The emergence of agentic AI systems has given new life to two distinct approaches for human-AI collaboration: multi-agent architectures and Centaurian integration. This section examines these paradigms in detail, highlighting the distinct challenges each presents for system design and coordination. Indeed, although both paradigms involve interactions between intelligent entities, they represent fundamentally different approaches to human-artificial collaboration [46]. Multi-agent systems maintain distinct boundaries between components while enabling complex interactions, much like natural ecosystems. In contrast, "Centaurian" systems pursue deeper integration—analogous to symbiotic relationships in nature—fusing human and artificial competencies in tightly knit partnerships that often blur the lines between human decision-making and AI-driven processes. Living systems theory [38] helps us understand how both approaches must address a core challenge: maintaining system identity through regulated boundaries and feedback loops [53], whether in loosely coupled collectives or tightly integrated hybrid intelligences.

Communication spaces group interactions into three conceptual layers: surface, observation, and computation. Whether in a multi-agent (MAS) or a Centaurian system, each space encapsulates a coherent set of interaction rules and constraints. Surface Space mediates all contact with the outside environment—user interfaces, sensors, and external APIs. In MAS, surface space typically involves message-passing protocols or event listeners. In Centaurian systems, it can reflect a direct blending of human sensory input and AI-driven data capture. Observation Space bridges the surface interface with internal processing, handling message transformations, routing, and light coordination. In MAS, protocols here ensure agents remain autonomous yet cooperative. In Centaurian systems, observation may feature continuous feedback loops that unify human perception with AI analysis. Computation Space serves as the system's "core," performing decision-making, allocating resources, and generating final outputs. MAS solutions often involve multiple autonomous modules, each coordinating a portion of the computation. By contrast, Centaurian architectures might fuse human insights with AI algorithms in a shared decision-making environment.

This use case demonstrates how our theoretical framework accommodates both multi-agent and Centaurian paradigms within a complex system. While predominantly exhibiting multi-agent characteristics through its distributed architecture, the system also incorporates Centaurian elements in specific human-AI interaction points. Figure 8 illustrates the data flow in an experiment with a semi-centralized coordinated swarm of robots, using both "rigid" optimization algorithms and "flexible" intervention through a large language model (LLM). This setup encapsulates a true multi-agent HCI interaction, integrating human operators, conversational AI, the satellite control unit, and swarm robots.

While our first use case emphasized the multi-agent paradigm, this second use case demonstrates a stronger inclination toward the Centaurian approach, while still maintaining some multi-agent characteristics. Figure 10 shows the framework of RABBIT TECH'S Large Action Model (LAM), which integrates advanced computational agents to effectively model and predict human actions on computer applications. The system exemplifies the Centaurian paradigm's emphasis on tight integration between human and artificial components, while incorporating multi-agent elements in its distributed architecture.