English(EN) Online Learning with LLM Experts from Limited Feedback

新算法在有限反馈下优化LLM专家路由

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了新的算法，用于在反馈有限的在线环境中，对大型语言模型（LLM）专家进行自适应路由。该方法被表述为一个多臂老虎机问题，旨在通过策略性地选择和观察奖励来最小化遗憾，从而最大化响应质量。实验表明，即使在反馈预算有限的情况下，这些策略也能有效地学习高质量的路由，覆盖各种LLM。 AI

影响这项研究通过在最少反馈的情况下优化提示分发，有望实现更高效、更具成本效益的大型语言模型使用。

排序理由该集群包含一篇在arXiv上发表的研究论文，详细介绍了LLM提示路由的新算法。[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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇在arXiv上发表的研究论文，详细介绍了LLM提示路由的新算法。[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, 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。

arXiv cs.LG TIER_1 English(EN) · Wang Wei, Soumyabrata Pal, Koyel Mukherjee, Franck Dernoncourt, Ryan A. Rossi, Branislav Kveton, Hoda Eldardiry · 2026-09-10 04:00

Limited Feedback下的LLM专家在线学习

arXiv:2609.05820v1 Announce Type: new Abstract: We study adaptive routing of prompts to large language model (LLM) experts to maximize response quality in an online setting with limited feedback. We formulate it as a bandit problem with $K$ actions that represent experts and $d$ …