CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning

Computer Science > Artificial Intelligence [Submitted on 15 May 2026] CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning Fangzhou Lin, Shuo Xing, Peiran Li, Siyuan Yang, Qianwen Ge, Kazunori Yamada, Ziming Zhang, Haichong Zhang, Zhengzhong Tu Parallel reasoning, where a generator samples many candidate solutions and an aggregator selects the best, is one of the most effective forms of test-time scaling in large language models, and pairwise self-verification has become its strongest aggregation primitive. Yet pairwise verification carries a heavy cost: each judgment reads two complete solutions in full, and existing methods perform tens of such judgments per problem regardless of whether the comparison is informative. We introduce CAPS (Cascaded Adaptive Pairwise Selection), an inference-only framework that allocates verifier compute non-uniformly along two orthogonal axes: an evidence axis that adapts how much of each candidate the judge sees, and a distribution axis that adapts how comparisons are spread across the pool. CAPS instantiates these into a four-stage cascade with an optional rescue subroutine, and admits a closed-form verifier-token cost in which the per-candidate marginal cost is roughly halved relative to uniform full-evidence schedules. On four self-verifying models (Qwen3-14B, GPT-OSS-20B, Qwen3-4B-Instruct/Thinking) and five reasoning benchmarks spanning code (LiveCodeBench-v5/v6, CodeContests) and math (AIME 2025, HMMT 2025), CAPS outperforms the leading pairwise verifier on 14 of 20 suites while using 25.4% of its verifier-token budget on code, and outperforms pointwise self-verification on all 20. The trade-off suites admit an interpretable diagnostic in terms of the verifier's accuracy at partial versus full evidence, providing a concrete pre-deployment check for cascade suitability. Comments: 31 pages, 2 figures, 18 tables Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2605.15513 [cs.AI]   (or arXiv:2605.15513v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.15513 Focus to learn more Submission history From: Fangzhou Lin [view email] [v1] Fri, 15 May 2026 01:16:12 UTC (220 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)