# Position: Collaborative Agentic AI Needs Interoperability Across Ecosystems

arXiv: https://arxiv.org/abs/2505.21550 · HTML: https://mlsanity.com/paper/2505.21550/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 88 references that are in the map.
- First posted on arXiv 25 May 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities](https://mlsanity.com/paper/2310.10436/) (2023)
- [The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies](https://mlsanity.com/paper/2407.19354/) (2024)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Generative AI](https://mlsanity.com/paper/2309.07930/) (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)
- [Robin: A multi-agent system for automating scientific discovery](https://mlsanity.com/paper/2505.13400/) (2025)
- [A Scalable Communication Protocol for Networks of Large Language Models](https://mlsanity.com/paper/2410.11905/) (2024)
- [Generative to Agentic AI: Survey, Conceptualization, and Challenges](https://mlsanity.com/paper/2504.18875/) (2025)
- [LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities](https://mlsanity.com/paper/2405.06700/) (2024)
- [The AI Agent Index](https://mlsanity.com/paper/2502.01635/) (2025)
- [Near to Mid-term Risks and Opportunities of Open-Source Generative AI](https://mlsanity.com/paper/2404.17047/) (2024)
- [Decentralized Low-Latency Collaborative Inference via Ensembles on the Edge](https://mlsanity.com/paper/2206.03165/) (2022)
- [Build Agent Advocates, Not Platform Agents](https://mlsanity.com/paper/2505.04345/) (2025)
- [The Internet of Things: New Interoperability, Management and Security Challenges](https://mlsanity.com/paper/1604.04824/) (2016)
- [Is Fragmentation a Threat to the Success of the Internet of Things?](https://mlsanity.com/paper/1808.07355/) (2018)

## Built on by (most cited first, 8 of 8)

- [AI Agents with Decentralized Identifiers and Verifiable Credentials](https://mlsanity.com/paper/2511.02841/) (2025)
- [Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP](https://mlsanity.com/paper/2602.11327/) (2026)
- [From Multi-Agent Systems and the Semantic Web to Agentic AI: A Unified Narrative of the Web of Agents](https://mlsanity.com/paper/2507.10644/) (2025)
- [BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Web](https://mlsanity.com/paper/2508.13787/) (2025)
- [Toward a Safe Internet of Agents](https://mlsanity.com/paper/2512.00520/) (2025)
- [Distributed Legal Infrastructure for a Trustworthy Agentic Web](https://mlsanity.com/paper/2603.06884/) (2026)
- [AONA: A Comprehensive Architecture and Workflow Design for Global Agentic Collaboration](https://mlsanity.com/paper/2606.20573/) (2026)
- [The Wealth of Agents: Scaling Agentic AI Across Developers](https://mlsanity.com/paper/2610.20518/) (2026)

## Abstract (arXiv)

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 building blocks: 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.