Skip to content
Search
paperJune 2026Unreviewed

SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems

Ruxue Shi, Yili Wang, Mengnan Du, Qinggang Zhang, Rui Miao, Yixin Liu, Xin Wang

View resource

Abstract

LLM-based multi-agent systems (MAS) solve complex tasks through inter-agent collaboration, but their communication-driven nature also allows security risks to spread across agents and trigger system-wide failures. Existing MAS defenses mainly follow a reactive paradigm after execution by detecting and isolating harmful agents, which may cause irreversible damage and degrade collaborative utility. To address this, we propose a proactive defense framework for MAS security, namely a Simulation-awar

Categories

Agent ArchitectureThreat Modeling

Cite

@misc{shi2026saiguard,
  title = {{SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems}},
  author = {Ruxue Shi and Yili Wang and Mengnan Du and Qinggang Zhang and Rui Miao and Yixin Liu and Xin Wang},
  year = {2026},
  month = jun,
  eprint = {2606.12474},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/a96d1118b026d24af509a0e6ecd47b710bf0f138}
}