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

arXiv: https://arxiv.org/abs/2605.22883 · HTML: https://mlsanity.com/paper/2605.22883/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

- 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, 15 of 15)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [MLPerf Training Benchmark](https://mlsanity.com/paper/1910.01500/) (2019)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization](https://mlsanity.com/paper/2505.06371/) (2025)
- [MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI](https://mlsanity.com/paper/2410.12032/) (2024)
- [Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling](https://mlsanity.com/paper/2509.20241/) (2025)
- [BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug Synthesis](https://mlsanity.com/paper/2506.10501/) (2025)
- [Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective](https://mlsanity.com/paper/2511.00739/) (2025)
- [Understanding Power and Energy Utilization in Large Scale Production Physics Simulation Codes](https://mlsanity.com/paper/2201.01278/) (2022)
- [SPEChpc 2021 Benchmarks on Ice Lake and Sapphire Rapids Infiniband Clusters: A Performance and Energy Case Study](https://mlsanity.com/paper/2309.05373/) (2023)
- [Strategies to Measure Energy Consumption Using RAPL During Workflow Execution on Commodity Clusters](https://mlsanity.com/paper/2505.09375/) (2025)
- [Harvesting energy consumption on European HPC systems: Sharing Experience from the CEEC project](https://mlsanity.com/paper/2511.03029/) (2025)

## Built on by (most cited first, 2 of 2)

- [The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution](https://mlsanity.com/paper/2605.27599/) (2026)
- [When Is Smaller Greener? Right-Sizing Language Models for Agentic AI](https://mlsanity.com/paper/2610.19345/) (2026)

## Abstract (arXiv)

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.