SOURCE-LINKED INTELLIGENCE

Canonical Procedural Actions: An Auditable Annotation Protocol for Tool-Use Agent Traces

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Tool-use agent traces identify messages and API calls, but procedural analyses also need explicit units of action and inspectable links to their evidence. We present Canonical Procedural Actions (CPAs), an annotation protocol that records a procedural function, its first agent-event anchor, the agent events that realize it, and separate contextual evidence. Multiple actions may share a message anchor without an inferred within-message order. A retail case study produces a versioned 24-entry codebook through open induction, recorded consolidation, and successive application audits. Two isolated

Read original source ↗ Open in workspace

recordType

paper

region

Global