# $M^3$: A Multi-LLM System for Multi-Turn Jailbreaking as a Markov Decision Process

> 全文为英语

**Published:** 2026年10月26日
**Author:** Yuqing Huang, Jack Ji, Jithin Pradeep, Sagarika Suresh, Jekaterina Novikova
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/m-3-a-multi-llm-system-for-multi-turn-jailbreaking-as-a-markov-decision

arXiv:2610.31937v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) remain vulnerable to carefully orchestrated multi-turn interactions that progressively bypass safety mechanisms. However, many existing red-teaming approaches rely on heuristics or impose strong…

> 内容来自原始来源： **arXiv — cs.AI**
> [在 arXiv — cs.AI 阅读全文](https://arxiv.org/abs/2610.31937)

**标签：** #Papers with Code #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*