Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tsai, Ming-Hua, Tran, Phat
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.30035
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915903435702272
author Tsai, Ming-Hua
Tran, Phat
author_facet Tsai, Ming-Hua
Tran, Phat
contents This study investigates the use of NeuralUCB for cost-aware large language model (LLM) routing. Existing routing approaches can be broadly grouped into supervised routing methods and partial-feedback methods, each with different tradeoffs in efficiency and adaptivity. We implement a NeuralUCB-based routing policy and evaluate it on RouterBench under a simulated online setting. Experimental results show that the proposed method consistently outperforms random and min-cost baselines in utility reward. Compared with the max-quality reference, our method achieves substantially lower inference cost while maintaining competitive reward. These findings suggest that NeuralUCB is a promising approach for cost-aware LLM routing, while also highlighting remaining challenges in action discrimination and exploration.
format Preprint
id arxiv_https___arxiv_org_abs_2603_30035
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reward-Based Online LLM Routing via NeuralUCB
Tsai, Ming-Hua
Tran, Phat
Machine Learning
Computation and Language
This study investigates the use of NeuralUCB for cost-aware large language model (LLM) routing. Existing routing approaches can be broadly grouped into supervised routing methods and partial-feedback methods, each with different tradeoffs in efficiency and adaptivity. We implement a NeuralUCB-based routing policy and evaluate it on RouterBench under a simulated online setting. Experimental results show that the proposed method consistently outperforms random and min-cost baselines in utility reward. Compared with the max-quality reference, our method achieves substantially lower inference cost while maintaining competitive reward. These findings suggest that NeuralUCB is a promising approach for cost-aware LLM routing, while also highlighting remaining challenges in action discrimination and exploration.
title Reward-Based Online LLM Routing via NeuralUCB
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2603.30035