Learning Dynamic Belief Graphs for Theory-of-mind Reasoning

• URL: http://arxiv.org/abs/2603.20170v1
• Date: Fri, 20 Mar 2026 17:46:55 GMT
• Title: Learning Dynamic Belief Graphs for Theory-of-mind Reasoning
• Abstract summary: 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.
• Score: 5.807546348023422
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 -- especially in high-stakes settings such as disaster response, emergency medicine, and human-in-the-loop autonomy. Prior approaches either prompt LLMs directly or use latent-state models that treat beliefs as static and independent, often producing incoherent mental models over time and weak reasoning in dynamic contexts. We introduce a structured cognitive trajectory model for LLM-based ToM that represents mental state as a dynamic belief graph, jointly inferring latent beliefs, learning their time-varying dependencies, and linking belief evolution to information seeking and decisions. Our model contributes (i) a novel projection from textualized probabilistic statements to consistent probabilistic graphical model updates, (ii) an energy-based factor graph representation of belief interdependencies, and (iii) an ELBO-based objective that captures belief accumulation and delayed decisions. Across multiple real-world disaster evacuation datasets, our model significantly improves action prediction and recovers interpretable belief trajectories consistent with human reasoning, providing a principled module for augmenting LLMs with ToM in high-uncertainty environment. https://anonymous.4open.science/r/ICML_submission-6373/

Related papers

• Cognitive Profiling of LRMs' Reasoning Traces Using Bloom's Taxonomy [51.08110837378928]
  We introduce a framework for automatic annotation of reasoning steps through the lens of Bloom's taxonomy.<n>We perform a large-scale analysis across models and datasets, revealing both similarities and differences in thinking patterns across models and tasks.<n>Our findings establish a fine-grained framework for analyzing thinking patterns in LRMs and provide actionable insights for enhancing reasoning quality.
  arXiv  Detail & Related papers  (2026-08-24T12:55:51Z)
• MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation [51.824145170051516]
  MobEvolve is a self-evolving framework for human mobility generation.<n>It employs an agent to iteratively evolve its internal logic.<n>It significantly outperforms state-of-the-art deep generative and LLM-based methods.
  arXiv  Detail & Related papers  (2026-06-01T03:46:25Z)
• ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles [12.64432580192871]
  Large language model (LLM)-based multi-agent simulation offers a powerful testbed for studying social opinion dynamics.<n>We introduce ScioMind, a cognitively grounded simulation framework that bridges structured opinion dynamics with agent reasoning.<n>We evaluate ScioMind on multiple case studies in a real-world policy debate scenario.
  arXiv  Detail & Related papers  (2026-05-13T16:07:00Z)
• Dynamic Theory of Mind as a Temporal Memory Problem: Evidence from Large Language Models [0.8666275811953881]
  Theory of Mind (ToM) is central to social cognition and human-AI interaction.<n>Large Language Models (LLMs) have been used to help understand and represent ToM.<n>We introduce DToM-Track to investigate temporal belief reasoning in controlled multiturn conversations.
  arXiv  Detail & Related papers  (2026-03-15T22:54:03Z)
• Beyond Words: Evaluating and Bridging Epistemic Divergence in User-Agent Interaction via Theory of Mind [8.740788873949471]
  Large Language Models (LLMs) have developed rapidly and are widely applied to both general-purpose and professional tasks.<n>They still struggle to comprehend and respond to the true user needs when intentions and instructions are imprecisely conveyed.
  arXiv  Detail & Related papers  (2026-02-14T16:01:59Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns [51.02752099869218]
  Large Language Models (LLMs) display strikingly different generalization behaviors.<n>We introduce a novel benchmark that decomposes reasoning into atomic core skills.<n>We show that RL-tuned models maintain more stable behavioral profiles and resist collapse in reasoning skills, whereas SFT models exhibit sharper drift and overfit to surface patterns.
  arXiv  Detail & Related papers  (2025-12-30T08:16:20Z)
• Forgetting as a Feature: Cognitive Alignment of Large Language Models [39.146761527401424]
  We show that Large Language Models (LLMs) exhibit systematic forgetting of past information.<n> Drawing inspiration from human memory dynamics, we model LLM inference as a probabilistic memory process governed by exponential decay.<n>Building on these observations, we propose probabilistic memory prompting, a lightweight strategy that shapes evidence integration to mimic human-like memory decay.
  arXiv  Detail & Related papers  (2025-12-28T10:43:00Z)
• Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning [31.08532996770416]
  Large language models (LLMs) exhibit cognitive confusion, logical inconsistencies, and conflation between objective world states and subjective belief states.<n>We propose an adaptive world model-enhanced reasoning mechanism that constructs a dynamic textual world model to track entity states and temporal sequences.
  arXiv  Detail & Related papers  (2025-10-09T09:07:31Z)
• Superficial Self-Improved Reasoners Benefit from Model Merging [49.09091498084467]
  Self-improvement as a solution to synthesizing high-quality data corpus.<n>In particular, our analysis reveals that even when LMs show improved in-domain (ID) reasoning accuracy, they actually compromise their generalized reasoning capabilities.<n>We propose Iterative Model Merging (IMM), a method that strategically combines weights from original and self-improved models to preserve generalization.
  arXiv  Detail & Related papers  (2025-03-03T22:41:25Z)
• Interpretable Imitation Learning with Dynamic Causal Relations [65.18456572421702]
  We propose to expose captured knowledge in the form of a directed acyclic causal graph. We also design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-09-30T20:59:42Z)

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.