paperMay 2026Unreviewed

When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions

Minfeng Qi, Tianqing Zhu, Zijie Xu, Congcong Zhu, Qin Wang, Wanlei Zhou

Abstract

Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets. A single LLM instance often compresses evidence extraction, planning, execution, and validation into one context, which increases the risk of context drift and error propagation. Existing LLM-based multi-agent systems support general collaboration, but they do not explicitly model the role boundaries, artifact provenance, and cost constraints t

Cite

@misc{qi2026when,
  title = {{When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions}},
  author = {Minfeng Qi and Tianqing Zhu and Zijie Xu and Congcong Zhu and Qin Wang and Wanlei Zhou},
  year = {2026},
  month = may,
  eprint = {2605.08763},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.08763}
}