# Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum

arXiv: https://arxiv.org/abs/2609.18283 · HTML: https://mlsanity.com/paper/2609.18283/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

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

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [Multi-agent Architecture Search via Agentic Supernet](https://mlsanity.com/paper/2502.04180/) (2025)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [MasRouter: Learning to Route LLMs for Multi-Agent Systems](https://mlsanity.com/paper/2502.11133/) (2025)
- [Mobile Edge Computing: A Survey on Architecture and Computation Offloading](https://mlsanity.com/paper/1702.05309/) (2017)
- [Brain-inspired computing: We need a master plan](https://mlsanity.com/paper/2104.14517/) (2021)
- [The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization](https://mlsanity.com/paper/2505.06371/) (2025)
- [S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency](https://mlsanity.com/paper/2502.04790/) (2025)
- [TokenPowerBench: Benchmarking the Power Consumption of LLM Inference](https://mlsanity.com/paper/2512.03024/) (2025)
- [Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling](https://mlsanity.com/paper/2501.08219/) (2025)
- [AdaptOrch: Task-Adaptive Multi-Agent Orchestration in the Era of LLM Performance Convergence](https://mlsanity.com/paper/2602.16873/) (2026)
- [Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling](https://mlsanity.com/paper/2509.20241/) (2025)
- [Where Do the Joules Go? Diagnosing Inference Energy Consumption](https://mlsanity.com/paper/2601.22076/) (2026)
- [SweetSpot: An Analytical Model for Predicting Energy Efficiency of LLM Inference](https://mlsanity.com/paper/2602.05695/) (2026)
- [The Energy Cost of Artificial Intelligence Lifecycle in Communication Networks](https://mlsanity.com/paper/2408.00540/) (2024)
- [On the Effectiveness of Proposed Techniques to Reduce Energy Consumption in RAG Systems: A Controlled Experiment](https://mlsanity.com/paper/2601.02522/) (2026)

## Abstract (arXiv)

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.