English

GenSelect: A Generative Approach to Best-of-N

Machine Learning 2025-07-25 v1 Computation and Language

Abstract

Generative reward models with parallel sampling have enabled effective test-time scaling for reasoning tasks. Current approaches employ pointwise scoring of individual solutions or pairwise comparisons. However, pointwise methods underutilize LLMs' comparative abilities, while pairwise methods scale inefficiently with larger sampling budgets. We introduce GenSelect, where the LLM uses long reasoning to select the best solution among N candidates. This leverages LLMs' comparative strengths while scaling efficiently across parallel sampling budgets. For math reasoning, we demonstrate that reasoning models, such as QwQ and DeepSeek-R1-0528, excel at GenSelect, outperforming existing scoring approaches with simple prompting.

Keywords

Cite

@article{arxiv.2507.17797,
  title  = {GenSelect: A Generative Approach to Best-of-N},
  author = {Shubham Toshniwal and Ivan Sorokin and Aleksander Ficek and Ivan Moshkov and Igor Gitman},
  journal= {arXiv preprint arXiv:2507.17797},
  year   = {2025}
}

Comments

Presented at the 2nd AI for MATH Workshop @ ICML