of forest regeneration. We explored the influence of biophysical and socioeconomic drivers on forest regeneration in a rural landscape of Southeastern Brazil, where native forest cover increased by 7.7%. We evaluated forest regeneration through the analysis of time series of multi-temporal satellite images and socioeconomic information obtained through a Social Survey with 47 landowners, using each farm as the study unit. Natural forest regeneration was mainly favored by lower land suitability for agriculture and higher proximity (lower distances) to forest remnants, as well by higher numbers of land-uses types in the farm and lower economic dependence of landowners from the farm income. Our results emphasize the importance of considering farmers' decisions on predictive models of natural forest regeneration, which are critically needed to guide the implementation of large-scale forest restoration initiatives in agricultural landscapes.