English(EN) Sample, Mix, or Verify? Allocating Test-Time Compute under Imperfect Verifiers

新的SPLIT方法优化了AI模型测试计算分配

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-19 04:00

研究人员开发了一种名为SPLIT的新方法，用于优化语言模型和代理测试阶段的计算资源分配。SPLIT通过使用一个公式来计算提交正确答案的概率，解决了验证器不完美（可能接受错误答案或拒绝正确答案）的挑战。该方法在七个基准测试以及众多模型和系统上进行了测试，始终实现了接近最优的分配，优于固定规则，并在各种成本限制下提供了更有效的预算规划策略。 AI

影响优化了AI模型测试的计算资源分配，提高了各种基准测试的效率和准确性。

排序理由该集群包含一篇详细介绍AI模型测试优化新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍AI模型测试优化新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Srinivasan Iyengar · 2026-10-19 04:00

抽样、混合还是验证？在不完美验证器下分配测试时计算

arXiv:2610.23255v1 Announce Type: cross Abstract: A common way to make language models and agents more accurate is to spend more compute at inference time: generate many candidate solutions and submit the one a verifier prefers. Success then requires that some candidate is correc…

本文如何被排名

报道来源 [1]

抽样、混合还是验证？在不完美验证器下分配测试时计算

相关实体

相关话题