Metraipolis › archive › dc_3cc63cf16a45
Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum — arXiv:2609.18283
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18283
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:07:57.634Z
- SHA-256 of the archived text
b44898950e19459c0fe23bf068a8b37e20f0c785280b94b81b67306eba79fe80- Stable URL of this page
https://metraipolis.com/documento/dc_3cc63cf16a45
How to cite
Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum — arXiv:2609.18283 — arXiv (en), https://arxiv.org/abs/2609.18283 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3cc63cf16a45 (Metraipolis archive dc_3cc63cf16a45, sha256 b44898950e19459c0fe23bf068a8b37e20f0c785280b94b81b67306eba79fe80)
BibTeX
@misc{dc3cc63cf16a45,
title = {Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum — arXiv:2609.18283},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18283},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3cc63cf16a45; sha256 b44898950e19459c0fe23bf068a8b37e20f0c785280b94b81b67306eba79fe80},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18283. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As telecommunication networks evolve toward autonomous 5G-Advanced and 6G operations, agentic artificial intelligence (AI) workflows, where large language models (LLMs) execute multi-step reasoning, invoke diagnostic tools, retrieve domain knowledge, and coordinate across agent teams, are increasingly embedded across the edge-cloud continuum. While the biological brain accomplishes complex cognition on an exceptionally modest metabolic power budget of approximately 20W contemporary LLMs are profoundly energy- and memory-intensive, making sustainable lifecycle orchestration a critical operational priority. However, existing AI lifecycle metrics evaluate only isolated, single-model inferences or overlook multi-agent execution graphs entirely. Consequently, network operators lack foundational models to determine whether distributed agent communication incurs meaningful energy costs and where across edge-cloud tiers agent teams should physically reside. To address this gap, we introduce agentic-eCAL, generalizing the Energy Cost of AI Lifecycle (eCAL) metric to directed multi-agent workflows by coupling a closed-form two-rate single-call energy model (compute-bound prefill and memory-bound decode) with 7-layer OSI data transport. Grounded in hundreds of GPU benchmark configurations on NVIDIA A100 and H100, 16 open-weight models and 8 orchestration topologies, we validate components of the metric and study workflow placement implications. Our findings demonstrate that inter-agent text transport incurs 0.25% of workflow energy across 5G RAN, metro, and optical links. Therefore in edge-cloud agent placement the dominant energy cost of distribution is often not the transmission of inter-agent text itself, but the additional inference and context processing induced by that communication. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.18283 — 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 2026-10-15T14:08:19.241Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).