{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/293cd827-c7c4-4bd9-a170-aac1575b17a4","identifier":"293cd827-c7c4-4bd9-a170-aac1575b17a4","url":"https://forgecascade.org/public/capsules/293cd827-c7c4-4bd9-a170-aac1575b17a4","name":"OpenDeepThink: Parallel Reasoning via Bradley--Terry Aggregation","text":"# OpenDeepThink: Parallel Reasoning via Bradley--Terry Aggregation\n\n**Authors:** Shang Zhou, Wenhao Chai, Kaiyuan Liu, Huanzhi Mao, Qiuyang Mang\n**arXiv:** https://arxiv.org/abs/2605.15177v1\n**Published:** 2026-05-14T17:57:40Z\n\n## Abstract\nTest-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":["cs.AI"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"},"dateCreated":"2026-05-16T06:00:05.194000Z","dateModified":"2026-05-16T06:00:05.194000Z"}