# The Energy Footprint of LLM-Based Environmental Analysis: LLMs and Domain Products

arXiv: https://arxiv.org/abs/2604.00053 · HTML: https://mlsanity.com/paper/2604.00053/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

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

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [The rising costs of training frontier AI models](https://mlsanity.com/paper/2405.21015/) (2024)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models](https://mlsanity.com/paper/2309.14393/) (2023)
- [Measuring the environmental impact of delivering AI at Google Scale](https://mlsanity.com/paper/2508.15734/) (2025)
- [Internet of Agents: Fundamentals, Applications, and Challenges](https://mlsanity.com/paper/2505.07176/) (2025)
- [ProAgent: From Robotic Process Automation to Agentic Process Automation](https://mlsanity.com/paper/2311.10751/) (2023)
- [The Price of Prompting: Profiling Energy Use in Large Language Models Inference](https://mlsanity.com/paper/2407.16893/) (2024)
- [LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences](https://mlsanity.com/paper/2410.02950/) (2024)
- [Towards Sustainable Large Language Model Serving](https://mlsanity.com/paper/2501.01990/) (2024)
- [Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models](https://mlsanity.com/paper/2502.05610/) (2025)
- [This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs](https://mlsanity.com/paper/2603.15699/) (2026)
- [Accurate and Energy Efficient: Local Retrieval-Augmented Generation Models Outperform Commercial Large Language Models in Medical Tasks](https://mlsanity.com/paper/2506.20009/) (2025)
- [Breaking the ICE: Exploring promises and challenges of benchmarks for Inference Carbon & Energy estimation for LLMs](https://mlsanity.com/paper/2506.08727/) (2025)

## Built on by (most cited first, 2 of 2)

- [Watts and Debts of Agentic Frameworks: An Empirical Study (Registered Report)](https://mlsanity.com/paper/2606.10702/) (2026)
- [From Caveman to Expert Analyst: Energy Consumption of Variable LLM Tasks](https://mlsanity.com/paper/2608.12350/) (2026)

## Abstract (arXiv)

As large language models (LLMs) are increasingly used in domain-specific applications, including climate change and environmental research, understanding their energy footprint has become an important concern. The growing adoption of retrieval-augmented (RAG) systems for climate-domain specific analysis raises a key question: how does the energy consumption of domain-specific RAG workflows compare with that of direct generic LLM usage? Prior research has focused on standalone model calls or coarse token-based estimates, while leaving the energy implications of deployed application workflows insufficiently understood. In this paper, we assess the inference-time energy consumption of two LLM-based climate analysis chatbots (ChatNetZero and ChatNDC) compared to the generic GPT-4o-mini model. We estimate energy use under actual user queries by decomposing each workflow into retrieval, generation, and hallucination-checking components. We also test across different times of day and geographic access locations. Our results show that the energy consumption of domain-specific RAG systems depends strongly on their design. More agentic pipelines substantially increase inference-time energy use, particularly when used for additional accuracy or verification checks, although they may not yield proportional gains in response quality. While more research is needed to further test these initial findings more robustly across models, environments and prompting structures, this study provides a new understanding on how the design of domain-specific LLM products affects both the energy footprint and quality of output.