mlsanityData to 7 Oct 2026

A Notion of Complexity for Theory of Mind via Discrete World Models

arXiv 2406.11911 ↗First posted 16 Jun 2024cs.AI cs.CL cs.LGcited by 16

On the map: World models → World models for language agents

Abstract (arXiv)

Theory of Mind (ToM) can be used to assess the capabilities of Large Language Models (LLMs) in complex scenarios where social reasoning is required. While the research community has proposed many ToM benchmarks, their hardness varies greatly, and their complexity is not well defined. This work proposes a framework inspired by cognitive load theory to measure the complexity of ToM tasks. We quantify a problem's complexity as the number of states necessary to solve it correctly. Our complexity measure also accounts for spurious states of a ToM problem designed to make it apparently harder. We use our method to assess the complexity of five widely adopted ToM benchmarks. On top of this framework, we design a prompting technique that augments the information available to a model with a description of how the environment changes with the agents' interactions. We name this technique Discrete World Models (DWM) and show how it elicits superior performance on ToM tasks.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 21 of its 60 references that are in the map. First posted on arXiv 16 Jun 2024.

Builds on

21 of 60 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought22 Jun
  2. 2023Reasoning with Language Model is Planning with World Model24 May
  3. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr
  4. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs24 Oct

Other references · 17

  1. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  2. 2018World Modelscited by 1,444
  3. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  4. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 417
  5. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 288
  6. 2018Machine Theory of Mindcited by 222
  7. 2021Implicit Representations of Meaning in Neural Language Modelscited by 179
  8. 2023FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactionscited by 162
  9. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Modelscited by 161
  10. 2023Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarkscited by 139
  11. 2023How FaR Are Large Language Models From Agents with Theory-of-Mind?cited by 75
  12. 2024ToMBench: Benchmarking Theory of Mind in Large Language Modelscited by 70
5 more
  1. 2023Boosting Theory-of-Mind Performance in Large Language Models via Promptingcited by 64
  2. 2021Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of otherscited by 39
  3. 2024Code Pretraining Improves Entity Tracking Abilities of Language Modelscited by 31
  4. 2022Mind the gap: Challenges of deep learning approaches to Theory of Mindcited by 21
  5. 2023MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logiccited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 5.

16 papers.

Sort:

By area:

  1. 2025Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Modelscited by 28
  2. 2025AutoToM: Scaling Model-based Mental Inference via Automated Agent Modelingcited by 23
  3. 2025Code Simulation as a Proxy for High-order Tasks in Large Language Modelscited by 6
  4. 2025A Critical Assessment of Modern Generative Models' Ability to Replicate Artistic Stylescited by 6
  5. 2025EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity Statescited by 6
  6. 2025Modeling Others' Minds as Codecited by 6
  7. 2025Towards properly implementing Theory of Mind in AI systems: An account of four misconceptionscited by 3
  8. 2026Bridging the Agent-World Gap: Text World Models for LLM-based Agentscited by 3
  9. 2026A formal definition and meta-model for a machine theory of mindcited by 1
  10. 2025TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligencecited by 0
  11. 2025EvolvTrip: Enhancing Literary Character Understanding with Temporal Theory-of-Mind Graphscited by 0
  12. 2025Language Models Might Not Understand You: Evaluating Theory of Mind via Story Promptingcited by 0
4 more
  1. 2025Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoningcited by 0
  2. 2026Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluationscited by 0
  3. 2026MindZero: Learning Online Mental Reasoning With Zero Annotationscited by 0
  4. 2026PICTURE: Enhancing Theory-of-Mind in Large Language Models by Revealing, Not Hiding, Characters' Lack of Knowledgecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Probing the Robustness of Theory of Mind in Large Language Models
  2. 2025Decompose-ToM: Enhancing Theory of Mind Reasoning in Large Language Models through Simulation and Task Decomposition
  3. 2026Understanding Artificial Theory of Mind: Perturbed Tasks and Reasoning in Large Language Models
  4. 2024Zero, Finite, and Infinite Belief History of Theory of Mind Reasoning in Large Language Models
  5. 2024Mind Your Theory: Theory of Mind Goes Deeper Than Reasoning
  6. 2024Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Models
  7. 2026To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks
  8. 2024Position: Theory of Mind Benchmarks are Broken for Large Language Models