Saved in:
Bibliographic Details
Main Authors: Ho, Anh Khoa Ngo, Chauvin, Martin, Gosset, Simon, Cordier, Philippe, Gamazaychikov, Boris
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.19311
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911426883354624
author Ho, Anh Khoa Ngo
Chauvin, Martin
Gosset, Simon
Cordier, Philippe
Gamazaychikov, Boris
author_facet Ho, Anh Khoa Ngo
Chauvin, Martin
Gosset, Simon
Cordier, Philippe
Gamazaychikov, Boris
contents As large language models become integral to agentic artificial intelligence systems, their energy demands during inference may pose significant sustainability challenges. This study investigates whether deploying smaller-scale language models can reduce energy consumption without compromising responsiveness and output quality in a multi-agent, real-world environments. We conduct a comparative analysis across language models of varying scales to quantify trade-offs between efficiency and performance. Results show that smaller open-weights models can lower energy usage while preserving task quality. Building on these findings, we propose practical guidelines for sustainable artificial intelligence design, including optimal batch size configuration and computation resource allocation. These insights offer actionable strategies for developing scalable, environmentally responsible artificial intelligence systems.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19311
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Balancing Sustainability And Performance: The Role Of Small-Scale LLMs In Agentic Artificial Intelligence Systems
Ho, Anh Khoa Ngo
Chauvin, Martin
Gosset, Simon
Cordier, Philippe
Gamazaychikov, Boris
Artificial Intelligence
As large language models become integral to agentic artificial intelligence systems, their energy demands during inference may pose significant sustainability challenges. This study investigates whether deploying smaller-scale language models can reduce energy consumption without compromising responsiveness and output quality in a multi-agent, real-world environments. We conduct a comparative analysis across language models of varying scales to quantify trade-offs between efficiency and performance. Results show that smaller open-weights models can lower energy usage while preserving task quality. Building on these findings, we propose practical guidelines for sustainable artificial intelligence design, including optimal batch size configuration and computation resource allocation. These insights offer actionable strategies for developing scalable, environmentally responsible artificial intelligence systems.
title Balancing Sustainability And Performance: The Role Of Small-Scale LLMs In Agentic Artificial Intelligence Systems
topic Artificial Intelligence
url https://arxiv.org/abs/2601.19311