@article{qualityconstrainedentropymaximizationpol, title = {Quality-constrained Entropy Maximization Policy Optimization for LLM Diversity}, author = {Haihui Pan and Yuzhong Hong and Kaichen Zhang and Shaoke Lv and Junwei Bao and Hongfei Jiang and Yang Song}, year = {2026}, eprint = {2602.15894}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.15894}, }