The Theory of Mind Utility: Formal Specification of a Mentalizing Mechanism

2026-06-10

AI Summary

This work proposes a formal method for inferring others’ belief states and their underlying cognitive components—such as information sources, reception order, and credibility. To this end, we introduce Local Epistemic World Models (LEWMs), directed typed graphs that represent agents, state nodes, and epistemic relationships. Candidate LEWMs are iteratively evaluated against observed behavior until confidence thresholds are met. Our approach provides the first formal computational account of mental state reasoning, featuring a structured LEWM framework and a residual function that yields falsifiable predictions about theory-of-mind failures. Unlike Bayesian Theory of Mind models that presuppose fixed belief structures, our method requires no prior assumptions, is domain-agnostic, and systematically explains and predicts reasoning biases. It thus offers a general-purpose upstream mechanism for downstream social cognition tasks such as goal inference.

Abstract

Inferring others' beliefs requires more than reading surface signals; it requires tracking who told them what, in what order, and how credibly. The Theory of Mind Utility (ToM-U) formalizes this epistemic state inference problem at the computational level of analysis, specifying what mentalizing computes and why without commitment to algorithmic or neural implementation. ToM-U achieves this by constructing Local Epistemic World Models (LEWMs) -- directed typed graphs that represent agents, state nodes, and the epistemic relationships among them -- and evaluating discrete candidate LEWMs against observed behavior until one achieves sufficient confidence. Five formal definitions specify the LEWM structure, agent node properties including ordered information access history, a bounded proliferation mechanism for recursive mentalizing, three inference procedures, and a residue function that captures the structured trace left by failed mentalizing attempts. ToM-U differs from Bayesian Theory of Mind and adjacent formal accounts, which presuppose rather than derive belief states, and from simulation theory and theory-theory, which lack a formal apparatus for epistemic state inference. The architecture generates directional, falsifiable predictions about mentalizing failure that follow from structural properties of the model rather than auxiliary assumptions, and positions ToM-U as a domain-agnostic mechanism upstream of goal inference and other downstream social cognitive processes.

Problem

• Theory of Mind
• Epistemic State Inference
• Mentalizing
• Belief Attribution
• Computational Modeling

Innovation

• Theory of Mind Utility
• Local Epistemic World Models
• epistemic state inference
• recursive mentalizing
• computational-level modeling