arXiv Machine Learning June 30, 2026 By Seoungbin Bae, Junyoung Son, Dabeen Lee

Learning to Route and Schedule LLMs from User Retrials via Contextual Queueing Bandits

Read the original on arXiv Machine Learning →

arXiv:2602. 02061v2 Announce Type: replace Abstract: Explosive demands for LLMs often cause user queries to accumulate in server queues, requiring efficient routing (query-LLM matching) and scheduling (query prioritization) mechanisms.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 16

Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts

arXiv:2606. 14929v1 Announce Type: cross Abstract: Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models.

By Yan Dai, Negin Golrezaei, Patrick Jaillet

rag reinforcement-learning safety

arXiv AI

Jul 28

WISERouter: LLM Routing with Workload Budget Constraint

arXiv:2607. 23765v1 Announce Type: cross Abstract: Large language models (LLMs) achieve impressive performance across multiple domains, but using the most capable model for every query is prohibitive at scale.

By Yifei Li, Zihui Gao, Laks V. S. Lakshmanan

llms reinforcement-learning

arXiv Machine Learning

1d ago

Sequential Batch Learning in Finite-Action Linear Contextual Bandits

arXiv:2004. 06321v2 Announce Type: replace Abstract: We study the sequential batch learning problem in linear contextual bandits with finite action sets, where the decision maker is constrained to split incoming individuals into (at most) a fixed number of batches and can only observe outcomes for the individuals within a batch at the batch's end.

By Yanjun Han, Zhengqing Zhou, Zihao Hu, Jose Blanchet, Peter W. Glynn, Yinyu Ye, Zhengyuan Zhou

reinforcement-learning

arXiv Machine Learning

Jun 5

Learning to Route LLMs from Implicit Cost-Performance Preferences via Meta-Learning

arXiv:2606. 06178v1 Announce Type: new Abstract: Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense.

By Jiahao Zeng, Ming Tang, Ningning Ding

llms reinforcement-learning

arXiv AI

Jul 13

Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing

arXiv:2607. 09015v1 Announce Type: cross Abstract: We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large language model (LLM) routing.

By Ajay Narayanan Sridhar, Ronak Singh, Mehrdad Mahdavi, Vijaykrishnan Narayanan

llms reinforcement-learning benchmarks

arXiv AI

Jun 9

Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries

arXiv:2606. 08410v1 Announce Type: cross Abstract: Personalized decision-making in multi-objective bandits requires learning user-specific trade-offs among competing objectives.

By Linfeng Cao, Ming Shi, Ness B. Shroff

reinforcement-learning

Related stories

Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts

WISERouter: LLM Routing with Workload Budget Constraint

Sequential Batch Learning in Finite-Action Linear Contextual Bandits

Learning to Route LLMs from Implicit Cost-Performance Preferences via Meta-Learning

Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing

Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries