双账本模型：跨云、模型与记账系统的多智能体 AI 交易粒度成本核算
The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record
AI 导读
arXiv 论文提出双账本模型（Two-Ledger Model），将 FOCUS 结算账单数据与基于 OpenTelemetry GenAI 遥测的调用粒度归因账本相连，解决企业无法核算单笔订单、理赔或案例 AI 成本的问题。
正文 · 原文
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, because providers never see enterprise transaction boundaries. The FinOps Open Cost and Usage Specification (FOCUS) gives billing data one schema across providers but remains settlement-grain even as it adds AI token and requester attribution. We formalize this grain mismatch, derive seven requirements, and propose the Two-Ledger Model: a settlement ledger of FOCUS-conformant billing data joined to an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry. A layered correlation spine (trace context, A2A/MCP metadata, business-key correlation, probabilistic matching) assigns each record to its business transaction with recorded method and confidence; a versioned rate card prices usage in near real time; period reconciliation ties both ledgers to the invoice, and the unexplained residual identifies shadow AI. Costs are reported per order, claim, or outcome with agentic cost metrics. A simulation with known ground truth shows the spine sustaining cost coverage above 99% as trace propagation falls to zero, the reconciliation residual recovering planted unmetered spend within 0.24 percentage points while flagging provider billing errors, and mid-flight gating cutting p99 transaction cost by up to 61% at a 2-4% false-pause rate. We propose the attribution ledger as an invocation-grain FOCUS profile for standardization.
| Comments: | 16 pages, 5 figures, 12 tables. Code and synthetic data: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Multiagent Systems (cs.MA) |
| ACM classes: | I.2.11; K.6.2; C.2.4 |
| Cite as: | arXiv:2611.06989 [cs.AI] |
| (or arXiv:2611.06989v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06989 arXiv-issued DOI via DataCite |
Submission history
From: Vivek Acharya [view email]
[v1]
Wed, 4 Nov 2026 17:04:04 UTC (66 KB)
来源：arXiv cs.AI · arxiv.org