Attributing Agent Failures to Their History Needs an Executed Counterfactual: Toward a Reporting Standard

arXiv cs.AINovember 5, 2026en

arXiv:2611.05650v1 Announce Type: new Abstract: Published explanations of why long-horizon agents fail are commonly taxonomies labeled over completed trajectories: a judge reads a transcript and names the failure. We argue that a claim attributing an agent's behavior to its history should carry intervention-verified evidence, per instance or via a validated estimator: freeze an executable mid-trajectory state, alter only the history the agent sees, and continue - executed rather than inferred from the transcript, at a state whose restoration has been measured, with a replay certificate matched to the estimand. Each of the four manipulation classes we name has a precedent, and several methods

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning
• Agenter