A Computable Game-Theoretic Framework for Multi-Agent Theory of Mind

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhu, Fengming, Pan, Yuxin, Zhu, Xiaomeng, Lin, Fangzhen
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917110607773696
author Zhu, Fengming
Pan, Yuxin
Zhu, Xiaomeng
Lin, Fangzhen
author_facet Zhu, Fengming
Pan, Yuxin
Zhu, Xiaomeng
Lin, Fangzhen
contents Originating in psychology, $\textit{Theory of Mind}$ (ToM) has attracted significant attention across multiple research communities, especially logic, economics, and robotics. Most psychological work does not aim at formalizing those central concepts, namely $\textit{goals}$, $\textit{intentions}$, and $\textit{beliefs}$, to automate a ToM-based computational process, which, by contrast, has been extensively studied by logicians. In this paper, we offer a different perspective by proposing a computational framework viewed through the lens of game theory. On the one hand, the framework prescribes how to make boudedly rational decisions while maintaining a theory of mind about others (and recursively, each of the others holding a theory of mind about the rest); on the other hand, it employs statistical techniques and approximate solutions to retain computability of the inherent computational problem.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22536
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Computable Game-Theoretic Framework for Multi-Agent Theory of Mind
Zhu, Fengming
Pan, Yuxin
Zhu, Xiaomeng
Lin, Fangzhen
Artificial Intelligence
Computer Science and Game Theory
Multiagent Systems
Originating in psychology, $\textit{Theory of Mind}$ (ToM) has attracted significant attention across multiple research communities, especially logic, economics, and robotics. Most psychological work does not aim at formalizing those central concepts, namely $\textit{goals}$, $\textit{intentions}$, and $\textit{beliefs}$, to automate a ToM-based computational process, which, by contrast, has been extensively studied by logicians. In this paper, we offer a different perspective by proposing a computational framework viewed through the lens of game theory. On the one hand, the framework prescribes how to make boudedly rational decisions while maintaining a theory of mind about others (and recursively, each of the others holding a theory of mind about the rest); on the other hand, it employs statistical techniques and approximate solutions to retain computability of the inherent computational problem.
title A Computable Game-Theoretic Framework for Multi-Agent Theory of Mind
topic Artificial Intelligence
Computer Science and Game Theory
Multiagent Systems
url https://arxiv.org/abs/2511.22536