Safety · Concept
Multi-Agent Adversarial Stress Testing of Role-Playing Agents
Interrogator–target–judge platform with six progressive strategies exposing multi-turn RPLA persona and ethics failures.
Forecast horizon
Connections
Connections · 2
How this node ties into the rest of the map, and the evidence behind each link.
to · supports 3/10
NRT-Bench: Multi-Turn Red-Teaming Benchmark for Safety-Critical AI Agents Multi-turn multi-strategy interrogator design extends red-teaming practice for persona-constrained agents.
+3 growth to · applies to 3/10
LLM Psychological Manipulation in Multi-Turn Interactions Multi-turn adversarial strategies stress-test persona fidelity and ethical drift in RPLAs.
+3 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 →