Federated Multi-Agent Systems (FedMAS) offer a promising paradigm for collaborative reasoning among LLM-based agents while keeping raw client data decentralized. However, reliable multi-round collaboration remains challenging. Agent selection must take into consideration evolving task requirements and the agent's historical reliability, while privacy rules must adapt to changing collaboration contexts and meet the client's personalized needs. To address these challenges, we propose PFedMA, a federated multi-agent framework for feedback driven multi-round collaboration under heterogeneous privacy requirements. Across rounds, PFedMA maintains historical capability and reliability states to guide agent selection, evaluates task responses before aggregation, and refines subsequent queries according to accumulated collaboration feedback. PFedMA enables bidirectional local to global and global to local private rule evolution across heterogeneous clients. Clients generalize locally updated privacy rules and selectively incorporate globally maintained rules, thereby facilitating cross-client privacy rule evolution while preserving personalized constraints. Extensive experiments across reasoning, privacy sensitive, and adversarial settings show that PFedMA improves task performance, reduces measured privacy leakage, and improves system robustness.
AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration
Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)计算与智能研究院);The University of Sydney(悉尼大学);School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)计算机科学与技术学院)
Multi-Agent Collaboration via Cross-Team Orchestration
State Key Lab of CAD & CG(CAD与CG国家重点实验室);Zhejiang Polytechnic Institute(浙江工业大学);Polytechnic Institute, Zhejiang University(浙江大学 polytechnic 院);Shanghai Jiao Tong University(上海交通大学);King’s College London(伦敦国王学院);Tsinghua University(清华大学);Beijing University of Posts and Telecommunications(北京邮电大学);Tencent Robotics X(腾讯机器人科技)
Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines
Department of Computer Science, University of Texas at El Paso(德克萨斯理工大学计算机科学系);School of Computing, Southern Illinois University Carbondale(南方伊利诺伊大学卡本代尔分校计算机学院);Hanyang University(翰阳大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)