为智能体系统提供可预测的碳与成本管控框架，避免事后失控。
Green SARC: Predictive Cost and Carbon Governance for Agentic AI Systems
- 构建四层架构治理框架，从源头控制资源消耗
- 实测显示任务深度呈平方级增长，实际耗能超预期31%
- 零超支门禁设计，适合高预算敏感型智能体应用
智能体系统通过工具和子智能体执行任务，但其财务与环境成本的管控仍依赖于执行后或旁侧的仪表盘。Green SARC 将 SARC 治理架构框架（智能体循环中四个执行点）应用于 FinOps 与 GreenOps，提出可预测的管控理论。报告四项与政策无关的结果：(i) 无约束的「状态雪球」在循环深度上为 $Θ(n^2)$；在 3,000 条真实多步计划（SWE-rebench）中，100% 符合该规律，中位曲率 $ar{c}_2=216$ 超过线性累积预测值 $p/2=134$，表明真实计划增速更快；(ii) 在真实残差上，正态-$σ$ 门限覆盖率不足（名义 95% 下仅 92%）；分拆-共形校准达到 95.2%；(iii) 期望预算下调参的软拉格朗日惩罚在 91.5% 的种子中突破预算；而架构门禁实现 0% 突破；(iv) 在绑定预算下，门禁对合成与真实（BurstGPT）请求的超支率均为 0%。端到端的令牌/美元/碳节省率达 47–55%，但具体数值取决于策略设定，由范围-上限旋钮决定，而非门禁拒绝。代码开源、无依赖，并附每个结论的再生脚本。
原文摘要 · Abstract (English)
Agentic AI systems act through tools and sub-agents, yet the controls meant to bound their financial and environmental cost still sit on dashboards evaluated beside or after execution. Green SARC applies the SARC governance-by-architecture framework -- four enforcement sites in the agent loop -- to FinOps and GreenOps, contributing the theory of what to enforce and how to predict it. We report four policy-independent results. (i) The unconstrained "State Snowball" is $Θ(n^2)$ in loop depth; on 3,000 real multi-step plans (SWE-rebench) it holds on 100%, with median curvature $\hat{c}_2=216$ exceeding the linear-accretion prediction $p/2=134$ -- real plans accrete faster than the model. (ii) On real residuals the Normal-$σ$ gate under-covers (92% at nominal 95%); split-conformal calibration holds (95.2%). (iii) A soft Lagrangian penalty tuned to the budget in expectation breaches it on 91.5% of seeds; the architectural gate breaches 0%. (iv) Under binding budgets the gate's over-budget incidence is 0% on synthetic and real (BurstGPT) arrivals. End-to-end token/USD/carbon savings (47--55%) are real but policy-dependent in magnitude -- set by a scope-cap knob, not by gate rejections. The library is open-source, dependency-free, and ships a regeneration script for every cited number.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。