Reasoning-intensive retrieval requires deep semantic inference beyond surface-level keyword matching, posing a challenge for current LLM-based rerankers limited by context constraints and order sensitivity. We propose \textbf{\BracketRank}, a framework that treats document reranking as a reasoning-driven competitive tournament. Our approach introduces three key innovations: (1) adaptive grouping based on model context limits, (2) reasoning-enhanced prompts that mandate step-by-step relevance explanations, and (3) a bracket-style elimination structure with winner and loser tracks. This design ensures robust document advancement while enabling parallel processing across competition stages. Evaluation on the BRIGHT reasoning benchmark shows that \BracketRank achieves \textbf{26.56 nDCG@10}, significantly outperforming state-of-the-art baselines including RankGPT-4 (17.0) and Rank-R1-14B (20.5). On TREC datasets, BracketRank achieves 77.90 nDCG@5 on DL 19 and 75.85 nDCG@5 on DL 20, exceeding all baselines, establishing that explicit reasoning within competitive elimination is a powerful paradigm for complex, multi-step retrieval tasks. https://github.com/DataScienceUIBK/BracketRank

翻译：推理密集型检索需要超越表层关键词匹配的深层语义推理，这对当前受限于上下文长度和顺序敏感性的基于大语言模型的排序器构成了挑战。本文提出BracketRank框架，将文档重排序视为一种推理驱动的竞争锦标赛机制。该方法包含三项关键创新：(1) 基于模型上下文限制的自适应分组，(2) 强制要求逐步相关性解释的推理增强提示，以及(3) 包含胜者组与败者组的括号式淘汰结构。该设计既保障文档稳健晋级，又支持跨竞争阶段的并行处理。在BRIGHT推理基准上的评估表明，BracketRank取得了26.56 nDCG@10的优异成绩，显著超越了包括RankGPT-4 (17.0)和Rank-R1-14B (20.5)在内的最先进基线方法。在TREC数据集上，BracketRank在DL 19上达到77.90 nDCG@5，在DL 20上达到75.85 nDCG@5，均超越所有基线方法，这证实了竞争淘汰框架中的显式推理是处理复杂多步检索任务的有效范式。https://github.com/DataScienceUIBK/BracketRank