Studies how to route tasks to suitable models or policies across general-purpose AI systems while balancing quality and compute cost. Evaluations across 25 benchmarks and over 374,000 runs quantify the resulting capability and efficiency gains.
Studies how to route tasks to suitable models or policies across general-purpose AI systems while balancing quality and compute cost. Evaluations across 25 benchmarks and over 374,000 runs quantify the resulting capability and efficiency gains.