@article{250511225, title = {HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization}, author = {Chengyu Huang and Zhengxin Zhang and Claire Cardie}, year = {2025}, eprint = {2505.11225}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.11225v1}, }