Collaborative Agentic AI Needs Interoperability Across Ecosystems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sharma, Rishi, de Vos, Martijn, Chari, Pradyumna, Raskar, Ramesh, Kermarrec, Anne-Marie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915308393988096
author Sharma, Rishi
de Vos, Martijn
Chari, Pradyumna
Raskar, Ramesh
Kermarrec, Anne-Marie
author_facet Sharma, Rishi
de Vos, Martijn
Chari, Pradyumna
Raskar, Ramesh
Kermarrec, Anne-Marie
contents Collaborative agentic AI is projected to transform entire industries by enabling AI-powered agents to autonomously perceive, plan, and act within digital environments. Yet, current solutions in this field are all built in isolation, and we are rapidly heading toward a landscape of fragmented, incompatible ecosystems. In this position paper, we argue that interoperability, achieved by the adoption of minimal standards, is essential to ensure open, secure, web-scale, and widely-adopted agentic ecosystems. To this end, we devise a minimal architectural foundation for collaborative agentic AI, named Web of Agents, which is composed of four components: agent-to-agent messaging, interaction interoperability, state management, and agent discovery. Web of Agents adopts existing standards and reuses existing infrastructure where possible. With Web of Agents, we take the first but critical step toward interoperable agentic systems and offer a pragmatic path forward before ecosystem fragmentation becomes the norm.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21550
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Collaborative Agentic AI Needs Interoperability Across Ecosystems
Sharma, Rishi
de Vos, Martijn
Chari, Pradyumna
Raskar, Ramesh
Kermarrec, Anne-Marie
Networking and Internet Architecture
Artificial Intelligence
Multiagent Systems
Collaborative agentic AI is projected to transform entire industries by enabling AI-powered agents to autonomously perceive, plan, and act within digital environments. Yet, current solutions in this field are all built in isolation, and we are rapidly heading toward a landscape of fragmented, incompatible ecosystems. In this position paper, we argue that interoperability, achieved by the adoption of minimal standards, is essential to ensure open, secure, web-scale, and widely-adopted agentic ecosystems. To this end, we devise a minimal architectural foundation for collaborative agentic AI, named Web of Agents, which is composed of four components: agent-to-agent messaging, interaction interoperability, state management, and agent discovery. Web of Agents adopts existing standards and reuses existing infrastructure where possible. With Web of Agents, we take the first but critical step toward interoperable agentic systems and offer a pragmatic path forward before ecosystem fragmentation becomes the norm.
title Collaborative Agentic AI Needs Interoperability Across Ecosystems
topic Networking and Internet Architecture
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2505.21550