Safety · Concept
Distributionally Robust Probabilistic Verification for AI Agents
Sound framework using distributionally robust optimization to compute upper bounds on policy violation probability for AI agents with probabilistic predicates.
Forecast horizon
Connections
Connections · 3
How this node ties into the rest of the map, and the evidence behind each link.
to · applies to 2/10
NRT-Bench: Multi-Turn Red-Teaming Benchmark for Safety-Critical AI Agents Probabilistic verification frameworks are evaluated on standard benchmarks for terminal and tool-calling agents, relevant to safety-critical deployments.
+2 growth to · supports 2/10
Systems-Safety Methods for Agentic AI Loss-of-Control Risk Distributionally robust probabilistic verification provides formal safety guarantees for agentic AI runtime policies.
+2 growth from · informs 2/10
Apothem-Optimal Neural Network Robustness Certifications Apothem-optimal certifications provide tractable robustness bounds complementing probabilistic verification approaches for AI agents.
+2 growthSignal sources
Signal sources
Dated facts from primary sources in this direction.
US evaluation centre Jun 2025
In June 2025 the US AI Safety Institute was renamed the Center for AI Standards and Innovation (CAISI), pivoting toward security, standards and adversary-model assessment.
NIST → Frontier safeguards May 2025
Anthropic activated its ASL-3 deployment and security standard with Claude Opus 4 on 22 May 2025 — the first real-world trigger of a responsible-scaling tier, focused on blocking bio-weapon uplift.
Anthropic → Cross-border testing 2025
The International Network of AI Safety Institutes (launched Nov 2024) ran a third joint testing exercise focused on agentic AI systems across cyber and fraud strands.
European Commission — AI Office →