解决智能体系统中任务委托的可观测性难题
Observability for Delegated Execution in Agentic AI Systems
- 设计轻量网关与统一信息模型绑定执行时的委托上下文
- 实现跨工具委托范围的可靠追溯，无需依赖时间窗口推测
- 适合需要审计与安全追踪的AI代理系统开发者
在基于大模型的智能体系统中，委托范围内的执行行为无法通过标准可观测性手段（如审计日志和执行轨迹）识别，因为不同且不兼容的委托分配可能产生完全相同的日志与轨迹。由于智能体动态选择工具、同一指令下运行序列多变，并生成协作子代理，导致执行轨迹碎片化且交错，仅凭因果结构难以重建委托范围。尽管每项操作均有授权与记录，现有审计、追踪与安全架构缺乏语义能力，无法还原特定委托下的实际行为。本文聚焦于委托范围内的归属与访问/共享足迹重建，而非意图推断或推理过程复现。提出一种面向智能体的可观测性基础架构，包含轻量级网关与通用信息模型，可在执行时绑定委托上下文，实现跨工具的可靠委托范围重构，支持直接的取证查询，无需启发式的时间窗口关联。
原文摘要 · Abstract (English)
Delegation-scoped execution is not identifiable from standard observables: audit logs and execution traces can be identical under multiple incompatible delegation assignments. This gap is especially acute in LLM-based agentic systems, where agents dynamically select tools, vary execution sequences across runs for the same instruction, and spawn cooperating sub-agents. These dynamics fragment and interleave traces, making delegation-scoped reconstruction from causal structure alone structurally underdetermined. Although individual actions are authorized and logged, existing audit, tracing, and security schemas lack the semantics to reconstruct what actions occurred under a given delegation across heterogeneous systems. We focus on delegation-scoped attribution and access/share footprint reconstruction, not intent inference or reasoning reconstruction. We present an agent-aware observability substrate consisting of a lightweight gateway and a common information model that binds delegation context at execution time. This enables reliable cross-tool delegation-scoped reconstruction and direct forensic queries without heuristic time-window correlation.
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。