@article{rubricemmetarlwithrubricguidedpolicydeco, title = {RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards}, author = {Gaotang Li and Bhavana Dalvi Mishra and Zifeng Wang and Jun Yan and Yanfei Chen and Chun-Liang Li and Long T. Le and Rujun Han and George Lee and Hanghang Tong and Chen-Yu Lee and Tomas Pfister}, year = {2026}, eprint = {2605.10899}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.10899}, }