arXiv：cs.AI· Deepak Panigrahy, Aakash Tyagi, Stephen Abkin, David Kebo Houngninou, Rabi Mahapatra·· 21 小时前
A-LEMS：面向智能体 AI 的目标级能耗核算——每成功目标能耗 EpG
Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems
AI 导读
研究者提出 A-LEMS 跨层框架，把 AI 能耗核算单位改为「每成功目标能耗」（EpG）：统计包含失败与重试的全部工作流能耗，再除以成功完成的目标数。
正文
Abstract:Current AI energy benchmarks measure consumption per model invocation. For agentic systems, where a single user goal may trigger multistep orchestration, tool calls, retries, and failure recovery, the invocation count is an implementation artifact rather than a task property, and per inference normalization misrepresents the energy cost of completing a goal. We present A-LEMS (Agentic LLM Energy Measurement System), a cross layer framework that redefines the unit of AI energy accounting as Energy per Successful Goal (EpG): total workflow energy across all attempts, including failures and retries, divided by successfully completed goals. A-LEMS combines a temporal boundary model, a five layer attribution pipeline mapping hardware signals (RAPL on x86; SPBM and DCGM on ARM) to workflow energy, and a reproducibility protocol binding every measurement to hardware, environment, and runtime configuration. Building on EpG, we define the Orchestration Overhead Index (OOI), the ratio of agentic to linear EpG on matched goals under identical success criteria. Across nine task families on Intel x86 and NVIDIA Grace GB10 ARM, CPU only OOI ranges 0.35x to 11.07x. Including GPU dynamic energy, which accounts for 83.8% of agentic EpG in local inference, widens this to 0.4x to 26.48x, so CPU only measurement understates overhead about twofold for reasoning tasks. For remote inference, network wait energy shifts OOI from 2.5x to 2.35x. The overhead arises from orchestration structure (planning, retries, recovery) that induces additional inference calls, not from costlier individual calls. The metric is not biased upward: single tool calculator dispatch inverts to OOI = 0.61x (95% CI [0.35, 0.97]) on x86. Goal level accounting via EpG and OOI provides a measurement foundation for benchmarking agentic AI.
| Comments: | v2: 37 pages. Adds ARM platform (NVIDIA Grace GB10) with GPU (DCGM) and network wait energy, nine task families, bootstrap confidence intervals, stochastic retry model, and new coauthors |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Performance (cs.PF) |
| Cite as: | arXiv:2605.22883 [cs.AI] |
| (or arXiv:2605.22883v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22883 arXiv-issued DOI via DataCite |
Submission history
From: Deepak Panigrahy [view email]
[v1]
Wed, 20 May 2026 22:55:19 UTC (240 KB)
[v2]
Mon, 12 Oct 2026 16:19:56 UTC (1,078 KB)
来源：arXiv：cs.AI · arxiv.org