ملف الباحث
Anonymous
ورقتان في مجموعة PaperMetrix
المنشورات
أوراق هذا المؤلف
-
WhyLab: A Causal Audit Framework for Stable Agent Self-Improvement
2026 · Zenodo (CERN European Organization for Nuclear Research)
Self-improving AI agents lack runtime safeguards that prevent evaluation drift, fragile outcome acceptance, and unbounded parameter updates from compounding into catastrophic policy degradation. WhyLab introduces a causal audit framework comprising three complementary defenses: C1: Information-theoretic …