[
    {
        "id": "osp-15855",
        "type": "article-journal",
        "title": "When to Remember, When to Abstain: Category-Conditioned Retention for Reliable Agent Memory",
        "author": [
            {
                "family": "Owolabi",
                "given": "Olukunle"
            },
            {
                "family": "Gupta",
                "given": "Pulkit"
            },
            {
                "family": "Wang",
                "given": "Fei"
            }
        ],
        "URL": "https://omanscience.com/en/articles/when-to-remember-when-to-abstain-category-conditioned-retention-for-reliable-agent-memory",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Persistent agent memory is only as reliable as its retention decision: an assertion weakly supported by its source can be stored and later reused as established fact. We study whether the retention decision should be governed by a confidence bar conditioned on the semantic category of the assertion rather than by a single global threshold, retaining well-evidenced categories liberally while abstaining more aggressively where inference is unreliable. We evaluate this in a deployed cold-start memory pipeline on 100 synthetic personas. The empirical evaluation is motivated by a sharp reliability asymmetry: across 4{,}715 candidate assertions, only 77.9\\% of value and belief assertions are supported by their source, versus 96.2\\% for all other categories. A global confidence threshold cannot separate these: it either admits unsupported value claims or discards well-evidenced ones. Conditioning the threshold on category resolves the tradeoff. In repeated held-out evaluation, a stricter bar on values alone reduces unsupported retentions from 6.2\\% to 4.0\\% (an ${\\approx}36\\%$ relative reduction, modest but consistent across folds) and, as corroborating evidence, preserves an estimated 13 percentage points more coverage (95\\% CI 9.8--16.0) than a global threshold at comparable retention. Our results suggest that reliable retention depends on the type of assertion, not on confidence alone, and that a category-conditioned threshold can act as a simple, effective form of selective prediction at the write boundary."
    }
]