2026-05-25原文

Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems

New research proposes A-LEMS, a framework that measures AI energy consumption per successful goal (EpG) rather than per inference, revealing that agentic workflows consume 4.33x more energy on average than linear baselines, with orchestration structure being the primary driver, but potentially more efficient for tool-augmented tasks.

Article intelligence

EngineersAdvanced

Key points

Current AI energy benchmarks measure per-inference energy, which is inadequate for agentic systems involving multi-step orchestration, tool calls, and retries.
A-LEMS introduces Energy per Successful Goal (EpG) and Orchestration Overhead Index (OOI) to accurately measure energy costs of agentic workflows.
Experiments show agentic workflows use 4.33x more energy per goal than linear baselines, but for tool-augmented tasks, agentic execution can be more energy-efficient.
This work provides a new measurement foundation for energy benchmarking in agentic AI, highlighting orchestration structure as the key determinant.

Why it matters

This matters because current AI energy benchmarks measure per-inference energy, which is inadequate for agentic systems involving multi-step orchestration, tool calls, and retries.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.22883] Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems

[Submitted on 20 May 2026]

Title:Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems

View a PDF of the paper titled Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems, by Deepak Panigrahy and 1 other authors

View PDF HTML (experimental)

Abstract:Current AI energy benchmarks measure consumption at the granularity of a single model invocation or training run. For classical single-turn workloads this unit remains coherent. For agentic systems - where a single user goal may trigger multi-step orchestration, tool calls, retries, and failure-recovery cycles - the invocation count is an implementation artifact rather than a task property, and inference-level normalization misrepresents the energy cost of goal completion. We present A-LEMS (Agentic LLM Energy Measurement System), a cross-layer measurement framework that redefines the unit of AI energy accounting from energy per inference to Energy per Successful Goal (EpG). EpG aggregates total workflow energy across all execution attempts, including failures and retries, normalized by successfully completed goals. A-LEMS formalizes energy attribution through a temporal boundary model, a five-layer observation pipeline mapping RAPL signals to workflow-level energy, and a reproducibility protocol binding every measurement to hardware and runtime configuration. Building on EpG, we define the Orchestration Overhead Index (OOI), isolating the energy cost of orchestration relative to linear execution under identical task criteria.

Across five reasoning and three tool-augmented task families, agentic workflows consume 4.33x higher mean energy per successful goal than linear baselines (888.1 J vs 205.3 J). This overhead is driven by orchestration structure, not inference compute. For tool-augmented tasks, OOI inverts below 1.0x: agentic execution is cheaper than linear, confirming the metric captures orchestration structure rather than a fixed upward bias.

These findings establish that energy-per-inference is insufficient for agentic AI. EpG and OOI provide the measurement foundation for accurate benchmarking, where orchestration structure is the primary determinant of energy cost.

Comments: 34 pages, 16 figures, 10 tables

Subjects:

Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Performance (cs.PF)

Cite as: arXiv:2605.22883 [cs.AI]

(or arXiv:2605.22883v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.22883

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Deepak Panigrahy [view email] [v1] Wed, 20 May 2026 22:55:19 UTC (240 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems, by Deepak Panigrahy and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-05

Change to browse by:

cs cs.LG cs.PF

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)