English(EN) Chance-Constrained Personalized LLM Routing with Online Preference Learning

新算法通过在线学习用户偏好来优化大语言模型路由

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-19 04:00

研究人员开发了一种新的个性化大语言模型（LLM）路由算法，该算法通过在线学习用户偏好来最小化推理成本，同时保持响应质量。该方法将问题构建为约束上下文老虎机问题，即使在用户偏好未知的情况下也能平衡成本和可靠性。该框架适用于需要可靠性保证的各种在线模型选择场景。 AI

影响这项研究通过根据学习到的用户需求和模型能力动态路由请求，有望实现更高效、更具成本效益的大语言模型资源利用。

排序理由该集群包含一篇提交到 arXiv 的研究论文，详细介绍了一种新的大语言模型路由算法。[lever_c_demoted from research: ic=1 ai=1.0]

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: 9 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇提交到 arXiv 的研究论文，详细介绍了一种新的大语言模型路由算法。[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。

arXiv cs.LG TIER_1 English(EN) · Ameya Anjarlekar, Rasoul Etesami, R Srikant · 2026-10-19 04:00

具有在线偏好学习的约束个性化大模型路由

arXiv:2610.22695v1 Announce Type: new Abstract: We study personalized LLM routing, where a router selects among heterogeneous models with different costs and capabilities. The router must minimize cumulative inference cost while ensuring reliable realized response quality, even t…