@article{NeurIPS'26:L2RR,
    author = {Zhang, Zhen-Yu and Zhang, Jiandong and Yao, Huaxiu and Niu, Gang and Sugiyama, Masashi},
    title = {Dataset Mismatch Matters in Group Relative Policy Optimization for Reinforcement Learning from Verifiable Rewards},
    journal = {Advances in Neural Information Processing Systems (NeurIPS)},
    volume = {39},
    pages = {in press},
    year = {2026}
}