让AI代理系统实时检测并自动执行治理规则，防止违规行为发生。
Governance-Aware Agent Telemetry for Closed-Loop Enforcement in Multi-Agent AI Systems
- 在OpenTelemetry基础上扩展治理属性，实现可追踪的合规数据采集。
- 使用声明式规则在200毫秒内完成违规行为实时检测。
- 支持分级干预措施，适合企业级多智能体系统的安全管控场景。
企业级多智能体AI系统每小时产生数千次智能体间交互，但现有可观测性工具仅记录依赖关系而不采取行动。OpenTelemetry和Langfuse虽收集遥测数据，却将治理视为事后分析任务，而非实时执行目标，导致‘观察但不行动’的漏洞——违规行为往往在造成损失后才被发现。本文提出治理感知的智能体遥测架构（GAAT），构建从数据采集到自动执行的闭环。GAAT引入：(1) 治理遥测模式（GTS），在OpenTelemetry中扩展治理属性；(2) 实时违规检测引擎，基于OPA兼容的声明式规则，在亚200毫秒延迟内运行；(3) 治理执行总线（GEB），支持分级干预策略；(4) 可信遥测平面，通过密码学溯源保障数据可信性。
原文摘要 · Abstract (English)
Enterprise multi-agent AI systems produce thousands of inter-agent interactions per hour, yet existing observability tools capture these dependencies without enforcing anything. OpenTelemetry and Langfuse collect telemetry but treat governance as a downstream analytics concern, not a real-time enforcement target. The result is an "observe-but-do-not-act" gap where policy violations are detected only after damage is done. We present Governance-Aware Agent Telemetry (GAAT), a reference architecture that closes the loop between telemetry collection and automated policy enforcement for multi-agent systems. GAAT introduces (1) a Governance Telemetry Schema (GTS) extending OpenTelemetry with governance attributes; (2) a real-time policy violation detection engine using OPA-compatible declarative rules under sub-200 ms latency; (3) a Governance Enforcement Bus (GEB) with graduated interventions; and (4) a Trusted Telemetry Plane with cryptographic provenance.
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。