SOURCE-LINKED INTELLIGENCE

Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving

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

Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajectories extend. While in practice, many queries do not require the capabilities of the largest available model, and routinely directing such queries to a high-capability model can introduce unnecessary, considerable computation and energy consumption. In this paper, we investigate whether adaptive routing across a heterogeneous pool of LLMs can reduce this energy burden without substantially compromising task performance. We design a language-model-ba

Read original source ↗ Open in workspace

recordType

paper

region

Global