WANG, Xinyi; SONG, Yiping; TIAN, Zhiliang; LIU, Bo; LUO, Tingjin; HUANG, Minlie. DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 40, p. 33683–33691, 2026. DOI: 10.1609/aaai.v40i40.40658. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40658. Acesso em: 25 may. 2026.