AMT-X: Multi-Turn Red-Teaming Framework Reveals Gap Between Partial and Fully Actionable LLM Harm

Jul 14, 2026

Researchers introduce AMT-X, a phase-structured multi-turn red-teaming framework that employs a multi-role jury and phase-conditioned checklists to evaluate the safety of large language models (LLMs). When tested on six frontier models, AMT-X achieved 97.6-100% attack success under lenient scoring, but only 66.7-78.6% under stricter criteria requiring complete operational detail. This demonstrates a substantial gap between partially and fully actionable harmful outputs.

Why it matters: The findings indicate that current single-turn safety evaluations may underestimate the risks posed by adaptive adversaries, emphasizing the need for more nuanced assessment methods in AI safety.

Full story at: arXiv Cryptography and Security ↗