Summary
As AI systems increasingly work as groups of agents using tools and helping each other, the authors look at how to make these setups work well together. They explore how to create a common foundation so different AI agents can communicate, cooperate, and be controlled safely across various platforms and organizations. Their work breaks down the challenge into three parts: the communication protocols agents use, how systems can run and manage these agents, and how this fits into broader service computing ideas about trust and control. This helps move from isolated AI tools to a more connected and manageable AI ecosystem.
What this means in practice
- •For enterprise software developers: Build interoperable AI services by implementing standardized agent communication protocols and governance layers across organizational systems.
- •For cloud platform architects: Design cloud-based infrastructures that enable deployment, orchestration, and control of heterogeneous AI agents as manageable service components.
A position paper. It proposes an approach and reports no results.
Authors
Haoyi Xiong, Yi Liu, Jiang Bian, Peng Diao, Bin Zhu, Tingting Hu, Yi Wang, Sumi Helal
Abstract
Large language model applications are increasingly being organized as tool-using and multi-agent workflows rather than as isolated chat interfaces. This perspective paper examines the architectural problem that follows from that shift: agents may reason, invoke tools, and delegate work, but dependable deployment still requires interoperability across frameworks, runtimes, data boundaries, and organizational control domains. We study this problem through the lens of the \emph{Internet of Agentics} (IoA), an emerging service-computing view in which heterogeneous agents are treated as governable service participants rather than only as stand-alone model endpoints. The paper organizes the landscape as a three-layer progression: from today's fragmented agent ecosystem, to interoperable agents, and ultimately to trustworthy and governable autonomy. First, it examines the protocol stack centered on the Agentic AI Foundation, including MCP for agent--tool interaction; A2A for agent--agent coordination; AGENTS.md and Skills-style procedural manifests; and discovery, transport, and trust mechanisms such as AGNTCY and SLIM. Second, it reviews the systems abstractions that make agents deployable as service components, including logical agent architectures, orchestration patterns, gateways, registries, runtime control loops, and hardware-aware inference infrastructure. Third, it situates these developments within services computing, arguing that agentic systems reinterpret classical concerns from SOA and microservices---discovery, composition, governance, pricing, and trust---at the level of cognitive capabilities rather than deterministic functions.