Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads

Abstract

arXiv:2607.18253v1 Announce Type: new Abstract: Modern language query routers improve inference efficiency by assigning each query to a model that balances response quality and monetary cost. However, current query routers are largely latency-agnostic and do not consider the generation latency experienced by queries at model instances. In practice, latency is often controlled by load-balancing policies such as round-robin or join-the-shortest-queue, which do not account for model accuracy or inf