# Modeling the Mental World for Embodied AI: A Comprehensive Review arXiv: https://arxiv.org/abs/2601.02378 ยท HTML: https://mlsanity.com/paper/2601.02378/ ## Key facts - Cited by 1 papers in the map (data through 14 Oct 2026). - Placed in World models for navigation, one of 11 directions in World models. - Builds on 38 of its 117 references that are in the map. - First posted on arXiv 17 Dec 2025. ## Placed in - World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/) ## Builds on (most cited first, 30 of 38) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025) - [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023) - [World Models](https://mlsanity.com/paper/1803.10122/) (2018) - [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025) - [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024) - [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024) - [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025) - [DreamGen: Unlocking Generalization in Robot Learning through Video World Models](https://mlsanity.com/paper/2505.12705/) (2025) - [Predictive Coding: a Theoretical and Experimental Review](https://mlsanity.com/paper/2107.12979/) (2021) - [Boosting Theory-of-Mind Performance in Large Language Models via Prompting](https://mlsanity.com/paper/2304.11490/) (2023) - [LLMs achieve adult human performance on higher-order theory of mind tasks](https://mlsanity.com/paper/2405.18870/) (2024) - [Embodied AI Agents: Modeling the World](https://mlsanity.com/paper/2506.22355/) (2025) - [OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models](https://mlsanity.com/paper/2402.06044/) (2024) - [IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments](https://mlsanity.com/paper/2506.09849/) (2025) - [CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models](https://mlsanity.com/paper/2506.09943/) (2025) - [Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning](https://mlsanity.com/paper/2412.12175/) (2024) - [Language Models Represent Beliefs of Self and Others](https://mlsanity.com/paper/2402.18496/) (2024) - [A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs](https://mlsanity.com/paper/2506.09987/) (2025) - [Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models](https://mlsanity.com/paper/2502.11881/) (2025) - [WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning](https://mlsanity.com/paper/2506.04363/) (2025) - [Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States](https://mlsanity.com/paper/2505.17663/) (2025) - [SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions](https://mlsanity.com/paper/2506.23046/) (2025) - [Social World Models](https://mlsanity.com/paper/2509.00559/) (2025) - [Generative Emergent Communication: Large Language Model is a Collective World Model](https://mlsanity.com/paper/2501.00226/) (2024) - [Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection](https://mlsanity.com/paper/2501.15355/) (2025) - [MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems](https://mlsanity.com/paper/2505.18943/) (2025) - [A Systematic Review on the Evaluation of Large Language Models in Theory of Mind Tasks](https://mlsanity.com/paper/2502.08796/) (2025) - [SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments](https://mlsanity.com/paper/2505.23713/) (2025) - [Through the Theory of Mind's Eye: Reading Minds with Multimodal Video Large Language Models](https://mlsanity.com/paper/2406.13763/) (2024) ## Built on by (most cited first, 1 of 1) - [MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention](https://mlsanity.com/paper/2606.01063/) (2026) ## Abstract (arXiv) As the application of Embodied AI Agents in avatars, wearable devices, and robotic systems continues to deepen, their core research challenges have gradually shifted from physical environment interaction to the accurate understanding of social interactions. Traditional physical world models (PWM) focus on quantifiable physical attributes such as space and motion, failing to meet the needs of social intelligence modeling. In contrast, the Mental World Model (MWM), as a structured representation of humans' internal mental states, has become the critical cognitive foundation for embodied agents to achieve natural human-machine collaboration and dynamic social adaptation. However, current MWM research faces significant bottlenecks: such as fragmented conceptual framework with vague boundaries between MWM and PWM, disjointed reasoning mechanisms for the technical pathways and applicable scenarios of different Theory of Mind (ToM) reasoning paradigms, and detachment between evaluation and practice. To address these issues, this review systematically synthesizes over 100 authoritative studies to provide a comprehensive overview of MWM research for embodied AI. Its core contributions are threefold: First, it constructs a complete theoretical framework for MWM for the first time. Specifically, it distinguishes the essential differences between MWM and PWMs. Second, it systematically defines the key components of MWM through two paradigms for mental element representation. Third, it comprehensively analyzes two core ToM reasoning paradigms with 19 ToM methods. Finally, it also clarifies the integration trend of neuro-symbolic hybrid architectures, and synthesizes 26 ToM evaluation benchmarks. This work aims to promote the integration of embodied agents into human society and advance the in-depth development of human-machine collaborative interaction.