paperMay 2026Unreviewed

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs

Jianan Li, Simeng Qin, Xiaojun Jia, Lionel Z. Wang, Tianhang Zheng, Xiaoshuang Jia, Yang Liu, Xiaochun Cao

Abstract

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their explicit chain-of-thought (CoT) mechanism introduces new security risks, making them particularly vulnerable to jailbreak attacks. Existing approaches often rely on static CoT templates to elicit harmful outputs, but such fixed designs suffer from limited diversity, adaptability, and effectiveness. To overcome these lim

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{li2026reasoning,
  title = {{Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs}},
  author = {Jianan Li and Simeng Qin and Xiaojun Jia and Lionel Z. Wang and Tianhang Zheng and Xiaoshuang Jia and Yang Liu and Xiaochun Cao},
  year = {2026},
  month = may,
  eprint = {2605.24497},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.24497}
}