arXiv: Cost-Aware LLM Routing via NeuralUCB — Bandit-Based Agent Orchestration for Model Selection

arXiv·low signal

Tsai and Tran apply NeuralUCB (neural contextual bandits) to cost-aware LLM routing, dynamically selecting which model to invoke based on query complexity and cost constraints. The approach outperforms static routing and supervised classifiers by balancing exploration-exploitation in real-time model selection. Relevant to multi-agent orchestration platforms (Perplexity Computer's 19-model router, Grok 4.20's 4-agent system) where intelligent model routing directly impacts both cost and quality.