PAPER·July 24, 2026When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time ModerationarXiv
PAPER·April 29, 2026BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric DebateHugging Face Papers
PAPER·April 22, 2026Symbolic Guardrails for Domain-Specific Agents: Stronger Safety and Security Guarantees Without Sacrificing UtilityHugging Face Papers
PAPER·April 8, 2026Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem ProvingHugging Face Papers