The Theory of Mind Utility: Formal Specification of a Mentalizing Mechanism
Quick Answer
This paper shows that The Theory of Mind Utility (ToM-U) formalizes mentalizing mechanisms through Local Epistemic World Models (LEWMs), enabling inference of beliefs based on structured relationships rather than assumptions.
Quick Take
The Theory of Mind Utility (ToM-U) formalizes mentalizing mechanisms through Local Epistemic World Models (LEWMs), enabling inference of beliefs based on structured relationships rather than assumptions. This framework generates falsifiable predictions about mentalizing failures and positions ToM-U as a foundational model for social cognition.
Key Points
- ToM-U constructs LEWMs to represent agents and their epistemic relationships.
- Five formal definitions outline the structure and properties of LEWMs.
- The model allows for recursive mentalizing with a bounded proliferation mechanism.
- ToM-U differs from Bayesian models by deriving belief states rather than presupposing them.
- Predictions about mentalizing failures stem from the model's structural properties.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 12721v1 Announce Type: new 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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Arbor: Tree Search as a Cognition Layer for Autonomous Agents
Arbor introduces a multi-agent framework utilizing structured tree search for optimizing LLM inference, achieving up to 193% throughput-latency improvement compared to vendor-optimized systems. It employs an Orchestrator and Critic agent for stability and coordination, demonstrating hardware-agnostic performance with minimal variance.