{
  "id": 797,
  "url": "https://arxiv.org/abs/2606.20408v3",
  "title": "NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms",
  "summary": "Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark for multi-turn red-teaming of LLM agents acting as operators of a safety-critical system, instantiated in a simulated nuclear power plant control room. A five-role operator team, each backed by a configurable LLM, runs a plant governed by six critical s",
  "authors": "Hanwool Lee, Dasol Choi, Bokyeong Kim, Haon Park, Seung Geun Kim",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-18T15:57:53.000Z",
  "fetched_at": "2026-07-14T14:14:46.037Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/797",
  "original_url": "https://arxiv.org/abs/2606.20408v3",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}