[Paper Review] Human-Artificial Interaction in the Age of Agentic AI: A System-Theoretical Approach

Uwe M. Borghoff, Paolo Bottoni+1 more|ArXiv.org|Feb 19, 2025

Economic Development and Digital Transformation3 citations

TL;DR

The paper introduces a system-theoretical framework that unifies multi-agent systems (MAS) and Centaurian human–AI integration using communication spaces and colored Petri nets, demonstrated through two use cases involving satellites, swarm robotics, and Large Action Models (LAMs).

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.

Motivation & Objective

• Motivate a dynamic view of human–AI interaction as coordination among heterogeneous agents within networked systems.
• Differentiate MAS and Centaurian integration and explore how they can be unified through a common framework.
• Develop a formal, Petri net–based model (communication spaces) to represent surface, observation, and computation layers.
• Demonstrate the framework with real-world use cases: satellite/swarm robotics and Large Action Models in HCI.

Proposed method

• Adopts Petri nets and colored Petri nets as the formal base for modeling concurrent, heterogeneous agent interactions.
• Introduces communication spaces (surface, observation, computation) as a unifying architectural layer across MAS and Centaurian paradigms.
• Maps communication spaces onto colored Petri nets with typed tokens and guards to enforce agent-specific capabilities.
• Proposes a group-agent construct to manage message delivery and composition within collaborative topics.
• Provides illustrative pseudo-code and schematic Petri net snippets to demonstrate Centaurian coupling such as human approval tokens enabling AI planning.

Experimental results

Research questions

• RQ1 How can MAS and Centaurian human–AI collaboration be modeled within a single, coherent framework?
• RQ2 What formal apparatus (Petri nets, colored tokens, guards) best captures heterogeneous, hybrid human–AI interactions across surface, observation, and computation spaces?
• RQ3 How do the proposed communication spaces support both autonomous operation and deep integration in practical scenarios?
• RQ4 What insights do the use cases (satellite/swarm robots and LAMs) provide about transitioning between MAS and Centaurian modes?

Key findings

• A unified communication-spaces framework enables both loose coupling (MAS) and deep integration (Centaurian) in human–AI systems.
• Colored Petri nets with typed tokens effectively encode heterogeneous data, states, and interaction protocols across surface, observation, and computation layers.
• The group-agent construct supports scalable, topic-based collaboration and controlled information flow among active agents.
• Two use cases illustrate how agentic AI can operate in multi-agent mode with Centaurian interaction points, and how LAMs achieve neuro-symbolic, Centaurian integration with humans.
• The framework provides a formal basis for designing next-generation hybrid intelligence systems balancing autonomy and integration.