当智能体信任跨越组织边界：结构性外部化与信任证据参考模型

中文摘要 AI 辅助

智能体系统日益跨组织边界调用工具、服务、数据及其他智能体，然而依赖方无法仅凭生产域的控制与记录来评估被委托的行动。本文通过综合可信人工智能治理、智能体安全、分布式信任管理、身份、溯源、保证及控制平面研究，提出了信任即服务（TaaS）。分析单元是一种跨域依赖命题，该命题指明签发者、主体与行动、依赖方、管理边界、证据依赖、不利条件以及所需的验证或裁决语义。三条件结构性外部化诊断可识别出依赖多个域、需要独立于生产者的依赖、并且必须在撤销、失败、冲突记录或争议后仍可审查的命题。针对此类命题，本文规定了一种信任证据信封：一个不可变的工作流清单，链接到仅追加的、由签发者归属的证明，用于任务范围权限、策略与执行决策、溯源、有效性、披露、状态、挑战及恢复。一个拓扑中立的逻辑参考模型将这些功能分配给明确的角色和信任域。三个分析场景及TaaS-Eval协议提案定义了清单、独立消费者、硬门控、对抗性证据测试、指标及可复现工件报告。通过将既定的身份、授权、溯源、保证及治理机制组合在受限的委托行动周围，TaaS为跨域依赖提供了可复用的配置文件。它使证据依赖、独立验证、挑战及恢复显式化，支持可互操作的治理和未来评估，而不将生产者断言视为地面真相。

英文摘要

Agentic systems increasingly invoke tools, services, data, and other agents across organizational boundaries, yet a relying party cannot assess a delegated action solely from producing-domain controls and records. This paper develops Trustworthiness as a Service (TaaS) through a synthesis of trustworthy-AI governance, agent security, distributed trust management, identity, provenance, assurance, and control-plane research. The analytical unit is a cross-domain reliance proposition that names the issuer, subject and action, relying party, administrative boundary, evidence dependencies, adverse condition, and required verification or adjudication semantics. The three-condition structural-externalization diagnostic identifies propositions that depend on multiple domains, require producer-independent reliance, and must remain reviewable after revocation, failure, conflicting records, or dispute. For such propositions, the paper specifies a trust-evidence envelope: an immutable workflow manifest linked to append-only, issuer-attributed attestations for task-scoped authority, policy and execution decisions, provenance, validity, disclosure, status, challenge, and recovery. A topology-neutral logical reference model assigns these functions to explicit roles and trust domains. Three analytical scenarios and the TaaS-Eval protocol proposal define manifests, independent consumers, hard gates, adversarial evidence tests, metrics, and reproducible artifact reporting. By composing established identity, authorization, provenance, assurance, and governance mechanisms around a bounded delegated action, TaaS provides a reusable profile for cross-domain reliance. It makes evidence dependencies, independent verification, challenge, and recovery explicit, supporting interoperable governance and future evaluation without treating producer assertions as ground truth.

发表机构

• China Mobile Jiutian Artificial Intelligence Technology (Beijing) Co., Ltd.（中国移动九天人工智能技术（北京）有限公司）

机构由 AI 辅助整理，请以论文原文为准。