Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chu, Kexin, Xiang, Dawei, Zhang, Wei
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.14241
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911728196911104
author Chu, Kexin
Xiang, Dawei
Zhang, Wei
author_facet Chu, Kexin
Xiang, Dawei
Zhang, Wei
contents Tool-augmented LLM agents increasingly access the same tool type through multiple functionally equivalent providers, such as web-search APIs, retrievers, or LLM backends exposed behind a shared interface. This creates a provider-routing problem under runtime load: the router must choose among providers that differ in latency, reliability, and answer quality, often without gold labels at deployment time. We introduce LQM-ContextRoute, a contextual bandit router for same-function tool providers. Its key design is latency-quality matching: instead of letting low latency offset poor answers in an additive reward, the router ranks providers by expected answer quality per service cycle. It combines this capacity-aware score with query-specific quality estimation and LLM-as-judge feedback, allowing it to adapt online to both load changes and provider-quality differences. On the main web-search load benchmark, LQM-ContextRoute improves F1 by +2.18 pp over SW-UCB while staying on the latency-quality frontier. In a high-heterogeneity StrategyQA setting, LQM-ContextRoute avoids additive-reward collapse and improves accuracy by up to +18 pp over SW-UCB; on heterogeneous retriever pools, it improves NDCG by +2.91--+3.22 pp over SW-UCB. These results show that same-function tool routing benefits from treating latency as service capacity, especially when runtime pressure and provider-quality heterogeneity coexist.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14241
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents
Chu, Kexin
Xiang, Dawei
Zhang, Wei
Machine Learning
Tool-augmented LLM agents increasingly access the same tool type through multiple functionally equivalent providers, such as web-search APIs, retrievers, or LLM backends exposed behind a shared interface. This creates a provider-routing problem under runtime load: the router must choose among providers that differ in latency, reliability, and answer quality, often without gold labels at deployment time. We introduce LQM-ContextRoute, a contextual bandit router for same-function tool providers. Its key design is latency-quality matching: instead of letting low latency offset poor answers in an additive reward, the router ranks providers by expected answer quality per service cycle. It combines this capacity-aware score with query-specific quality estimation and LLM-as-judge feedback, allowing it to adapt online to both load changes and provider-quality differences. On the main web-search load benchmark, LQM-ContextRoute improves F1 by +2.18 pp over SW-UCB while staying on the latency-quality frontier. In a high-heterogeneity StrategyQA setting, LQM-ContextRoute avoids additive-reward collapse and improves accuracy by up to +18 pp over SW-UCB; on heterogeneous retriever pools, it improves NDCG by +2.91--+3.22 pp over SW-UCB. These results show that same-function tool routing benefits from treating latency as service capacity, especially when runtime pressure and provider-quality heterogeneity coexist.
title Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents
topic Machine Learning
url https://arxiv.org/abs/2605.14241