Papers with multi-turn reinforcement learning problem
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to training multi-turn attackers to probe model safety vulnerabilities rely on turn-level optimization, which is insufficient for learning long-term attack strategies. |
| Approach: | They propose a multi-turn reinforcement learning problem that optimizes the harmfulness of the final-turn response as the outcome reward. |
| Outcome: | The proposed approach improves attack success rates across multiple models and benchmarks, highlighting the effectiveness of the proposed approach. |