This page may contain stale information. Last updated: 2026-07-05

Definition

Agent energy consumption measures the electricity and GPU compute required for AI agents that autonomously plan, call external tools, and iterate through multi-step reasoning loops — as distinct from single-turn chatbot inference.

KAIST Quantification (HPCA 2026)

First real-world quantitative analysis under service conditions (kaist, Prof. Minsoo Yoo):

MetricAgent vs Chatbot
Energy per queryUp to 136.5× higher
Response timeUp to 153.7× longer
GPU idle timeUp to 54.5% of runtime (waiting on tools)
70B agent average348.41 Wh per question

Why Agents Cost More

  • Repeated LLM invocations (Reflexion, LATS-style loops)
  • Serialized tool-calling: expensive GPUs idle during external API/web waits
  • Test-time scaling: accuracy traded for compute

198.9 GW projection assumes 13.7 billion daily agent requests — hypothetical scale-up scenario for infrastructure stress-testing, not a forecast.

Implications

  • Agent architecture choices (tool loops, model size, batching) directly affect data center capex
  • “Smarter AI” competition shifting toward “more efficient AI” per KAIST framing
  • Open-source benchmark code released for reproducibility

Sources