AI RESEARCH
Failure-Centered Runtime Evaluation for Deployed Trilingual Public-Space Agents
arXiv CS.AI
•
ArXi:2604.23990v1 Announce Type: new This paper presents PSA-Eval, a failure-centered runtime evaluation framework for deployed trilingual public-space agents. The central claim is that, when the evaluation object shifts from a static input-output mapping to a runtime system, the basic unit of analysis should shift from score to failure. PSA-Eval extends the conventional chain Question -> Answer -> Score -> End into Question -> Batch -> Run -> Score -> Failure Case -> Repair -> Regression Batch, making failures traceable, reviewable, repairable, and regression-testable.