# Energy-Aware Routing to Large Reasoning Models

arXiv: https://arxiv.org/abs/2601.00823 · HTML: https://mlsanity.com/paper/2601.00823/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 20 of 20)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [Explaining Neural Scaling Laws](https://mlsanity.com/paper/2102.06701/) (2021)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [Large Language Model Routing with Benchmark Datasets](https://mlsanity.com/paper/2309.15789/) (2023)
- [Compact Language Models via Pruning and Knowledge Distillation](https://mlsanity.com/paper/2407.14679/) (2024)
- [Multi-Step Reasoning with Large Language Models, a Survey](https://mlsanity.com/paper/2407.11511/) (2024)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [The Price of Prompting: Profiling Energy Use in Large Language Models Inference](https://mlsanity.com/paper/2407.16893/) (2024)
- [EcoServe: Designing Carbon-Aware AI Inference Systems](https://mlsanity.com/paper/2502.05043/) (2025)
- [Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service](https://mlsanity.com/paper/2304.09781/) (2023)
- [Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations](https://mlsanity.com/paper/2403.08151/) (2024)
- [Foundation Models for Discovery and Exploration in Chemical Space](https://mlsanity.com/paper/2510.18900/) (2025)
- [A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search](https://mlsanity.com/paper/2507.00004/) (2025)
- [Carbon- and Precedence-Aware Scheduling for Data Processing Clusters](https://mlsanity.com/paper/2502.09717/) (2025)
- [Stochastic Routing and Scheduling Policies for Energy Harvesting Communication Networks](https://mlsanity.com/paper/1711.00745/) (2017)

## Abstract (arXiv)

Large reasoning models (LRMs) have heterogeneous inference energy costs based on which model is used and how much it reasons. To reduce energy, it is important to choose the right LRM and operate it in the right way. As a result, the performance of systems that dispatch tasks to different individual LRMs depend on the balance between mean energy provisioning and stochastic fluctuations. The critical regime is the unique operating point at which neither auxiliary energy nor baseline energy is systematically wasted. Increasing baseline supply shifts the system toward persistent over-supply and baseline-energy waste, while reducing supply induces persistent reliance on auxiliary energy. Yet in this regime, performance remains volatility-limited and so a second-order characterization provides further insights that we develop. Here, performance is governed by how variability is absorbed across time, models, and execution choices. This perspective highlights variance-aware routing and dispatch as a principled design axis, and provides a theoretical basis for developing energy-aware model routing policies. Routing behavior is characterized when dispatch policies are based on training-compute and inference-compute scaling laws for LRMs.