Who Verifies the Graph? Misspecification Attacks on Causal Action Verification for Language Agents

Excerpt

arXiv:2609.40027v1 Announce Type: cross Abstract: Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed intervention is identifiable against a committed action-state graph, and they issue a certificate that carries the identification argument and a one-sided lower confidence bound. One such verifier, CIVeX, reports zero false executions on a confounded tool-use benchmark. We red-team it by corrupting only the committed graph. Omitting a single bidire