@article{cpgdtowardstablerulebasedreinforcement, title = {CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models}, author = {Zongkai Liu and Fanqing Meng and Lingxiao Du and Zhixiang Zhou and Chao Yu and Wenqi Shao and Qiaosheng Zhang}, year = {2025}, eprint = {2505.12504}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.12504v1}, }