SIPO: Unifying Reinforcement Learning with On-Policy Self-Di
arXiv:2609.36742v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a stand
推荐理由：研究进展具备参考价值，值得关注
arXiv:2609.36742v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a stand
推荐理由：研究进展具备参考价值，值得关注