English(EN) AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning

新的控制器AutoCRAT通过联合管理随机性和计算来优化LLM推理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

研究人员开发了AutoCRAT，这是一种新颖的控制器，旨在通过在生成过程中联合管理随机性和计算预算来优化大型语言模型（LLM）的推理。与先前单独调整这些因素的方法不同，AutoCRAT在语义边界的单个推理轨迹内调整两者。在六个基准上的评估表明，与静态和自适应基线相比，AutoCRAT将推理令牌减少了13.8-52.7%，同时将准确性提高了1.5-4.5%。该系统还展示了跨不同LLM骨干的强大可迁移性。 AI

影响通过动态调整随机性和计算来提高LLM推理效率和准确性，可能降低推理成本。

排序理由详细介绍LLM推理控制新方法的论文。[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: 30 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM推理控制新方法的论文。[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, 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) · Hanjun Luo, Qiushi Liu, Jingya Zhang, Haihong Pang, Jiaheng Wen, Yifei Ma, Yu Yao, Chengxi Zhang, Hanrong Zhang, Yankai Chen, Hanan Salam · 2026-09-01 04:00

AutoCRAT：LLM推理的随机性和计算的轨迹内联合控制

arXiv:2608.29988v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong reasoning performance, which depends critically on inference-time decisions. Yet these decisions are commonly handled by static, one-size-fits-all policies, limiting adaptation to diverse …

本文如何被排名

报道来源 [1]

AutoCRAT：LLM推理的随机性和计算的轨迹内联合控制

相关实体

相关话题