TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning

@article{wenxuan2026,
  title = {TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning},
  author = {Jiang, Wenxuan and Zuo, Yuxin and Zhang, Zijian and Wu, Xuecheng and Fan, Zining and Liu, Wenxuan and Chen, Li and Li, Xiaoyu and Cao, Xuezhi and Jin, Xiaolong and Liu, Ninghao},
  journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year = {2026},
  month = {Jan},
}

Jiang, Wenxuan et al. (2026). TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing.

Jiang, Wenxuan, et al.. "TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026.

Jiang, Wenxuan, et al.. "TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (2026).

Jiang, Wenxuan et al., 2026. TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing.

TY  - JOUR
TI  - TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning
AU  - Jiang, Wenxuan
AU  - Zuo, Yuxin
AU  - Zhang, Zijian
AU  - Wu, Xuecheng
AU  - Fan, Zining
AU  - Liu, Wenxuan
AU  - Chen, Li
AU  - Li, Xiaoyu
AU  - Cao, Xuezhi
AU  - Jin, Xiaolong
AU  - Liu, Ninghao
PY  - 2026
JO  - Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
ER  -