Research · curated 29 Jul 2026

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment

Coverage timeline

29 Jul 2026arxiv.orgprimary

Single-source research — first reported, latest, and curated coincide.

Why it matters

Multi-turn jailbreak learning like DC-GRPO shows how automated attackers can reliably bypass LLM safety alignment across realistic conversational settings, raising the bar for red-teaming and defensive alignment.

The paper "MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment" introduces DC-GRPO, a turn-level credit assignment framework for training reinforcement-learning attackers that jailbreak LLMs across multi-turn conversations. The authors report attack success rates (ASR5@3) of roughly 98% across multiple victim LLMs and benchmarks, substantially outperforming prior methods such as SEMA and TROJail.