Multicellular organisms, such as plants, are characterized by highly specialized and tightly regulated cell populations, establishing specific morphological structures and executing distinct functions. Gene regulatory networks (GRNs) describe condition-specific interactions of transcription factor (TF) regulating the expression of target genes, underpinning these specific functions. As efficient and validated methods to identify cell-type specific GRNs from single-cell data in plants are lacking, limiting our understanding of the organization of specific cell-types in both model species and crops, we developed MINI-EX (Motif-Informed Network Inference based on single-cell EXpression data), an integrative approach to infer cell-type specific networks in plants. MINI-EX uses single-cell transcriptomic data to define expression-based networks and integrates TF motif information to filter the inferred regulons, resulting in networks with increased accuracy. Next, regulons are assigned to different cell-types, leveraging cell-specific expression, and candidate regulators are prioritized using network centrality measures, functional annotations, and expression specificity. This embedded prioritization strategy offers a unique and efficient means to unravel signaling cascades in specific cell-types controlling a biological process of interest. We demonstrate MINI-EX's stability towards input data sets with low number of cells and its robustness towards missing data, and we show it infers state-of-the-art networks with a better performance compared to related single-cell network tools. MINI-EX successfully identifies key regulators controlling root development in Arabidopsis and rice, and governing ear development in maize, enhancing our understanding of cell-type specific regulation and unraveling the role of different regulators controlling the development of specific cell-types in plants.