English(EN) Truncated Reasoning Under a Budget: Evaluating System-1 Models as Decision-Makers

新型系统-1模型“Jev”在预算约束下优化LLM推理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

一篇新研究论文提出了一种名为“Jev”的系统-1决策模型，该模型通过从候选选项中选择答案而非生成完整的推理过程来与大型语言模型（LLMs）协同工作。这种方法旨在降低LLM生成过多推理令牌所带来的计算成本。实验表明，与强制从不完整的LLM推理中提取答案相比，Jev在较低的令牌预算下能提高准确性，并能在保持高准确率的同时显著降低估算的计算成本。 AI

影响这项研究提出了一种通过优化推理令牌生成来降低LLM推理成本的方法，有望带来更高效的AI应用。

排序理由研究论文发布在arXiv上，详细介绍了一个新模型及其评估。[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: 8 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文发布在arXiv上，详细介绍了一个新模型及其评估。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Zhongyin Wang, Zhaoqian Xue, Junting Mu, Haozheng Liu, Ye Yuan, Haolun Wu, Lingyao Li · 2026-10-27 04:00

预算约束下的截断推理：评估System-1模型作为决策者

arXiv:2610.25768v2 Announce Type: replace Abstract: Large language models (LLMs) often generate more reasoning tokens than needed. Limiting the reasoning budget reduces cost, but forcing an answer from an incomplete trace can hurt accuracy. System-1 decision models select among c…

本文如何被排名

报道来源 [1]

预算约束下的截断推理：评估System-1模型作为决策者

相关实体

相关话题