Olympiad-level formal mathematical reasoning with reinforcement learning
已完结10由 KeYanDog 发布于 2026/1/8 17:51:59
DOI:10.1038/s41586-025-09833-y
作者:Thomas Hubert, Rishi Mehta, Laurent Sartran, Miklós Z. Horváth, Goran ?u?i?, Eric Wieser, Aja Huang, Julian Schrittwieser, Yannick Schroecker, Hussain Masoom, Ottavia Bertolli, Tom Zahavy, Amol Mand
文献类型:期刊论文
补充材料:只需要正文