{"slug": "the-theory-of-mind-utility-formal-specification-of-a-mentalizing-mechanism", "title": "The Theory of Mind Utility: Formal Specification of a Mentalizing Mechanism", "summary": "Researchers have introduced the Theory of Mind Utility (ToM-U), a formal computational model that specifies how agents infer others' beliefs by tracking information access, order, and credibility. The model constructs Local Epistemic World Models (LEWMs) — directed graphs representing agents and their epistemic relationships — and evaluates them against observed behavior to determine mental states. ToM-U provides a domain-agnostic mechanism for mentalizing that generates falsifiable predictions about inference failures, distinguishing it from existing theories by deriving belief states rather than presupposing them.", "body_md": "arXiv:2606.12721v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/the-theory-of-mind-utility-formal-specification-of-a-mentalizing-mechanism", "canonical_source": "https://arxiv.org/abs/2606.12721", "published_at": "2026-06-12 04:00:00+00:00", "updated_at": "2026-06-12 04:52:28.441190+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/the-theory-of-mind-utility-formal-specification-of-a-mentalizing-mechanism", "markdown": "https://wpnews.pro/news/the-theory-of-mind-utility-formal-specification-of-a-mentalizing-mechanism.md", "text": "https://wpnews.pro/news/the-theory-of-mind-utility-formal-specification-of-a-mentalizing-mechanism.txt", "jsonld": "https://wpnews.pro/news/the-theory-of-mind-utility-formal-specification-of-a-mentalizing-mechanism.jsonld"}}