TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards

arXiv:2512.07761v3 Announce Type: replace Abstract: Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of training automated multi-turn attackers to probe model safety vulnerabilities. However, existing approaches typically rely on turn-level optimization, which is insufficient for learning long-term attack strategies. To bridge this gap, we formulate this task as a multi-tur