Hierarchical Decentralized Multi-Agent Coordination with Privacy-Preserving Knowledge Sharing: Extending AgentNet for Scalable Autonomous Systems
By: Goutham Nalagatla
Potential Business Impact:
Helps many AI agents work together better.
Decentralized multi-agent systems have shown promise in enabling autonomous collaboration among LLM-based agents. While AgentNet demonstrated the feasibility of fully decentralized coordination through dynamic DAG topologies, several limitations remain: scalability challenges with large agent populations, communication overhead, lack of privacy guarantees, and suboptimal resource allocation. We propose AgentNet++, a hierarchical decentralized framework that extends AgentNet with multilevel agent organization, privacy-preserving knowledge sharing via differential privacy and secure aggregation, adaptive resource management, and theoretical convergence guarantees. Our approach introduces cluster-based hierarchies where agents self-organize into specialized groups, enabling efficient task routing and knowledge distillation while maintaining full decentralization. We provide formal analysis of convergence properties and privacy bounds, and demonstrate through extensive experiments on complex multi-agent tasks that AgentNet++ achieves 23% higher task completion rates, 40% reduction in communication overhead, and maintains strong privacy guarantees compared to AgentNet and other baselines. Our framework scales effectively to 1000+ agents while preserving the emergent intelligence properties of the original AgentNet.
Similar Papers
AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
Multiagent Systems
Lets AI agents work together without a boss.
Hierarchical Adaptive Consensus Network: A Dynamic Framework for Scalable Consensus in Collaborative Multi-Agent AI Systems
Multiagent Systems
Helps groups of robots work together faster.
Decentralized Multi-Agent System with Trust-Aware Communication
Multiagent Systems
Builds safer, smarter robot teams that can't be stopped.