Toward a Safe Internet of Agents

TL;DR

The paper tackles the safety challenges of the Internet of Agents (IoA) by proposing a principled, bottom-up architectural framework that scales from a single agent to an interoperable multi-agent system (IMAS). It treats each component as a dual-use interface, identifying vulnerabilities and mitigation principles across three levels (Single Agent, MAS, IMAS) and detailing guardrails, verification, and governance needed for secure interoperability. A core argument is that safety is an emergent property of architectural design, not an afterthought, and that robust, interoperable standards are essential for trustworthy agent ecosystems. The work also outlines open research frontiers—verifiable control, decentralized identity, systemic resilience, interoperable forensics, and data sovereignty—that must be addressed to realize a safe, scalable IoA.

Abstract

Background: Autonomous agents powered by Large Language Models (LLMs) are driving a paradigm shift toward an "Internet of Agents" (IoA). While offering immense potential, this vision also introduces novel and systemic risks to safety and security. Objectives: Unlike common threat-centric taxonomies, our survey provides a principled, architectural framework for engineering safe and reliable agentic systems. We aim to identify the architectural sources of vulnerabilities to establish a foundation for secure design. Methods: We perform a bottom-up deconstruction of agentic systems, treating each component as a dual-use interface. The analysis spans three levels of complexity: the foundational Single Agent, the collaborative Multi-Agent System (MAS), and the visionary Interoperable Multi-Agent System (IMAS). At each level, we identify core architectural components and their inherent security risks. Results & Conclusions: Our central finding is that agentic safety is an architectural principle, not an add-on. By identifying specific vulnerabilities and deriving mitigation principles at each level of the agentic stack, this survey serves as a foundational guide for building the capable, safe, and trustworthy AI needed to realize a secure Internet of Agents.