Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems
cs.AI, cs.LG, cs.PF
Submitted: 2026-05-20
Updated: 2026-10-12
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
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Why Do Multi-Agent LLM Systems Fail?
- Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey
- Training Verifiers to Solve Math Word Problems
- How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference
- Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling
- Carbon Emissions and Large Neural Network Training
- Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective
- Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning
- Strategies to Measure Energy Consumption Using RAPL During Workflow Execution on Commodity Clusters
- MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems