TrajSelector: Harnessing Latent Representations for Effective and Robust Best-of-N Selection in Large Reasoning Models

@article{bin2026,
  title = {TrajSelector: Harnessing Latent Representations for Effective and Robust Best-of-N Selection in Large Reasoning Models},
  author = {Yu, Bin and Wang, Xinming and Lian, Shijie and Li, Haotian and Wu, Changti and Hu, Ruina and Wang, Bailing and Wei, Yuliang and Chen, Kai},
  journal = {Findings of the Association for Computational Linguistics: EMNLP 2026},
  year = {2026},
  month = {Jan},
  doi = {10.18653/2026.findings-emnlp.214},
  url = {https://doi.org/10.18653/2026.findings-emnlp.214},
}

Yu, Bin et al. (2026). TrajSelector: Harnessing Latent Representations for Effective and Robust Best-of-N Selection in Large Reasoning Models. Findings of the Association for Computational Linguistics: EMNLP 2026. https://doi.org/10.18653/2026.findings-emnlp.214

Yu, Bin, et al.. "TrajSelector: Harnessing Latent Representations for Effective and Robust Best-of-N Selection in Large Reasoning Models." Findings of the Association for Computational Linguistics: EMNLP 2026, 2026, https://doi.org/10.18653/2026.findings-emnlp.214.

Yu, Bin, et al.. "TrajSelector: Harnessing Latent Representations for Effective and Robust Best-of-N Selection in Large Reasoning Models." Findings of the Association for Computational Linguistics: EMNLP 2026 (2026). https://doi.org/10.18653/2026.findings-emnlp.214

Yu, Bin et al., 2026. TrajSelector: Harnessing Latent Representations for Effective and Robust Best-of-N Selection in Large Reasoning Models. Findings of the Association for Computational Linguistics: EMNLP 2026. Available at: <https://doi.org/10.18653/2026.findings-emnlp.214>.

TY  - JOUR
TI  - TrajSelector: Harnessing Latent Representations for Effective and Robust Best-of-N Selection in Large Reasoning Models
AU  - Yu, Bin
AU  - Wang, Xinming
AU  - Lian, Shijie
AU  - Li, Haotian
AU  - Wu, Changti
AU  - Hu, Ruina
AU  - Wang, Bailing
AU  - Wei, Yuliang
AU  - Chen, Kai
PY  - 2026
JO  - Findings of the Association for Computational Linguistics: EMNLP 2026
DO  - 10.18653/2026.findings-emnlp.214
UR  - https://doi.org/10.18653/2026.findings-emnlp.214
ER  -