Wang X, Song Y, Tian Z, Liu B, Luo T, Huang M. DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answering. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 25];40(40):33683-91. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40658