AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems

2025-04-01

AI Summary

Existing LLM-based multi-agent systems suffer from poor scalability, single-point failures, and privacy-sensitive challenges—such as knowledge silos—in cross-organizational collaboration, primarily due to centralized coordination. To address these issues, this paper proposes the first fully decentralized framework for LLM multi-agent systems. It models agent networks as directed acyclic graphs (DAGs) to support dynamic topology evolution; introduces an RAG-based adaptive expertise refinement mechanism enabling autonomous role differentiation and continual learning; and integrates distributed task routing with privacy-preserving, data-minimal interaction protocols. Experiments demonstrate that the framework significantly improves fault tolerance and horizontal scalability. Crucially, it enables robust, loosely coupled, and evolvable cross-organizational collaboration while ensuring organizational data remains within its domain—thereby upholding strict data sovereignty and privacy constraints.

Technology Category

• Multiagent Systems: Multiagent Learning
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The rapid advancement of Large Language Models (LLMs) has catalyzed the development of multi-agent systems, where multiple LLM-based agents collaborate to solve complex tasks. However, existing systems predominantly rely on centralized coordination, which introduces scalability bottlenecks, limits adaptability, and creates single points of failure. Additionally, concerns over privacy and proprietary knowledge sharing hinder cross-organizational collaboration, leading to siloed expertise. To address these challenges, we propose AgentNet, a decentralized, Retrieval-Augmented Generation (RAG)-based framework that enables LLM-based agents to autonomously evolve their capabilities and collaborate efficiently in a Directed Acyclic Graph (DAG)-structured network. Unlike traditional multi-agent systems that depend on static role assignments or centralized control, AgentNet allows agents to specialize dynamically, adjust their connectivity, and route tasks without relying on predefined workflows. AgentNet's core design is built upon several key innovations: (1) Fully Decentralized Paradigm: Removing the central orchestrator, allowing agents to coordinate and specialize autonomously, fostering fault tolerance and emergent collective intelligence. (2) Dynamically Evolving Graph Topology: Real-time adaptation of agent connections based on task demands, ensuring scalability and resilience.(3) Adaptive Learning for Expertise Refinement: A retrieval-based memory system that enables agents to continuously update and refine their specialized skills. By eliminating centralized control, AgentNet enhances fault tolerance, promotes scalable specialization, and enables privacy-preserving collaboration across organizations. Through decentralized coordination and minimal data exchange, agents can leverage diverse knowledge sources while safeguarding sensitive information.

Problem

• Decentralized coordination for scalable multi-agent systems
• Privacy-preserving collaboration across organizations
• Dynamic agent specialization without centralized control

Innovation

• Decentralized RAG-based framework for LLM agents
• Dynamic DAG-structured network for task routing
• Retrieval-based memory for continuous skill refinement