PulseAugur
中
实时 09:12:14
English(EN) Hill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training

新研究探讨大语言模型的测试时扩展，解决吸引子和信任问题

作者 PulseAugur 编辑部 · [3 个来源] ·

三篇新研究论文探讨了改进大型语言模型测试时扩展的方法，这是一种允许模型在推理时花费额外计算来增强推理和解决问题能力的技术。第一篇论文指出，顺序扩展方法可能会陷入吸引子，阻碍进一步改进，并提出了一种模型混合干预措施来摆脱这些状态。第二篇论文侧重于信任来自测试时扩展曲线的准确性声明的挑战，提出了一种更有效的方法来认证这些曲线。第三篇论文介绍了“爬山采样”，这是复杂进化策略的更简单有效的替代方案，通过将样本条件化为先前找到的最佳解决方案，在特定基准上展示了最先进的结果。 AI

影响 这些方法可能带来更高效、更可靠的大语言模型推理能力，尤其是在复杂、长周期的任务中。

排序理由 三篇在arXiv上发表的学术论文，详细介绍了语言模型测试时扩展的新方法和分析。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新研究探讨大语言模型的测试时扩展，解决吸引子和信任问题

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
三篇在arXiv上发表的学术论文，详细介绍了语言模型测试时扩展的新方法和分析。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
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
47 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [3]

  1. arXiv cs.LG TIER_1 English(EN) · Joseph Rance, Fabio Pizzati, Juil Sock, Woody Bayliss, Marc G\'orriz Blanch, Philip Torr, Adel Bibi ·

    迈向序列测试时间缩放的更好探索

    arXiv:2609.39632v1 Announce Type: new Abstract: Test-time scaling improves language model reasoning by spending additional compute at inference. However, both classes of existing methods often fail to continue improving over long timescales. Parallel methods repeatedly sample ind…

  2. arXiv cs.CL TIER_1 English(EN) · Sohail (Neel), Sarkar, Shakuntala Baichoo ·

    绘制成本低廉，但信任成本高昂：测试时缩放曲线的认证

    arXiv:2609.40190v1 Announce Type: cross Abstract: Sampling several answers and keeping the one a verifier scores highest is one of the simplest ways to buy accuracy at test time. Its effect is reported as a scaling curve: accuracy against the number $k$ of sampled answers. The cu…

  3. arXiv cs.AI TIER_1 English(EN) · Jacob Beck, Philip V. Ogren, Ari Kobren ·

    用于测试时缩放的Hill采样：重复采样、进化和训练的简单且更好的替代方案

    arXiv:2609.25510v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can improve solutions to verifiable scientific and algorithmic problems by spending additional computation at test time. Recent systems achieve strong results with increasingly elaborate evolut…

相关实体

相关话题