AI 中文总结
针对金融机构模型风险管理问题，提出动态IaC治理循环，贡献包括引入校准DoA得分、构建DAG定义算法、开发轨迹监测协议及解决版本变化等实际复杂性问题，用于智能体人工智能系统风险传播与漂移检测。
AI 中文摘要
随着金融机构从传统预测模型向自主智能体系统过渡，传统模型风险管理（MRM）的静态模型库存要求面临结构过时问题。本文提出了一个动态的代码即库存（IaC）治理循环，将模型库存视为一个有生命力的架构组件而非定期文档工件。我们有四个主要贡献。首先，引入校准的自主程度（DoA）重要性得分及明确的分类工具复杂性加权方案，解决朴素加法风险公式的主导问题。其次，将智能体库存构建为有向无环图（DAG）并定义正式的复合风险传播算法，上游验证失败会对所有可达后代施加风险惩罚。第三，基于集成的思维链（CoT）嵌入的分布余弦漂移开发轨迹监测协议，有构建和认证黄金路径基线的明确程序，一种匹配自举校准，且有两阶段响应来区分合法推理变化与有害漂移。第四，解决了先前文献中基本不存在的实际复杂性问题，如大语言模型基础模型版本变化、名义上无环的智能体图中的潜在反馈回路以及在风险传播之前进行验证的两遍执行结构。
英文摘要
As financial institutions transition from traditional predictive models to autonomous agentic systems, the static model inventory requirements of traditional model risk management (MRM) face structural obsolescence. This paper proposes a dynamic Inventory-as-Code (IaC) governance loop that treats the model inventory as a living architectural component rather than a periodic documentation artifact. We make four principal contributions. First, we introduce a calibrated Degree of Autonomy (DoA) materiality score with an explicit, taxonomized tool-complexity weighting scheme that addresses the dominance problem of naive additive risk formulations. Second, we construct the agent inventory as a Directed Acyclic Graph (DAG) and define a formal Composite Risk Propagation algorithm under which upstream validation failures induce risk penalties on all reachable descendants. Third, we develop a Trajectory Monitoring protocol based on distributional cosine drift across ensembled Chain-of-Thought (CoT) embeddings, with an explicit procedure for constructing and certifying the Golden Path baseline, a matched-bootstrap calibration that we show is necessary to avoid a severe false-positive artifact in the naive alternative, and a two-stage response that separates legitimate reasoning variation from detrimental drift without demanding that a single exceedance event trigger an irreversible action. Fourth, we address practical complications largely absent from the prior literature: LLM base-model version changes, latent feedback loops in nominally acyclic agent graphs, and a two-pass execution structure that stages validation ahead of risk propagation.
