@article{beyondentropycorrectnessawareadvantagesh, title = {Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization}, author = {Weiwen Xu and Jia Liu and Hou Pong Chan and Long Li and Deng Cai and Min Chen and Hao Zhang}, year = {2026}, eprint = {2607.14614}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.14614}, }