Graph World Models: Concepts, Taxonomy, and Future Directions

• URL: http://arxiv.org/abs/2604.27895v1
• Date: Thu, 30 Apr 2026 14:09:14 GMT
• Title: Graph World Models: Concepts, Taxonomy, and Future Directions
• Abstract summary: This paper systematically formalizes and unifies emerging graph-based works under the concept of graph world models (GWMs)<n>To the best of our knowledge, GWMs have not yet been explicitly defined and surveyed as a unified research paradigm.
• Score: 21.0271660757056
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• World Action Models: The Next Frontier in Embodied AI [123.5787299299832]
  Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning.<n>They learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention.<n>A growing body of work addresses this limitation by integrating world models, predictive models of environment dynamics, into the action generation pipeline.
  arXiv  Detail & Related papers  (2026-05-12T13:10:52Z)
• The Trinity of Consistency as a Defining Principle for General World Models [106.16462830681452]
  General World Models are capable of learning, simulating, and reasoning about objective physical laws.<n>We propose a principled theoretical framework that defines the essential properties requisite for a General World Model.<n>Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress.
  arXiv  Detail & Related papers  (2026-02-26T16:15:55Z)
• Beyond MMD: Evaluating Graph Generative Models with Geometric Deep Learning [0.0]
  Graph Generative Models (GGMs) have emerged as a promising solution to the problem of generating realistic graphs.<n>This paper introduces a novel methodology for evaluating GGMs that overcomes the limitations of Maximum Mean Discrepancy (MMD)<n>We present a comprehensive evaluation of two state-of-the-art Graph Generative Models: Graph Recurrent Attention Networks (GRAN) and Efficient and Degree-guided graph GEnerative model (EDGE)
  arXiv  Detail & Related papers  (2025-12-16T09:51:44Z)
• Towards agent-based-model informed neural networks [0.5787117733071417]
  We present a framework for designing neural networks consistent with the underlying principles of agent-based models.<n>We validate the framework across three case studies of increasing complexity.
  arXiv  Detail & Related papers  (2025-12-05T14:50:50Z)
• Expressivity of Representation Learning on Continuous-Time Dynamic Graphs: An Information-Flow Centric Review [2.310679096120274]
  This paper provides a comprehensive review of Graph Representation Learning (GRL) on Continuous-Time Dynamic Graph (CTDG) models.<n>We introduce a novel theoretical framework that analyzes the expressivity of CTDG models through an Information-Flow (IF) lens.
  arXiv  Detail & Related papers  (2024-12-05T00:12:50Z)
• Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective [60.64922606733441]
  We introduce a mathematical model that formalizes relational learning as hypergraph recovery to study pre-training of Foundation Models (FMs) In our framework, the world is represented as a hypergraph, with data abstracted as random samples from hyperedges. We theoretically examine the feasibility of a Pre-Trained Model (PTM) to recover this hypergraph and analyze the data efficiency in a minimax near-optimal style.
  arXiv  Detail & Related papers  (2024-06-17T06:20:39Z)
• A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches [41.55545145863787]
  Future Frame Synthesis (FFS) is a core challenge in machine intelligence and a cornerstone for developing predictive world models.<n>This survey provides a comprehensive analysis of the FFS landscape, charting its critical evolution from deterministic algorithms focused on pixel-level accuracy to modern generative paradigms.<n>We introduce a novel taxonomy organized by algorithmicity, which not only categorizes existing methods but also reveals the fundamental drivers-advances in architectures, datasets, and computational scale-behind this paradigm shift.
  arXiv  Detail & Related papers  (2024-01-26T08:59:38Z)
• PGODE: Towards High-quality System Dynamics Modeling [40.76121531452706]
  This paper studies the problem of modeling multi-agent dynamical systems, where agents could interact mutually to influence their behaviors. Recent research predominantly uses geometric graphs to depict these mutual interactions, which are then captured by graph neural networks (GNNs) We propose a new approach named Prototypical Graph ODE to address the problem.
  arXiv  Detail & Related papers  (2023-11-11T12:04:47Z)
• Graph Foundation Models: Concepts, Opportunities and Challenges [66.37994863159861]
  Foundation models have emerged as critical components in a variety of artificial intelligence applications.<n>The capabilities of foundation models in generalization and adaptation motivate graph machine learning researchers to discuss the potential of developing a new graph learning paradigm.<n>This article introduces the concept of Graph Foundation Models (GFMs), and offers an exhaustive explanation of their key characteristics and underlying technologies.
  arXiv  Detail & Related papers  (2023-10-18T09:31:21Z)
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal [57.8455911689554]
  Knowledge graph reasoning (KGR) aims to deduce new facts from existing facts based on mined logic rules underlying knowledge graphs (KGs) It has been proven to significantly benefit the usage of KGs in many AI applications, such as question answering, recommendation systems, and etc.
  arXiv  Detail & Related papers  (2022-12-12T08:40:04Z)
• TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning [87.38675639186405]
  We propose a novel graph neural network approach, called TCL, which deals with the dynamically-evolving graph in a continuous-time fashion. To the best of our knowledge, this is the first attempt to apply contrastive learning to representation learning on dynamic graphs.
  arXiv  Detail & Related papers  (2021-05-17T15:33:25Z)
• Contrastive Topographic Models: Energy-based density models applied to the understanding of sensory coding and cortical topography [9.555150216958246]
  We address the problem of building theoretical models that help elucidate the function of the visual brain at computational/algorithmic and structural/mechanistic levels.
  arXiv  Detail & Related papers  (2020-11-05T16:36:43Z)

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.