This study examines recent advancements in soil erosion modeling using the Revised Universal Soil Loss Equation (RUSLE), integrated with remote sensing and artificial intelligence techniques. Adopting a Systematic Literature Review (SLR) and bibliometric analysis via Bibliometrix in R, 63 articles were analyzed from an initial 359 based on strict selection criteria. Findings reveal a sharp rise in publications since 2017, especially involving machine learning and Google Earth Engine (GEE) platforms. Co-authorship analysis highlights significant international collaboration, particularly between Asia and Europe. Concept maps and co-word analyses show a shift from traditional RUSLE applications toward AI and big data approaches. Thematic evolution further indicates a growing focus on climate change and the Sustainable Development Goals (SDGs). The review's primary contribution lies in its explicit identification of critical research priorities by pinpointing key gaps: the limited use of field validation, weak SDG integration, and fragmented international research networks. By highlighting these deficiencies, this study provides a clear roadmap for future investigations, steering the field toward more inclusive, data-driven, and validated approaches to address global land degradation and climate resilience. Overall, the study contributes to the development of more effective erosion mitigation models through technological integration and international collaboration.