提出可信赖智能体系统框架，用量化指标保障关键领域应用安全
TRACE: A Metrologically-Grounded Engineering Framework for Trustworthy Agentic AI Systems in Operationally Critical Domains
- 分层架构分离大模型与验证模块，明确设计选择
- 引入计算简约比(CPR)量化模型简洁性，降低风险
- 跨医疗、工业、司法领域验证，适合高可靠性场景
我们提出TRACE，一个面向操作关键领域的可信智能体AI系统跨域工程框架。该框架包含四层参考架构：显式划分经典机器学习与大语言模型验证器（L2a/L2b），状态化编排与升级策略（L3），以及有限人类监督（L4）；基于量测学的可信度量套件，对应GUM/VIM/ISO 17025标准；并引入模型简约性原则，以计算简约比（CPR）进行量化。三个实例——临床决策支持、工业多领域运营、司法AI助手——在截然不同的治理背景下复用同一架构与度量体系。L2a/L2b分离使大模型使用成为有意识的设计决策而非默认配置，且通过CPR实现简约性量化。TRACE首次将计算简约比作为可信AI工程中的首要设计原则。
原文摘要 · Abstract (English)
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.
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。