Metraipolis › archive › dc_7230279de337
Toward Sustainable Agentic AI: Carbon Tradeoffs Across Iterative Self-Refinement and Tool-Augmented Coding — arXiv:2611.12128
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12128
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:45.715Z
- SHA-256 of the archived text
6498a70457482a61e7664db34b5eb16eda69b0567385447720cf9bf49fda19a3- Stable URL of this page
https://metraipolis.com/documento/dc_7230279de337
How to cite
Toward Sustainable Agentic AI: Carbon Tradeoffs Across Iterative Self-Refinement and Tool-Augmented Coding — arXiv:2611.12128 — arXiv (en), https://arxiv.org/abs/2611.12128 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7230279de337 (Metraipolis archive dc_7230279de337, sha256 6498a70457482a61e7664db34b5eb16eda69b0567385447720cf9bf49fda19a3)
BibTeX
@misc{dc7230279de337,
title = {Toward Sustainable Agentic AI: Carbon Tradeoffs Across Iterative Self-Refinement and Tool-Augmented Coding — arXiv:2611.12128},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12128},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7230279de337; sha256 6498a70457482a61e7664db34b5eb16eda69b0567385447720cf9bf49fda19a3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12128. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic language model systems can improve performance either by iterating on their own outputs or by using external tools in grounded environments. While these strategies can reduce error rates and substitute for larger models in some settings, their environmental cost remains relatively underexplored. We present two complementary empirical studies that estimate the energy and carbon footprint of agentic AI across settings of increasing complexity. Study~1 evaluates iterative verbal self-refinement: GPT-4.1-mini at $k = 1$--$5$ steps versus a GPT-4.1 single-pass baseline on two MATH benchmark splits. Study~2 evaluates tool-augmented agentic coding: GPT-4.1-mini, Claude Opus~4.6, and GPT-5.3-codex on SWE-bench Lite, where agents operate inside Docker-isolated environments with access to code execution and file editing tools. In Study~1, $k=3$ refinements close a 16-percentage-point accuracy gap to within 1~point, but nearly triple the carbon footprint relative to the cheap single-pass baseline while remaining below the GPT-4.1 single-pass baseline under the current token-based carbon scenario. In Study~2, GPT-5.3-codex achieves the highest resolution rate in this sample (81.2\%), ahead of Claude Opus~4.6 (68.9\%) and GPT-4.1-mini (25.0\%), but resolved-task-normalized efficiency remains mixed: GPT-4.1-mini is lowest on estimated carbon and cost per resolved task, while GPT-5.3-codex delivers substantially higher task success. All carbon estimates cover output-token inference only; prompt tokens, which exceed 99\% of tokens in Study~2, and tool execution are not charged, so the figures are lower bounds on the full agentic footprint. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.12128 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:37.540Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).