Collaborative Agentic AI Needs Interoperability Across Ecosystems

TL;DR

This paper emphasizes the importance of interoperability in collaborative agentic AI, proposing a minimal architectural framework called Web of Agents to enable compatible, secure, and scalable ecosystems.

Contribution

It introduces the Web of Agents architecture, a minimal standard-based framework for achieving interoperability among agentic AI systems.

Findings

Proposes Web of Agents architecture with four core components.

Leverages existing standards and infrastructure for interoperability.

Provides a pragmatic approach to prevent ecosystem fragmentation.

Abstract

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.