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

arXiv cs.AIOctober 26, 2026en

arXiv cs.AI

AI Global Wire

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 assumptions that limit their applicability in fully black box settings. We address this gap by introducing $M^3$, an automated red-teaming framework that formalizes multi-turn jailbreaking as a finite-horizon Markov Decision Process (MDP). In $M^3$, an attacker LLM interacts with a target LLM while operating over a compact internal state produced by a state LLM. Across two benchmarks and six target models, $M^3$ consi

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Verktyg
• Forskning