Fetch.ai: An Architecture for Modern Multi-Agent Systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wooldridge, Michael J., Bagoly, Attila, Ward, Jonathan J., La Malfa, Emanuele, Licks, Gabriel Paludo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914106277101568
author Wooldridge, Michael J.
Bagoly, Attila
Ward, Jonathan J.
La Malfa, Emanuele
Licks, Gabriel Paludo
author_facet Wooldridge, Michael J.
Bagoly, Attila
Ward, Jonathan J.
La Malfa, Emanuele
Licks, Gabriel Paludo
contents Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such as centralization and inadequate trust and communication protocols. This paper introduces the Fetch.ai architecture, an industrial-strength platform designed to bridge this gap by facilitating the integration of classical MAS principles with modern AI capabilities. We present a novel, multi-layered solution built on a decentralized foundation of on-chain blockchain services for verifiable identity, discovery, and transactions. This is complemented by a comprehensive development framework for creating secure, interoperable agents, a cloud-based platform for deployment, and an intelligent orchestration layer where an agent-native LLM translates high-level human goals into complex, multi-agent workflows. We demonstrate the deployed nature of this system through a decentralized logistics use case where autonomous agents dynamically discover, negotiate, and transact with one another securely. Ultimately, the Fetch.ai stack provides a principled architecture for moving beyond current agent implementations towards open, collaborative, and economically sustainable multi-agent ecosystems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18699
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fetch.ai: An Architecture for Modern Multi-Agent Systems
Wooldridge, Michael J.
Bagoly, Attila
Ward, Jonathan J.
La Malfa, Emanuele
Licks, Gabriel Paludo
Multiagent Systems
Artificial Intelligence
Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such as centralization and inadequate trust and communication protocols. This paper introduces the Fetch.ai architecture, an industrial-strength platform designed to bridge this gap by facilitating the integration of classical MAS principles with modern AI capabilities. We present a novel, multi-layered solution built on a decentralized foundation of on-chain blockchain services for verifiable identity, discovery, and transactions. This is complemented by a comprehensive development framework for creating secure, interoperable agents, a cloud-based platform for deployment, and an intelligent orchestration layer where an agent-native LLM translates high-level human goals into complex, multi-agent workflows. We demonstrate the deployed nature of this system through a decentralized logistics use case where autonomous agents dynamically discover, negotiate, and transact with one another securely. Ultimately, the Fetch.ai stack provides a principled architecture for moving beyond current agent implementations towards open, collaborative, and economically sustainable multi-agent ecosystems.
title Fetch.ai: An Architecture for Modern Multi-Agent Systems
topic Multiagent Systems
Artificial Intelligence
url https://arxiv.org/abs/2510.18699