WorldGraph: Graph-Native World Modeling
cs.LG, cs.AI, cs.CV
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/USTC-DataDarknessLab/Graph-Native_World_Modeling
License: http://creativecommons.org/licenses/by/4.0/
The gist: World models infer latent states of an environment to capture its underlying dynamics and predict future evolution.
Terminology
Abstract
World models infer latent states of an environment to capture its underlying dynamics and predict future evolution. Many real-world environments, however, are inherently relational and observed as evolving graphs, where entities, relations, and their properties change over time. Prior graph-related world models use graph structures to organize internal states or support task-specific reasoning, rather than treating an evolving graph itself as the modeled world. We instead study graph world modeling (GWM), where graph evolution itself constitutes the world dynamics. We formulate graph world modeling over observed graph evolution, latent graph states, and heterogeneous graph-transition predictions. Based on this formulation, we construct GWM-Zero, a benchmark covering node-, edge-, and graph-level transitions over eight temporal graph datasets. We propose WorldGraph, which combines a state-aware graph transformer for multi-granularity structural and transition-conditioned evolution modeling with transition-aware GRPO using dynamic grouping and structure-aware verifiable rewards. Extensive experiments on GWM-Zero show that WorldGraph consistently outperforms representative graph representation, temporal graph learning, graph pretraining, and graph world-model baselines across all three transition granularities.
Sources
- Layer Normalization
- OpenAI Gym
- Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
- Graph World Models: Concepts, Taxonomy, and Future Directions
- Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
- Temporal Graph Networks for Deep Learning on Dynamic Graphs
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks