Metraipolis › archive › dc_b78ea7615deb
AgentDecarbonizer: Carbon-Aware Execution for AI Agents — arXiv:2608.20566
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20566
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:31:01.325Z
- SHA-256 of the archived text
ec5e616fc5b3740100c11773b9929fe301b2a7d0beea460cccba426c29214f54- Stable URL of this page
https://metraipolis.com/documento/dc_b78ea7615deb
How to cite
AgentDecarbonizer: Carbon-Aware Execution for AI Agents — arXiv:2608.20566 — arXiv (en), https://arxiv.org/abs/2608.20566 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b78ea7615deb (Metraipolis archive dc_b78ea7615deb, sha256 ec5e616fc5b3740100c11773b9929fe301b2a7d0beea460cccba426c29214f54)
BibTeX
@misc{dcb78ea7615deb,
title = {AgentDecarbonizer: Carbon-Aware Execution for AI Agents — arXiv:2608.20566},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20566},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b78ea7615deb; sha256 ec5e616fc5b3740100c11773b9929fe301b2a7d0beea460cccba426c29214f54},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20566. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI agents extend large language models from single prompt-response interactions to long-running, goaldirected workflows that issue many model calls, invoke tools, and interact with external environments. These workflows enable tasks such as software repair, data analysis, and experiment management, but their repeated model invocations can incur substantial carbon emissions. This paper characterizes the carbon emissions of OpenClaw agent workloads using WildClawBench, and shows that emissions depend on token consumption, context cache reuse, and the carbon intensity of the grid. Our characterization identifies deadline flexibility as an opportunity for carbon-aware execution: agent tasks can wait for lower-carbon-intensity periods or shift to lower-carbon grids. However, doing so requires handling uncertain execution time for temporal shifting and cached context recomputation during spatial shifting. We present AgentDecarbonizer, a carbon optimizer for AI agents that runs alongside OpenClaw. Given a task prompt and user-specified deadline, AgentDecarbonizer conservatively estimates task duration and selects deadline-feasible execution schedules, while accounting for cache recomputation overhead during spatial shifting. Evaluated on WildClawBench workloads with 60 agent tasks across four grids, AgentDecarbonizer reduces carbon emissions by up to 57.9 % compared with a carbon-agnostic baseline and by up to 37.5 % compared with a baseline that selects the carbon-optimal grid at task start time. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.20566 — 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 2026-10-18T10:27:55.931Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).