A Causal Model of Theory of Mind in Conflict for Artificial Intelligence

• URL: http://arxiv.org/abs/2606.16944v1
• Date: Mon, 15 Jun 2026 16:44:42 GMT
• Title: A Causal Model of Theory of Mind in Conflict for Artificial Intelligence
• Abstract summary: Existing AI-ToM models address emphhow to mentalize, but leave the question of when largely unaddressed.<n>This paper presents a structural causal model formalized as a directed acyclic graph (DAG)<n>It treats ToM as a mechanism activated by situational and agent-level conditions rather than as an always-on capacity.
• Score: 1.2183405753834562
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Theory of mind (ToM), the capacity to ascribe mental states to others and use those ascriptions for prediction and inference, is widely assumed to be essential for effective human-machine integration. Existing AI-ToM models address \emph{how} to mentalize, but leave the question of when largely unaddressed. The central question is: under what situational and agent-level conditions is ToM engagement causally warranted in conflict? This paper presents a structural causal model formalized as a directed acyclic graph (DAG), treating ToM as a mechanism activated by situational and agent-level conditions rather than as an always-on capacity. The model specifies four exogenous variables capturing situational and agent-level conditions, five endogenous mediators, and a mechanistic ToM node producing engagement states through three distinct causal pathways: a tractability pathway, a reasoning-depth pathway, and an enabling-cause pathway. The primary outcome is epistemic accuracy, which decouples social reasoning from behavioral policy and generalizes across social phenomena beyond conflict. The framework gives AI systems a principled, resource-rational decision procedure for mentalizing, with implications for efficiency, trust, and the development of robust artificial social intelligence. Simulation validation, empirical human-machine teaming studies, and ethical considerations arising from conflict-optimized mentalizing are discussed.

Related papers

• A game theory for foundation models shows new paths to rational cooperation through similarity inference [56.53805518668248]
  We show that foundation model agents engaging in optimal planning consistently converge to stable cooperation.<n>By shifting from decoupled to embedded agency, these agents model themselves as part of the universe they inhabit.
  arXiv  Detail & Related papers  (2026-08-04T17:24:33Z)
• The Theory of Mind Utility: Formal Specification of a Mentalizing Mechanism [2.226663588797889]
  Theory of Mind Utility (ToM-U) formalizes the problem of inference from belief states.<n>ToM-U generates predictions about mentalizing failure that follow from structural properties of the model.<n>The architecture positions ToM-U as a domain-agnostic mechanism upstream of goal inference and other downstream social cognitive processes.
  arXiv  Detail & Related papers  (2026-06-10T22:11:40Z)
• An Algebraic Exposition of the Theory of Dyadic Morality [11.173424329043657]
  This paper provides an exposition of the theory of dyadic morality (TDM)<n>We formalize TDM using structural causal modeling (SCM) notation.<n>We show how moral cognition compresses multi-node scenarios through node collapse and sequential processing.<n>This formalization enables neurosymbolic AI systems to compute morality in a way that is both mathematically rigorous and faithful to human moral cognition.
  arXiv  Detail & Related papers  (2026-05-15T16:33:51Z)
• Learning Dynamic Belief Graphs for Theory-of-mind Reasoning [5.807546348023422]
  Theory of Mind (ToM) reasoning with Large Language Models (LLMs) requires inferring how people's implicit, evolving beliefs shape what they seek and how they act under uncertainty.<n>We introduce a structured cognitive trajectory model for LLM-based ToM that represents mental state as a dynamic belief graph.<n>Our model significantly improves action prediction and recovers interpretable belief trajectories consistent with human reasoning.
  arXiv  Detail & Related papers  (2026-03-20T17:46:55Z)
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms [49.66022971508878]
  We argue that reasoning should be elevated from a modular component to the system's cognitive core.<n>We derive and systematize seven core reasoning challenges, such as the responsiveness-reasoning trade-off and social-game reasoning.<n>We identify a fundamental and unresolved tension between the high-latency, deliberative nature of LLM-based reasoning and the millisecond-scale, safety-critical demands of vehicle control.
  arXiv  Detail & Related papers  (2026-03-11T07:40:53Z)
• To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks [56.11584171938381]
  Theory of Mind (ToM) assesses whether models can infer hidden mental states such as beliefs, desires, and intentions.<n>Recent progress in Large Reasoning Models (LRMs) has boosted step-by-step inference in mathematics and coding.<n>We present a systematic study of nine advanced Large Language Models (LLMs) comparing reasoning models with non-reasoning models.
  arXiv  Detail & Related papers  (2026-02-11T08:16:13Z)
• Perfect AI Mimicry and the Epistemology of Consciousness: A Solipsistic Dilemma [2.5672176409865677]
  Advances in artificial intelligence require a re-examination of the foundations upon which we attribute consciousness.<n>As AI systems increasingly mimic human behavior and interaction with high fidelity, the concept of a "perfect mimic"-an entity empirically indistinguishable from a human-shifts from hypothetical to technologically plausible.<n>This paper argues that such developments pose a fundamental challenge to the consistency of our mind-recognition practices.
  arXiv  Detail & Related papers  (2025-10-06T08:44:55Z)
• Causal Responsibility Attribution for Human-AI Collaboration [62.474732677086855]
  This paper presents a causal framework using Structural Causal Models (SCMs) to systematically attribute responsibility in human-AI systems. Two case studies illustrate the framework's adaptability in diverse human-AI collaboration scenarios.
  arXiv  Detail & Related papers  (2024-11-05T17:17:45Z)
• Failure Modes of LLMs for Causal Reasoning on Narratives [51.19592551510628]
  We investigate the interaction between world knowledge and logical reasoning.<n>We find that state-of-the-art large language models (LLMs) often rely on superficial generalizations.<n>We show that simple reformulations of the task can elicit more robust reasoning behavior.
  arXiv  Detail & Related papers  (2024-10-31T12:48:58Z)
• CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning [68.74447489372037]
  We present a high-fidelity simulation environment that is designed for developing algorithms for causal discovery and counterfactual reasoning. A core component of our work is to introduce textitagency, such that it is simple to define and create complex scenarios. We perform experiments with three state-of-the-art methods to create baselines and highlight the affordances of this environment.
  arXiv  Detail & Related papers  (2021-06-25T00:21:41Z)
• Machine Common Sense [77.34726150561087]
  Machine common sense remains a broad, potentially unbounded problem in artificial intelligence (AI) This article deals with the aspects of modeling commonsense reasoning focusing on such domain as interpersonal interactions.
  arXiv  Detail & Related papers  (2020-06-15T13:59:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.