English(EN) Hermes: Learning Contextual Reasoning Unlocks Test-Time Scaling

Hermes框架学习上下文推理以改进AI模型扩展

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

研究人员推出Hermes，一个旨在通过在推理过程中智能分配额外计算来增强模型性能的新框架。这种称为上下文推理的方法允许模型决定如何管理上下文窗口并在它们之间保留信息。配套的Hermes-Learn框架训练模型开发这些自适应上下文推理策略，这些策略已被证明可以提高各种基准和模型的性能，甚至可以推断到训练期间未见的计算水平。 AI

影响这项研究可能通过使模型能够更好地利用可用的计算资源，从而实现更高效的AI模型扩展和复杂任务性能的提高。

排序理由该集群描述了一篇关于新颖AI模型推理框架的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 21 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇关于新颖AI模型推理框架的新研究论文。[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, 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: 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.AI TIER_1 English(EN) · Xinyu Li, Mononito Goswami, Hao Liu, Nikos Kanakaris, Langlin Huang, Prithwish Jana, Patrick Bl\"obaum, Purak Jain · 2026-10-01 04:00

Hermes：学习上下文推理可实现测试时扩展

arXiv:2609.38332v1 Announce Type: cross Abstract: Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context windows requires deciding how to allocate fresh contexts and what information t…

本文如何被排名

报道来源 [1]

Hermes：学习上下文推理可实现测试时扩展

相关实体

相关话题