Zhu, G. et al. 2026. FedGRPO: Privately Optimizing Foundation Models with Group-Relative Rewards from Domain Clients. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 24 (Mar. 2026), 19487–19495. DOI:https://doi.org/10.1609/aaai.v40i24.39027.