A Theory of Multilevel Interactive Equilibrium in NeuroAI
For researchers in multi-agent systems and NeuroAI, this work offers a conceptual extension of game theory to account for internal neural dynamics, but remains theoretical without empirical validation.
The paper proposes a game-theoretic framework called Multilevel Interactive Equilibrium (MIE) that generalizes Nash equilibrium to intelligent systems with internal computation, applicable to biological, artificial, and hybrid agents. It discusses applications in human-AI interaction and computational psychiatry, but provides no concrete experimental results or quantitative comparisons.
We propose a game-theoretic framework for adaptive multi-agent intelligent systems. Unlike classical game theory, which often treats strategies as primitive objects chosen by perfectly rational agents, the proposed framework provides a mathematical foundation for studying equilibrium in NeuroAI and can be viewed as an extension of game theory under relaxed assumptions, including partial observability, bounded computation, and uncertainty. At its core, Multilevel Interactive Equilibrium (MIE) generalizes the classical Nash equilibrium to intelligent systems with internal computation. Rather than being defined solely at the level of observable behavior, equilibrium emerges when neural learning dynamics, cognitive representations, and behavioral strategies mutually stabilize between interacting agents. This framework applies uniformly to interactions between two biological brains, two artificial agents, or hybrid human-AI systems. We discuss applications of multilevel game theory to human-autonomous vehicle driving, human-machine interaction, human-large language model (LLM) interaction, and computational psychiatry. We also outline experimental strategies and computational methods for estimating MIE and discuss challenges and prospects for future research.