Skip to content
Search
paperMay 2026Unreviewed

Defending LLM-based Multi-Agent Systems Against Cooperative Attacks with Sentence-Level Rectification

Yaoyang Luo, Zhi Zheng, Ziwei Zhao, Tong Xu, Zhao Jielun, Wenjun Xue, Yong Chen, Enhong Chen

View resourcePDF

Abstract

Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving. However, malicious agents in MAS may inject misinformation to mislead other agents and disrupt system performance, giving rise to a new research direction that focuses on attack mechanisms and defense strategies in MAS. Prior studies largely assume malicious agents act independently and investigate the corresponding d

Categories

Agent Architecture

Cite

@misc{luo2026defending,
  title = {{Defending LLM-based Multi-Agent Systems Against Cooperative Attacks with Sentence-Level Rectification}},
  author = {Yaoyang Luo and Zhi Zheng and Ziwei Zhao and Tong Xu and Zhao Jielun and Wenjun Xue and Yong Chen and Enhong Chen},
  year = {2026},
  month = may,
  eprint = {2605.28104},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.28104}
}