LM agents' changeable modules prevent persistent identity and sanction sensitivity, making reputation mechanisms structurally inapplicable and requiring protocol-based behavioral harnesses instead.
Beyond dns: Unlocking the internet of ai agents via the nanda index and verified agentfacts,
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Proposes layered architecture and three mechanisms (semantic propagation, identity/reputation, semantic-gradient design) for distributed agent networks with prototype simulations.
OAN proposes a trust layer using did:oan resource identities, federated governance, and trusted discovery to enable safe agent interconnection without replacing existing protocols.
DNS is suitable for AI agent discovery because the necessary metadata, including trust elements, fits within a single UDP transaction with millisecond latency, as shown by analysis of 119,757 real-world service endpoints.
AONA is a proposed four-layer overlay network architecture with dedicated node types and workflows for global, decentralized collaboration among AI agents.
citing papers explorer
-
OpenAgenet / OAN White Paper: Open Infrastructure for Trusted Agent Interconnection
OAN proposes a trust layer using did:oan resource identities, federated governance, and trusted discovery to enable safe agent interconnection without replacing existing protocols.