We introduce TRACE, a cross-domain engineering framework for trustworthy agentic AI in operationally critical domains. TRACE combines a four-layer reference architecture with an explicit classical-ML vs. LLM-validator split (L2a/L2b), a stateful orchestration-and-escalation policy (L3), and bounded human supervision (L4); a metrologically grounded trust-metric suite mapped to GUM/VIM/ISO 17025; and a Model-Parsimony principle quantified by the Computational Parsimony Ratio (CPR). Three instantiations--clinical decision support, industrial multi-domain operations, and a judicial AI assistant--transfer the samearchitecture and metrics across principally different governance contexts. The L2a/L2b separation makes the use of large language models a deliberate design decision rather than an architectural default, with parsimony quantified through CPR. TRACE introduces CPR as a first-class design principle in trustworthy-AI engineering.

翻译：我们提出TRACE，这是一种面向操作性关键领域可信代理型AI的跨领域工程框架。TRACE结合了四层参考架构（其中显式区分了经典机器学习层与大型语言模型验证层（L2a/L2b））、带状态治理的编排和升级策略（L3）、受限人工监督（L4），并基于计量学构建了符合GUM/VIM/ISO 17025标准的信任度量套件，以及通过计算简约比（CPR）量化的模型简约原则。三个实例化应用——临床决策支持、工业多域操作与司法AI助手——将同一架构和度量标准迁移至原则上不同的治理环境。L2a/L2b分离使大型语言模型的使用成为有意识的设计决策而非架构默认选择，其简约性通过CPR量化。TRACE将CPR引入为可信AI工程中的首要设计原则。