paper-with-me

홈 › Papers

OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation

2026-05-14 · Shang Zhou, Wenhao Chai, Kaiyuan Liu, Huanzhi Mao, Qiuyang Mang, Jingbo Shang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.15177

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies

2026-06-05 · Ekaterina Grishina, Stepan Kuznetsov, Askar Tsyganov, Ilya Ivanov 외 arxiv

The ranking of recommendation algorithms is a challenging problem since model performance is sensitive to dataset characteristics such as sparsity, sequential structure, and scale. This drives a demand for a proper metho…

Bradley-Terry Policy Optimization for Generative Preference Modeling

2025-10-17 · Shengyu Feng, Yun He, Shuang Ma, Beibin Li 외 arxiv

Reinforcement learning (RL) has recently proven effective at scaling chain-of-thought (CoT) reasoning in large language models for tasks with verifiable answers. However, extending RL-based thought training to more gener…

Reinforcement Learning

Nonparametric Estimation in the Dynamic Bradley-Terry Model

2020-02-28 · Heejong Bong, Wanshan Li, Shamindra Shrotriya, Alessandro Rinaldo

We propose a time-varying generalization of the Bradley-Terry model that allows for nonparametric modeling of dynamic global rankings of distinct teams. We develop a novel estimator that relies on kernel smoothing to pre…

model

Efficient Portfolio Selection through Preference Aggregation with Quicksort and the Bradley--Terry Model

2025-04-06 · Yurun Ge, Lucas Böttcher, Tom Chou, Maria R. D'Orsogna

How to allocate limited resources to projects that will yield the greatest long-term benefits is a problem that often arises in decision-making under uncertainty. For example, organizations may need to evaluate and selec…

Decision Making Under Uncertainty

Neural Bradley-Terry Rating: Quantifying Properties from Comparisons

2023-07-24 · Satoru Fujii

Many properties in the real world don't have metrics and can't be numerically observed, making them difficult to learn. To deal with this challenging problem, prior works have primarily focused on estimating those proper…