AI RESEARCH
When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
arXiv CS.AI
•
ArXi:2605.12947v1 Announce Type: cross LLM-enabled AI workflows increasingly produce outputs through iterative generate-evaluate-revise loops. Each iteration can improve the candidate, but it also creates a release decision: when to stop and output the current result? This raises a statistical challenge because deployment-time evaluator scores are adaptively generated and repeatedly monitored, yet the likelihood models or exchangeability assumptions typically used for calibration are unavailable. We propose an always-valid release wrapper for existing generator-evaluator pipelines.