Human-Artificial Interaction in the Age of Agentic AI: A System-Theoretical Approach

2025-02-19

AI Summary

Addressing the theoretical modeling challenge of human–machine collaboration in the AI era, this paper proposes the “Centaur System” paradigm—a unified decision-making entity integrating humans and machines—thereby distinguishing and unifying traditional multi-agent systems (MAS) and human-in-the-loop (HITL) systems. Method: We introduce a three-layer communication space model to formally characterize coordination mechanism differences between MAS and HITL systems; develop the first colored Petri net formalism for Centaur Systems; and integrate high-level reconfigurable network representations to capture MAS dynamism, grounded in systems theory, cybernetics, and distributed cognition theory. Contribution/Results: The framework provides a verifiable modeling foundation for autonomous robotics, AI cognitive architectures, and HITL decision-making. It enables the design of next-generation hybrid intelligent systems that simultaneously support structured collaboration and emergent behavior.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

This paper presents a novel perspective on human-computer interaction (HCI), framing it as a dynamic interplay between human and computational agents within a networked system. Going beyond traditional interface-based approaches, we emphasize the importance of coordination and communication among heterogeneous agents with different capabilities, roles, and goals. A key distinction is made between multi-agent systems (MAS) and Centaurian systems, which represent two different paradigms of human-AI collaboration. MAS maintain agent autonomy, with structured protocols enabling cooperation, while Centaurian systems deeply integrate human and AI capabilities, creating unified decision-making entities. To formalize these interactions, we introduce a framework for communication spaces, structured into surface, observation, and computation layers, ensuring seamless integration between MAS and Centaurian architectures, where colored Petri nets effectively represent structured Centaurian systems and high-level reconfigurable networks address the dynamic nature of MAS. Our research has practical applications in autonomous robotics, human-in-the-loop decision making, and AI-driven cognitive architectures, and provides a foundation for next-generation hybrid intelligence systems that balance structured coordination with emergent behavior.

Problem

• Explores human-AI interaction dynamics
• Compares multi-agent vs Centaurian systems
• Develops framework for hybrid intelligence systems

Innovation

• Dynamic interplay in networked systems
• Coordination among heterogeneous agents
• Communication spaces with layered structure