PulseAugur
中
实时 07:53:27
English(EN) Give Up to Get More: Priors, Not Policies, Govern Test-Time Compute Allocation

LLM 计算分配取决于先验信息,而非仅仅是策略

一篇新的研究论文探讨了在预算有限的情况下,为大型语言模型(LLM)处理多个输入时的计算资源分配的最佳策略。该研究发表在 arXiv 上,表明计算分配的有效性更多地取决于关于输入可解性的先验信息,而不是策略本身。通过利用验证器和从相关模型过去运行中获得的先验信息,Thompson Sampling 可以显著提高处理困难工作负载的成功率,优于轮询分配等简单策略。 AI

影响 优化计算分配可以提高 LLM 的使用效率,并改善在挑战性任务上的性能。

排序理由 发表在 arXiv 上的研究论文,讨论 LLM 计算分配策略。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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

LLM 计算分配取决于先验信息,而非仅仅是策略

本文如何被排名

Signal score
26 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
发表在 arXiv 上的研究论文,讨论 LLM 计算分配策略。[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]

  1. arXiv cs.LG TIER_1 English(EN) · Jinhyung Bae ·

    放弃以获得更多:先验知识而非策略决定测试时计算分配

    arXiv:2611.06372v1 Announce Type: new Abstract: When many inputs share a budget of repeated attempts by a large language model (LLM), a common rule gives harder inputs more. On public math, code and formal-proof samples, the best published difficulty-proportional rule captures ha…