新的LLM路由策略在固定预算内最大化任务完成率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-05 05:00

研究人员开发了一种名为ADP-HT的新型上下文老虎机策略，旨在优化在固定预算内将任务分配给大型语言模型（LLM）的效率。该策略学习特定于任务的成功概率，并使用粗粒度的响应长度标签来估计成本，目标是在预算耗尽前最大化已解决的任务数量。在MATH500、GPQA、RouterBench和LiveCodeBench等基准测试中，ADP-HT表现优于现有基线，甚至在严格的预算限制下也优于已部署的商业路由器。 AI

影响在预算受限的情况下，优化了组织的LLM使用和成本效益。

排序理由详细介绍LLM路由新算法的研究论文。[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 →

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; 详细介绍LLM路由新算法的研究论文。[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, 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]

arXiv cs.LG TIER_1 English(EN) · Hanzhang Qin, Sophie H. Yu, Yuewei Zhang, Zhi-Hai Zhang · 2026-11-05 05:00

路径预算大语言模型路由：具有 K-比特尾部成本学习的在线分配

arXiv:2611.05835v1 Announce Type: new Abstract: Firms using large language models under fixed budgets must decide which model to call and whether to retry a failed task. Because a call's charge is revealed only after completion, one long response can exhaust the remaining budget …

本文如何被排名

报道来源 [1]

路径预算大语言模型路由：具有 K-比特尾部成本学习的在线分配

相关实体

相关话题