cs.AINov 9, 2026

Toward Sustainable Agentic AI: Carbon Tradeoffs Across Iterative Self-Refinement and Tool-Augmented Coding

Authors: Boris Ruf, Adrien de Mailly Nesle, Marcin Detyniecki

Organizations: AXA AI Research

Abstract

Agentic language model systems can improve performance either by iterating on their own outputs or by using external tools in grounded environments. While these strategies can reduce error rates and substitute for larger models in some settings, their environmental cost remains relatively underexplored. We present two complementary empirical studies that estimate the energy and carbon footprint of agentic AI across settings of increasing complexity. Study1 evaluates iterative verbal self-refinement: GPT-4.1-mini at k=1k = 1--55 steps versus a GPT-4.1 single-pass baseline on two MATH benchmark splits. Study2 evaluates tool-augmented agentic coding: GPT-4.1-mini, Claude Opus4.6, and GPT-5.3-codex on SWE-bench Lite, where agents operate inside Docker-isolated environments with access to code execution and file editing tools. In Study1, k=3k=3 refinements close a 16-percentage-point accuracy gap to within 1point, but nearly triple the carbon footprint relative to the cheap single-pass baseline while remaining below the GPT-4.1 single-pass baseline under the current token-based carbon scenario. In Study2, GPT-5.3-codex achieves the highest resolution rate in this sample (81.2%), ahead of Claude Opus4.6 (68.9%) and GPT-4.1-mini (25.0%), but resolved-task-normalized efficiency remains mixed: GPT-4.1-mini is lowest on estimated carbon and cost per resolved task, while GPT-5.3-codex delivers substantially higher task success. All carbon estimates cover output-token inference only; prompt tokens, which exceed 99% of tokens in Study2, and tool execution are not charged, so the figures are lower bounds on the full agentic footprint.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Aug 20, 2026

AgentDecarbonizer: Carbon-Aware Execution for AI Agents

AI agents extend large language models from single prompt-response interactions to long-running, goaldirected workflows that issue many model calls, invoke tools, and interact with external environments. These workflows enable tasks such as software repair, data analysis, and experiment management, but their repeated model invocations can incur substantial carbon emissions. This paper characterizes the carbon emissions of OpenClaw agent workloads using WildClawBench, and shows that emissions depend on token consumption, context cache reuse, and the carbon intensity of the grid. Our characterization identifies deadline flexibility as an opportunity for carbon-aware execution: agent tasks can wait for lower-carbon-intensity periods or shift to lower-carbon grids. However, doing so requires handling uncertain execution time for temporal shifting and cached context recomputation during spatial shifting. We present AgentDecarbonizer, a carbon optimizer for AI agents that runs alongside OpenClaw. Given a task prompt and user-specified deadline, AgentDecarbonizer conservatively estimates task duration and selects deadline-feasible execution schedules, while accounting for cache recomputation overhead during spatial shifting. Evaluated on WildClawBench workloads with 60 agent tasks across four grids, AgentDecarbonizer reduces carbon emissions by up to 57.9 % compared with a carbon-agnostic baseline and by up to 37.5 % compared with a baseline that selects the carbon-optimal grid at task start time.
Oct 14, 2026

When Is Smaller Greener? Right-Sizing Language Models for Agentic AI

AI agents use a large language model (LLM) to plan and act over many steps. Which model should an agent use, so that its tasks are completed reliably with the least energy, cost and time? We treat this as a multi-criteria decision problem in which comparisons per call can mislead: a task succeeds only if all its steps succeed, and failed attempts still use resources. We therefore compare models on resources per successfully completed task. We derive crossover task lengths at which two models exchange their efficiency ranking, determined by their per-step reliability and resource use. Each objective has its own crossover. Below the shortest crossover the less reliable model dominates, above the longest the more reliable one dominates, and in between both are Pareto-efficient and preferences decide. This supports a two-stage framework: a preference-free dominance screen, followed by a multi-criteria ranking of the efficient models, subject to reliability and feasibility constraints. We also give conditions under which this structure holds when reliability and resource use change during a task. In a pilot with 15 open-weight models on two synthetic agent tasks, with measured GPU energy, the predicted crossover fell within the observed range for 72 of the 88 observed crossovers. At 20 steps, a 3-billion-parameter model used a tenth of the energy of a 27-billion one per completed task; at 100 steps, a 1.7-billion model used almost four times as much as an 8-billion one. Smaller is greener only up to a task length that can be predicted.
Aug 26, 2026

Can your AI agent be cheaper? Investigating the effects of task specifications on token spend in agentic coding tasks

Agentic coding workflows are now widely deployed in real-world systems. With long-horizon reasoning and tool use, token usage has become an important consideration for both cost and efficiency. Two engineers using AI will solve the same problem differently. How the specification of a task shapes an agent's token spend, and whether that spend can be predicted in advance, are open questions. Here, we study the effects of different task specifications on agentic token spend with the Kimi K3 model at three thinking efforts. Across 2,7002,700 runs, we show that reducing a full task specification to a bare user story raises token spend by 29.7%29.7\%, while run-to-run variance remains unaffected by any prompt changes. We show that prompt-sensitivity is task-dependent, running from 13%13\% to 115%115\%. We fit a simple predictor that can price a full distribution of task specifications and thinking effort configurations from a single cheap probe on an unseen task within 36%36\%, improving over prior work in predicting token spend. Our work provides initial results quantifying the effects of task specification on agentic token spend and introduces a method that can be used to systematically evaluate the cost of AI coding workflows.