# Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents

arXiv: https://arxiv.org/abs/2509.04979 · HTML: https://mlsanity.com/paper/2509.04979/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 12 of 12)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)](https://mlsanity.com/paper/2505.02279/) (2025)
- [PageRank beyond the Web](https://mlsanity.com/paper/1407.5107/) (2014)
- [Agentic Web: Weaving the Next Web with AI Agents](https://mlsanity.com/paper/2507.21206/) (2025)
- [Agent Network Protocol Technical White Paper](https://mlsanity.com/paper/2508.00007/) (2025)

## Built on by (most cited first, 1 of 1)

- [TrustFlow: Topic-Aware Vector Reputation Propagation for Multi-Agent Ecosystems](https://mlsanity.com/paper/2603.19452/) (2026)

## Abstract (arXiv)

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 Web of Agents: a machine-native ecosystem where autonomous agents interact, collaborate, and execute tasks at scale. Realizing this vision requires 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 DOVIS, a five-layer operational protocol (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 AgentRank-UC, a dynamic, trust-aware algorithm that combines usage (selection frequency) and 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.