AI RESEARCH
Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers
arXiv CS.LG
•
ArXi:2505.12601v2 Announce Type: replace As large language models (LLMs) grow in scale and specialization, routing--selecting the best model for a given input--has become essential for efficient and effective deployment. While recent methods rely on complex learned routing strategies, their dependence on disparate