@article{towardevaluativethinkingmetapolicy, title = {Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models}, author = {Zae Myung Kim and Chanwoo Park and Vipul Raheja and Suin Kim and Dongyeop Kang}, year = {2025}, eprint = {2504.20157}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.20157v2}, }