A Theory of Multilevel Interactive Equilibrium in NeuroAI

TL;DR

This paper introduces a game-theoretic framework called Multilevel Interactive Equilibrium (MIE) for analyzing adaptive multi-agent systems, extending classical game theory to include neural learning and internal computations.

Contribution

It develops a mathematical foundation for equilibrium in NeuroAI systems considering partial observability, bounded computation, and internal neural dynamics, applicable to diverse agent interactions.

Findings

MIE generalizes Nash equilibrium to neural and cognitive systems.

Framework applies to biological, artificial, and hybrid agent interactions.

Discusses methods for estimating MIE and future research directions.

Abstract

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.