RAMP: Risk-Aware Multi-Turn Planning for Jailbreak Red-Teaming

Yize Liu, Yunyun Hou, Aina Sui


Abstract
Multi-turn jailbreaking is a critical approach for evaluating the safety of large language models (LLMs). However, existing methods largely rely on heuristic strategies or trained attack agents, lacking a unified state-action formulation and systematic search over strategy compositions, and often struggling to balance attack success rate with query overhead. We propose RAMP, which formulates multi-turn jailbreaking as a risk-aware PDDL planning problem. Specifically, we characterize dialogue safety using predicate-based states, abstract common jailbreak strategies as high-level actions, and introduce a closed-loop framework that iteratively plans and executes each turn via a Judge, a Transitioner, and a Planner. Experimental results show that RAMP achieves consistently strong attack performance across both open-source and closed-source target models, while remaining effective under stricter turn budgets and yielding a favorable efficiency–effectiveness trade-off. Ablation studies, interpretability analyses, and extended experiments further show that multi-step planning, clue accumulation, and consistent findings across evaluator settings are key factors underlying these gains.
Anthology ID:
2026.findings-acl.925
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18553–18564
Language:
URL:
https://aclanthology.org/2026.findings-acl.925/
DOI:
10.18653/v1/2026.findings-acl.925
Bibkey:
Cite (ACL):
Yize Liu, Yunyun Hou, and Aina Sui. 2026. RAMP: Risk-Aware Multi-Turn Planning for Jailbreak Red-Teaming. In Findings of the Association for Computational Linguistics: ACL 2026, pages 18553–18564, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
RAMP: Risk-Aware Multi-Turn Planning for Jailbreak Red-Teaming (Liu et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.925.pdf
Checklist:
 2026.findings-acl.925.checklist.pdf