Extend-LTO (Exploitation of existing data and investigation of irradiation damage and recovery mechanisms in LWR RPV steels containing high Ni and Mn for extended Long-Term Operation) aims to enhance capability of advanced predictive methodologies (APM) for irradiation embrittlement and recovery by annealing in LWR-RPV steels through integration of physics-based models with advanced characterization and machine learning. It will extend ENTENTE database with new data generated on high Ni-Mn PWR-RPV welds and LYRA-10 RPV materials in reference, irradiated, post-irradiation annealed, and re-irradiated conditions, as well as large data from recent STRUMAT-LTO and FRACTESUS projects. The extended ENTENTE datasets will be exploited using artificial neural-networks to improve microstructure-property correlations and prediction of irradiation embrittlement and recovery by annealing for safe extended LTO of LWRs.