AgentDecarbonizer：面向AI智能体的碳感知执行方案

中文摘要 AI 辅助

AI智能体将大语言模型从单次提示-响应交互扩展为长期运行、面向目标的工作流，这类工作流会发起多次模型调用、调用工具并与外部环境交互，可实现软件修复、数据分析、实验管理等任务，但其重复的模型调用会产生大量碳排放。本文使用WildClawBench表征OpenClaw智能体工作负载的碳排放，结果表明碳排放取决于令牌消耗、上下文缓存复用以及电网的碳强度；研究发现截止日期灵活性是碳感知执行的机遇：智能体任务可等待碳强度更低的时段或转移至碳强度更低的电网，但这需要处理时间转移时的不确定执行时间，以及空间转移时的缓存上下文重计算问题。本文提出AgentDecarbonizer，一款与OpenClaw并行运行的AI智能体碳优化器，给定任务提示和用户指定的截止日期，它会保守估计任务时长并选择满足截止日期的执行调度方案，同时考虑空间转移时的缓存重计算开销。在包含60个智能体任务、涉及4个电网的WildClawBench工作负载上评估显示，AgentDecarbonizer相比不考虑碳因素的基线方案，可将碳排放最多降低57.9%；相比任务启动时选择碳最优电网的基线方案，最多降低37.5%。

英文摘要

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.

发表机构

• University of Waterloo（滑铁卢大学）
• University of Chicago（芝加哥大学）

机构由 AI 辅助整理，请以论文原文为准。