@article{pagmultiturnreinforcedllmselfcorrection, title = {PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier}, author = {Yuhua Jiang and Yuwen Xiong and Yufeng Yuan and Chao Xin and Wenyuan Xu and Yu Yue and Qianchuan Zhao and Lin Yan}, year = {2025}, eprint = {2506.10406}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.10406v1}, }