arXiv:2609.00595v1 Announce Type: cross
Abstract: Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating...
By Rui Yang, Junjie Xu, Zhengyu Liu, Neil Fendley, Yang Hong, Ziyang Li, Yinzhi Cao
arXiv:2606. 30602v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows.
By Kunyang Li, Kyle Domico, Jonathan Gregory, Patrick McDaniel
arXiv:2607. 06807v1 Announce Type: cross Abstract: While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction levels.
By Haowen Xu, Xue Tan, Lei Ma, Zhihao Zhang, Chao Wang, Qingze Wang, Ping Chen, Jun Dai, Xiaoyan Sun
MAS-Shield is a defense framework for Large Language Model–based Multi-Agent Systems that uses a coarse‑to‑fine filtering pipeline. It first selects critical agents, then applies lightweight auditing to most cases, and finally escalates only suspicious signals to a heavyweight committee. Experiments show a 92.5% recovery rate against adversarial attacks and a latency reduction of over 70% compared to existing methods.
By Kaixiang Wang, Zhaojiacheng Zhou, Bunyod Suvonov, Jiong Lou, Zihan Wang, Yuxiang Zheng, Yidan Lin, Wutong Zhang, Xianghan Kong, Chentao Wu, Jie Li
arXiv:2605.21694v2 Announce Type: replace-cross
Abstract: Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender...
By Sidnei Barbieri, \'Agney Lopes Roth Ferraz, Louren\c{c}o Alves Pereira J\'unior
arXiv:2606. 10749v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environments.
By Yuchen Ling, Shengcheng Yu, Zhenyu Chen, Chunrong Fang