双账本模型：跨云跨模型多智能体AI系统的交易粒度成本核算
原标题：The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record
AI 摘要
该论文指出，企业多智能体AI系统横跨多云、多模型与多个记录系统，但财务只能拿到结算粒度的账单数据，无法回答单笔订单、理赔或案件消耗了多少AI成本。作者形式化了结算粒度与交易粒度之间的错配，提出「双账本模型」：将符合FOCUS规范的结算账本与基于OpenTelemetry GenAI遥测的调用粒度归因账本关联，并通过分层关联脊柱、版本化费率卡和周期对账实现按交易归因成本。仿真显示，在追踪传播降至零时成本覆盖率仍高于99%，对账残差可在0.24个百分点内找回未计量支出，中途门控可将p99交易成本降低最多61%。
正文节选
The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record Abstract Enterprises run business transactions through multi-agent AI systems spanning clouds, large language models (LLMs), orchestration harnesses, and systems of record. Finance receives AI cost only at settlement grain, aggregated by SKU and charge period. The business question — what did this order, claim, or case cost in AI? — cannot be answered from billing data,