@article{yuqiao2026,
title = {Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies},
author = {Tan, Yuqiao and Wang, Minzheng and He, Shizhu and Liao, Huanxuan and Zhao, Chengfeng and Liang, Tian and Zhao, Jun and Liu, Kang},
journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
year = {2026},
month = {Jan},
doi = {10.18653/2026.emnlp-main.1173},
url = {https://doi.org/10.18653/2026.emnlp-main.1173},
}
Tan, Yuqiao et al. (2026). Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/2026.emnlp-main.1173
Tan, Yuqiao, et al.. "Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026, https://doi.org/10.18653/2026.emnlp-main.1173.
Tan, Yuqiao, et al.. "Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (2026). https://doi.org/10.18653/2026.emnlp-main.1173
Tan, Yuqiao et al., 2026. Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. Available at: <https://doi.org/10.18653/2026.emnlp-main.1173>.
TY - JOUR
TI - Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
AU - Tan, Yuqiao
AU - Wang, Minzheng
AU - He, Shizhu
AU - Liao, Huanxuan
AU - Zhao, Chengfeng
AU - Liang, Tian
AU - Zhao, Jun
AU - Liu, Kang
PY - 2026
JO - Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
DO - 10.18653/2026.emnlp-main.1173
UR - https://doi.org/10.18653/2026.emnlp-main.1173
ER -