Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective

@article{feng2026,
  title = {Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective},
  author = {Zhang, Feng and Ma, Xinhong and Dong, Ziqiang and Leng, XI and Zhao, Jianfei and Sun, Xin and Yang, Yang and Jiang, Guanjun},
  journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year = {2026},
  month = {Jan},
}

Zhang, Feng et al. (2026). Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing.

Zhang, Feng, et al.. "Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026.

Zhang, Feng, et al.. "Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (2026).

Zhang, Feng et al., 2026. Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing.

TY  - JOUR
TI  - Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
AU  - Zhang, Feng
AU  - Ma, Xinhong
AU  - Dong, Ziqiang
AU  - Leng, XI
AU  - Zhao, Jianfei
AU  - Sun, Xin
AU  - Yang, Yang
AU  - Jiang, Guanjun
PY  - 2026
JO  - Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
ER  -