SOURCE-LINKED INTELLIGENCE

AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models handle equally well. Existing routing solutions optimize single-turn query assignment but ignore a property unique to agentic workflows: subtask complexity varies widely within a single trajectory. A planning step may require frontier-class reasoning while a subsequent formatting step needs only a 7B model. We formalize step-level model routing as a sequential assignment problem over agent trajectories and propose AgentRouter, a lightweight clas

Read original source ↗ Open in workspace

recordType

paper

region

Global