Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

@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},
}

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.

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.

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).

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.

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
ER  -