Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents
This addresses the challenge of selecting effective agents in a decentralized AI ecosystem, which is incremental as it builds on existing ranking concepts like PageRank.
The paper tackles the problem of ranking AI agents in a future 'Web of Agents' by proposing DOVIS, a protocol for collecting usage and performance data, and AgentRank-UC, an algorithm that combines usage and competence metrics. It demonstrates viability through simulations and theoretical guarantees on convergence, robustness, and Sybil resistance.
AI agents -- powered by reasoning-capable large language models (LLMs) and integrated with tools, data, and web search -- are poised to transform the internet into a \emph{Web of Agents}: a machine-native ecosystem where autonomous agents interact, collaborate, and execute tasks at scale. Realizing this vision requires \emph{Agent Ranking} -- selecting agents not only by declared capabilities but by proven, recent performance. Unlike Web~1.0's PageRank, a global, transparent network of agent interactions does not exist; usage signals are fragmented and private, making ranking infeasible without coordination. We propose \textbf{DOVIS}, a five-layer operational protocol (\emph{Discovery, Orchestration, Verification, Incentives, Semantics}) that enables the collection of minimal, privacy-preserving aggregates of usage and performance across the ecosystem. On this substrate, we implement \textbf{AgentRank-UC}, a dynamic, trust-aware algorithm that combines \emph{usage} (selection frequency) and \emph{competence} (outcome quality, cost, safety, latency) into a unified ranking. We present simulation results and theoretical guarantees on convergence, robustness, and Sybil resistance, demonstrating the viability of coordinated protocols and performance-aware ranking in enabling a scalable, trustworthy Agentic Web.