Metraipolis › archive › dc_aebb552b2f9b
WorldGraph: Graph-Native World Modeling — arXiv:2609.34159
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34159
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:12.513Z
- SHA-256 of the archived text
0495597a1adc6c36703c14d8b32e4f96cf7b74701e113899b973490160289130- Stable URL of this page
https://metraipolis.com/documento/dc_aebb552b2f9b
How to cite
WorldGraph: Graph-Native World Modeling — arXiv:2609.34159 — arXiv (en), https://arxiv.org/abs/2609.34159 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aebb552b2f9b (Metraipolis archive dc_aebb552b2f9b, sha256 0495597a1adc6c36703c14d8b32e4f96cf7b74701e113899b973490160289130)
BibTeX
@misc{dcaebb552b2f9b,
title = {WorldGraph: Graph-Native World Modeling — arXiv:2609.34159},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34159},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aebb552b2f9b; sha256 0495597a1adc6c36703c14d8b32e4f96cf7b74701e113899b973490160289130},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34159. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.34159 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:02.880Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).