Energy-Aware Data-Driven Model Selection in LLM-Orchestrated AI Systems
Preprint
Abstract
As modern artificial intelligence (AI) systems become more advanced and capable, they can leverage a wide range of tools and models to perform complex tasks. Today, the task of orchestrating these models is often performed by Large Language Models (LLMs) that rely on qualitative descriptions of models for decision-making. However, the descriptions provided to these LLM-based orchestrators do not reflect true model capabilities and performance characteristics, leading to suboptimal model selection, reduced accuracy, and increased energy costs. In this paper, we conduct an empirical analysis of LLM-based orchestration limitations and propose GUIDE, a new energy-aware model selection framework that accounts for performance-energy trade-offs by incorporating quantitative model performance characteristics in decision-making. Experimental results demonstrate that GUIDE increases accuracy by 0.90%-11.92% across various evaluated tasks, and achieves up to 54% energy efficiency improvement, while reducing orchestrator model selection latency from 4.51 s to 7.2 ms.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Energy-aware tinyML model selection on zero energy devicesInternet of Things, 2025
- LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents2024
- DETRs Beat YOLOs on Real-time Object Detection2024
- TensorOpera Router: A Multi-Model Router for Efficient LLM Inference2024
- ViperGPT: Visual Inference via Python Execution for Reasoning2023
- From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference2023
- HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face2023