Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences

Sweta Karlekar, Carolina Zheng, Magnus Saebo, Nicolas Beltran-Velez, Shuyang Yu, John Bowlan, Michal Kucer, David M. Blei

BibTeX
@inproceedings{karlekar2026duel,
  author = {Sweta Karlekar and Carolina Zheng and Magnus Saebo and Nicolas Beltran-Velez and Shuyang Yu and John Bowlan and Michal Kucer and David M. Blei},
  title = {{Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences}},
  booktitle = {RSI @ ICLR},
  year = {2026},
  url = {https://openreview.net/forum?id=38t39AFZPE},
}

Loading related content...

Figure