Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it is hindered by two key bottlenecks: accurately selecting the correct solution from the candidate pool, and the high inference latency from generating many full solutions. We argue that both challenges are fundamentally linked to verifier calibration, as a well-calibrated verifier improves answer selection and enables early-stopping strategies to reduce latency. However, existing non-generative verifiers are limited as they score each candidate in isolation, overlooking rich contextual information across the set of candidates. To address this, we introduce the Multi-Sequence Verifier (MSV), a lightweight verifier that predicts each candidate's correctness conditioned on the full sampled set. MSV achieves improved calibration, which directly enhances best-of-N selection performance and empowers a novel early-stopping framework. Across challenging mathematical reasoning benchmarks, MSV improves best-of-64 accuracy by up to 6\% relative to strong baselines, and in the early-stopping setting reaches the same accuracy as baselines with less than half the latency.

翻译：摘要：并行测试时扩展（即为单个问题生成多个候选解决方案）是提升大型语言模型性能的有效技术。然而，该方法面临两大瓶颈：一是如何从候选方案中准确选择正确解，二是生成大量完整解决方案导致的高推理延迟。我们认为这两个挑战本质上与验证器的校准能力相关——校准良好的验证器既能改进答案选择，又能支持早停策略以降低延迟。然而，现有非生成式验证器存在局限性：它们孤立地评估每个候选方案，忽略了跨候选集的丰富上下文信息。为此，我们提出多序列验证器（MSV），这是一种轻量级验证器，能基于完整采样集预测每个候选方案的正确性。MSV实现了更优的校准，这直接提升了最佳-N选优性能，并赋能了一种新颖的早停框架。在具有挑战性的数学推理基准测试中，MSV将最佳-64选优准确率相比强基线提升了最高6%，而在早停设置下，可在不到基线一半延迟的情况下达到相同准确率。