SOURCE-LINKED INTELLIGENCE

EvoFlint: An Evolutionary Atlas of Multi-Turn LLM Vulnerabilities

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Frontier language models that refuse harmful single-turn prompts often comply when the same intent is reached gradually over many turns, making multi-turn attacks one of the least understood failure modes of large language models. Most automated red-teaming methods treat this as a generation problem: produce attacks that break the model. We argue it is better framed as a search problem: discover, organize, and iteratively refine a diverse archive of attack strategies, producing a structured map of how a target model fails rather than a list of one-off successes. We introduce EvoFlint, which ap

Read original source ↗ Open in workspace

recordType

paper

region

Global