Skip to content
Research

Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification.

arXiv:2609.33662v2 Announce Type: replace Abstract: Imperfect verifiers can assign a harmful update direction even when clipping and regularization bound its magnitude. We introduce Audit-First VAPO, which separates discrete directional admission from continuo

arXiv cs.AIResearch source·