Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, by methods such as independently sampling and aggregating multiple solutions, results in significantly better task outcomes. However, a critical bottleneck is verification: sampling is only effective if correct solutions can be reliably identified among candidates. While existing approaches typically evaluate candidates independently via scalar scoring, we demonstrate that models are substantially stronger at pairwise self-verification. Leveraging this insight, we introduce $V_1$, a framework that unifies generation and verification through efficient pairwise ranking. $V_1$ comprises two components: $V_1$-Infer, an uncertainty-guided algorithm using a tournament-based ranking that dynamically allocates self-verification compute to candidate pairs whose relative correctness is most uncertain; and $V_1$-PairRL, an RL framework that jointly trains a single model as both generator and pairwise self-verifier, ensuring the verifier adapts to the generator's evolving distribution. On code generation (LiveCodeBench, CodeContests, SWE-Bench) and math reasoning (AIME, HMMT) benchmarks, $V_1$-Infer improves Pass@1 by up to $10%$ over pointwise verification and outperforms recent test-time scaling methods while being significantly more efficient. Furthermore, $V_1$-PairRL achieves $7$--$9%$ test-time scaling gains over standard RL and pointwise joint training, and improves base Pass@1 by up to 8.7% over standard RL in a code-generation setting.

翻译：针对复杂推理任务的测试时扩展研究表明，通过独立采样并聚合多个解等方法利用推理时计算资源，能显著提升任务性能。然而，验证环节成为关键瓶颈：仅当能可靠地从候选解中识别正确解时，采样才具有效性。现有方法通常通过标量评分独立评估候选解，而本文证明模型在成对自验证方面具有显著更强的能力。基于此洞见，我们提出V_1框架，通过高效成对排序统一生成与验证过程。V_1包含两个核心组件：V_1-Infer——采用基于锦标赛排序的不确定性引导算法，动态分配自验证计算资源至相对正确性最不确定的候选对；以及V_1-PairRL——联合训练单一模型同时作为生成器与成对自验证器的强化学习框架，确保验证器能适应生成器的动态分布演化。在代码生成（LiveCodeBench、CodeContests、SWE-Bench）与数学推理（AIME、HMMT）基准测试中，V_1-Infer将Pass@1指标最高提升10%（相较于逐点验证），在显著提升效率的同时优于近期测试时扩展方法。此外，V_1-PairRL在测试时扩展中较标准强化学习与逐点联合训练获得7%-9%的性能增益，在代码生成场景中较标准强化学习将基础Pass@1指标最高提升8.7%。