@inproceedings{liu-etal-2026-astra,
    title = "{ASTRA}: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking {LLM}s",
    author = "Liu, Xu  and
      Chen, Yan  and
      Ling, Kan  and
      Zhu, Yichi  and
      Zhang, Hengrun  and
      Fan, Guisheng  and
      Yu, Huiqun",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1843/",
    pages = "39691--39710",
    ISBN = "979-8-89176-390-6",
    abstract = "Despite extensive safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. However, existing methods generally lack the capability for continuous learning and self-evolution from interactions, limiting the diversity and adaptability of attack strategies. To address this, we propose ASTRA, an automated framework capable of autonomously discovering, retrieving, and evolving attack strategies. ASTRA operates on a closed-loop ``attack-evaluate-distill-reuse'' mechanism, which not only generates attack prompts but also automatically distills reusable strategies from every interaction. To systematically manage these strategies, we introduce a dynamic three-tier strategy library (Effective, Promising, and Ineffective) that categorizes strategies based on performance. This hierarchical memory mechanism enables the framework to enhance efficiency by leveraging successful patterns while optimizing the exploration space by avoiding known failures. Extensive experiments in a black-box setting demonstrate that ASTRA significantly outperforms existing baselines."
}