AI RESEARCH
Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents
arXiv CS.LG
•
ArXi:2605.14241v1 Announce Type: new 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