@article{segmentaladvantageestimationenhancingppo, title = {Segmental Advantage Estimation: Enhancing PPO for Long-Context LLM Training}, author = {Xue Gong and Qi Yi and Ziyuan Nan and Guanhua Huang and Kejiao Li and Yuhao Jiang and Ruibin Xiong and Zenan Xu and Jiaming Guo and Shaohui Peng and Bo Zhou}, year = {2026}, eprint = {2601.07320}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.07320}, }