Internet of Agentic AI: Incentive-Compatible Distributed Teaming and Workflow

TL;DR

This work tackles the scalability limits of centralized agentic AI by introducing the Internet of Agentic AI, a network-native framework where autonomous agents across cloud and edge nodes form task-specific coalitions. It formalizes a networked model with domain specialization, dynamic coalition formation, and an incentive-compatible workflow-coalition feasibility framework, including a decentralized minimum-effort coalition algorithm compatible with local information. The healthcare case study demonstrates how heterogeneous, edge-cloud capabilities can be composed into scalable, economically viable workflows, with explicit definitions for task outcomes $O_q=f_q(\mathbf{u}^q)$ and rewards $R_q=r_q(O_q)$. The proposed C+MCP architecture positions the coordination layer above the Model Context Protocol, enabling principled planning and coalition formation prior to tool invocation, thereby enhancing interoperability, resilience, and economic viability in open AI ecosystems.

Abstract

Large language models (LLMs) have enabled a new class of agentic AI systems that reason, plan, and act by invoking external tools. However, most existing agentic architectures remain centralized and monolithic, limiting scalability, specialization, and interoperability. This paper proposes a framework for scalable agentic intelligence, termed the Internet of Agentic AI, in which autonomous, heterogeneous agents distributed across cloud and edge infrastructure dynamically form coalitions to execute task-driven workflows. We formalize a network-native model of agentic collaboration and introduce an incentive-compatible workflow-coalition feasibility framework that integrates capability coverage, network locality, and economic implementability. To enable scalable coordination, we formulate a minimum-effort coalition selection problem and propose a decentralized coalition formation algorithm. The proposed framework can operate as a coordination layer above the Model Context Protocol (MCP). A healthcare case study demonstrates how domain specialization, cloud-edge heterogeneity, and dynamic coalition formation enable scalable, resilient, and economically viable agentic workflows. This work lays the foundation for principled coordination and scalability in the emerging era of Internet of Agentic AI.

Figures (5)

• Figure 1: An illustration of the Internet of Agentic AI. Each node hosts one or more specialized AI agents designed for different tasks and participates in a shared communication network.
• Figure 2: An illustration of task-specific capability-covering coalition formation with distributed workflow execution.
• Figure 3: Agentic healthcare workflow with directional information flow. The system forms a closed loop in which the downstream diagnostic, validation, and communication outputs are returned to the clinic for coordination and finalization.
• Figure 4: Example feasible workflow coalition. The initiator node is shown in red, and selected coalition members in blue. Highlighted edges indicate coalition-induced communication paths used to coordinate workflow execution.
• Figure 5: Scaling behavior of workflow-coalition formation. Increasing per-agent capability breadth reduces both the coordination radius and coalition size required for feasibility. The coalition search exhibits rapid convergence in terms of the best achievable cost.

Theorems & Definitions (7)

• Definition 1: Capability-Covering Coalition
• Definition 2: k-Degree Feasibility
• Definition 3: Feasibility Radius
• Definition 4: Terminal Sub-Tasks
• Definition 5: Workflow-Coalition Feasibility
• Definition 6: $k$-Degree Workflow-Coalition Feasibility
• Definition 7: Minimum-Effort Coalition Selection