# Graph World Models: Concepts, Taxonomy, and Future Directions

arXiv: https://arxiv.org/abs/2604.27895 · HTML: https://mlsanity.com/paper/2604.27895/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 51 of its 65 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 30 of 51)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Semi-parametric Topological Memory for Navigation](https://mlsanity.com/paper/1803.00653/) (2018)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [Search on the Replay Buffer: Bridging Planning and Reinforcement Learning](https://mlsanity.com/paper/1906.05253/) (2019)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents](https://mlsanity.com/paper/2407.04363/) (2024)
- [DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation](https://mlsanity.com/paper/2308.07498/) (2023)
- [AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes](https://mlsanity.com/paper/2312.06644/) (2023)
- [Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships](https://mlsanity.com/paper/2402.12259/) (2024)
- [World Models for Autonomous Driving: An Initial Survey](https://mlsanity.com/paper/2403.02622/) (2024)
- [Improving Generative Imagination in Object-Centric World Models](https://mlsanity.com/paper/2010.02054/) (2020)
- [World Model as a Graph: Learning Latent Landmarks for Planning](https://mlsanity.com/paper/2011.12491/) (2020)
- [Embodied AI Agents: Modeling the World](https://mlsanity.com/paper/2506.22355/) (2025)
- [Visual Grounding of Learned Physical Models](https://mlsanity.com/paper/2004.13664/) (2020)
- [Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces](https://mlsanity.com/paper/2503.19199/) (2025)
- [Sora as a World Model? A Complete Survey on Text-to-Video Generation](https://mlsanity.com/paper/2403.05131/) (2024)
- [CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory](https://mlsanity.com/paper/2505.05622/) (2025)
- [Learning Knowledge Graph-based World Models of Textual Environments](https://mlsanity.com/paper/2106.09608/) (2021)
- [Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation](https://mlsanity.com/paper/2206.11403/) (2022)
- [Factored Adaptation for Non-Stationary Reinforcement Learning](https://mlsanity.com/paper/2203.16582/) (2022)
- [CityGPT: Empowering Urban Spatial Cognition of Large Language Models](https://mlsanity.com/paper/2406.13948/) (2024)
- [COKE: A Cognitive Knowledge Graph for Machine Theory of Mind](https://mlsanity.com/paper/2305.05390/) (2023)
- [AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction](https://mlsanity.com/paper/2408.13986/) (2024)
- [3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators](https://mlsanity.com/paper/2011.06464/) (2020)
- [RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing](https://mlsanity.com/paper/2407.01418/) (2024)

## Built on by (most cited first, 6 of 6)

- [A Structural Dynamics Graph World Model: Unified Modeling, Constrained Rollout, and Interpretable Calibration](https://mlsanity.com/paper/2608.08689/) (2026)
- [World-as-Graph: Relational World Modeling Through Latent Space Graphs](https://mlsanity.com/paper/2609.38927/) (2026)
- [Multi-Agent Embodied Autonomous Driving (MAEAD): From V2X Information Exchange to Shared World Models](https://mlsanity.com/paper/2606.13840/) (2026)
- [Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies](https://mlsanity.com/paper/2609.28670/) (2026)
- [WorldGraph: Graph-Native World Modeling](https://mlsanity.com/paper/2609.34159/) (2026)
- [Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context](https://mlsanity.com/paper/2610.19364/) (2026)

## Abstract (arXiv)

As one of the mainstream models of artificial intelligence, world models allow agents to learn the representation of the environment for efficient prediction and planning. However, classical world models based on flat tensors face several key problems, including noise sensitivity, error accumulation and weak reasoning. To address these limitations, many recent studies use graph structure to decompose the environment into entity nodes and interactive edges, and model virtual environments in a structured space. This paper systematically formalizes and unifies these emerging graph-based works under the concept of graph world models (GWMs). To the best of our knowledge, GWMs have not yet been explicitly defined and surveyed as a unified research paradigm. Furthermore, we propose a taxonomy based on relational inductive biases (RIB), categorizing GWMs by the specific structural priors they inject: (1) spatial RIB for topological abstraction; (2) physical RIB for dynamic simulation; and (3) logical RIB for causal and semantic reasoning. For each model category, we outline the key design principles, summarize representative models, and conduct comparative analyses. We further discuss open challenges and future directions, including dynamic graph adaptation, probabilistic relational dynamics, multi-granularity inductive biases, and the need for dedicated benchmarks and evaluation metrics for GWMs.