English

Usable Agent Discovery for Decentralized AI Systems

Multiagent Systems 2026-04-28 v1 Artificial Intelligence Distributed, Parallel, and Cluster Computing

Abstract

Large-scale agentic systems run on distributed infrastructures where many software agents share physical hosts and are discovered via peer-to-peer mechanisms. Discovery must handle node-level churn from failures and host departures and agent-level churn from demand-driven activation, deactivation, and state changes. Their interaction reshapes classic trade-offs between structured and unstructured overlays. We study decentralized agent discovery under this two-level churn, assuming nodes host multiple agents, overlays are structured or gossip-based, and agents switch between warm and cold states. Using Kademlia as a structured and Cyclon+Vicinity as a gossip baseline, we compare stable, node-churn-only, agent-cooling-only, and combined regimes to see when routing efficiency, resilience, and service readiness align or favor different designs. Structured overlays are more robust and efficient in stable and node-churn regimes, while gossip-based overlays remain competitive and can be faster when readiness dominates.

Keywords

Cite

@article{arxiv.2604.23080,
  title  = {Usable Agent Discovery for Decentralized AI Systems},
  author = {Patrizio Dazzi and Emanuele Carlini and Matteo Mordacchini and Saul Urso},
  journal= {arXiv preprint arXiv:2604.23080},
  year   = {2026}
}
R2 v1 2026-07-01T12:34:43.147Z