TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking

Abstract

The rise of LLM agents introduces a new threat by enabling planning, coding, and even end-to-end execution of expert-level attack workflows. However, this threat remains underexplored and underestimated since (i) safety alignment prevents LLMs from directly generating harmful instructions, and (ii) most existing jailbreak methods cannot consistently induce agents to execute malicious operations. In this paper, we propose TRACE, a practical agentic jailbreaking framework to further reveal the ris

Categories

Framework mappings

Suggested from the entry's categories.

@misc{zeng2026trace,
  title = {{TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking}},
  author = {Churui Zeng and Weiwei Qi and Kedong Xiu and Tianhang Zheng and Chaochao Lu and Liang He and Zhan Qin and Kui Ren},
  year = {2026},
  month = may,
  eprint = {2605.30883},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.30883}
}