SOURCE-LINKED INTELLIGENCE

When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative execution, concurrency, and partial failures, the resulting external state may be inconsistent with the workflow's intended resolution: required effects may be missing or duplicated, aborted effects may survive, and committed effects may depend on provisional state that is later withdrawn. Advanced transaction models address related failures, but assume that lower-level operations expose the semantics they depend on: whether an effect occurred, whether

Read original source ↗ Open in workspace

recordType

paper

region

Global