English

OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation

Artificial Intelligence 2026-05-19 v2

Abstract

Test-time compute scaling is a primary axis for improving LLM reasoning. Existing methods primarily scale depth by extending a single reasoning trace. Scaling breadth by sampling multiple candidates in parallel is straightforward, but introduces a selection bottleneck: choosing the best candidate without a ground-truth verifier, since pointwise LLM judging is noisy and biased. To address this, we introduce OpenDeepThink, a population-based test-time compute framework that selects via pairwise Bradley-Terry comparison. Each generation, the LLM judges random pairs of candidates and aggregates votes via Bradley-Terry into a global ranking; top-ranked candidates are preserved and the top three quarters are mutated using the natural-language critiques produced during comparison; the bottom quarter is discarded. OpenDeepThink raises Gemini 3.1 Pro's effective Codeforces Elo by +405 points in eight sequential LLM-call rounds (~27 minutes wall-clock). The pipeline transfers across weaker and stronger models without retuning, and on the multi-domain HLE benchmark, gains appear concentrated in objectively verifiable domains and reverse in subjective ones. We release CF-73, a curated set of 73 expert-rated Codeforces problems with International Grandmaster annotation and 99% local-evaluation agreement against the official verdict.

Keywords

Cite

@article{arxiv.2605.15177,
  title  = {OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation},
  author = {Shang Zhou and Wenhao Chai and Kaiyuan Liu and Huanzhi Mao and Qiuyang Mang and Jingbo Shang},
  journal= {arXiv preprint arXiv:2605.15177},
  year   = {2026}
}

Comments

19 pages, 4 figures