[
    {
        "id": "osp-15853",
        "type": "article-journal",
        "title": "Valid Stopping in Adaptive Generator-Verifier Loops",
        "author": [
            {
                "family": "Hegazy",
                "given": "Mahmoud"
            },
            {
                "family": "Jordan",
                "given": "Michael I."
            },
            {
                "family": "Dieuleveut",
                "given": "Aymeric"
            }
        ],
        "URL": "https://omanscience.com/en/articles/valid-stopping-in-adaptive-generator-verifier-loops",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Numerous agentic workflows are based on a generator-verifier loop: a generator proposes candidates, a cheap verifier scores them, and the workflow terminates when a proposal is verified as good enough. The verifier typically proxies a more costly ground-truth oracle, and as the generator searches adaptively against it, false acceptances may accumulate. Proposals can pass the proxy but fail under the costlier ground-truth check. We study when to stop these loops while controlling the false discovery rate of the accepted proposals. Our construction introduces tools of independent interest in distribution-free statistical testing and conformal risk control, including analysis of $e$-values constructed through index betting and a novel conformal risk control procedure for non-monotone losses. We validate the approach in synthetic settings and on a protein-design benchmark."
    }
]