A Theory of Multilevel Interactive Equilibrium in NeuroAI

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Zhe Sage, Zhu, Quanyan
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916000814858240
author Chen, Zhe Sage
Zhu, Quanyan
author_facet Chen, Zhe Sage
Zhu, Quanyan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10505
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Theory of Multilevel Interactive Equilibrium in NeuroAI
Chen, Zhe Sage
Zhu, Quanyan
Neural and Evolutionary Computing
Computer Science and Game Theory
Theoretical Economics
91A10, 91A15, 68T05, 68T07, 93E20, 92C20
I.2.11; I.2.6; J.4
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.
title A Theory of Multilevel Interactive Equilibrium in NeuroAI
topic Neural and Evolutionary Computing
Computer Science and Game Theory
Theoretical Economics
91A10, 91A15, 68T05, 68T07, 93E20, 92C20
I.2.11; I.2.6; J.4
url https://arxiv.org/abs/2605.10505