Metraipolis › archive › dc_8038f697c0b4

OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling — arXiv:2609.23753

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23753
License (as archived)
CC0-1.0
Archived
2026-10-09T07:08:35.355Z
SHA-256 of the archived text
12f180023ea7959e40ab53724cd6708a51bfcac1f0de5672167c0df8dceb9ea8
Stable URL of this page
https://metraipolis.com/documento/dc_8038f697c0b4

How to cite

OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling — arXiv:2609.23753 — arXiv (en), https://arxiv.org/abs/2609.23753 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8038f697c0b4 (Metraipolis archive dc_8038f697c0b4, sha256 12f180023ea7959e40ab53724cd6708a51bfcac1f0de5672167c0df8dceb9ea8)
BibTeX
@misc{dc8038f697c0b4,
  title = {OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling — arXiv:2609.23753},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23753},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8038f697c0b4; sha256 12f180023ea7959e40ab53724cd6708a51bfcac1f0de5672167c0df8dceb9ea8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23753. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative world models aim to predict future states conditioned on actions, where action controllability is fundamental for reliable dynamics modeling. While recent efforts leverage simulator-generated data to enhance this capability, existing training pipelines face two fundamental limitations. First, static offline data collection leads to a distribution misalignment between training sets and the model's evolving error patterns, failing to resolve critical long-tail scenarios where dynamics predictions remain unreliable. Second, the standard objective of minimizing observational discrepancy often encourages the model to exploit spurious correlations instead of capturing the underlying action-effect causality. To address these limitations, we propose OnlineWM, an online training framework that continuously improves world modeling through active simulator interaction and causality-aware optimization. OnlineWM introduces two key innovations: (1) Active Online Learning: Instead of using fixed datasets, OnlineWM adaptively queries the simulator for new interaction sequences that target the model's current predictive weaknesses, ensuring high-utility data acquisition. (2) Causality-Aware Fine-Tuning: We propose a counterfactual learning strategy that contrasts the outcomes of different actions from identical states, forcing the model to attribute state transitions to specific actions rather than ambient environmental evolution, thereby grounding its predictions in reliable causal mechanisms. By integrating active data acquisition with causal optimization, OnlineWM establishes a closed-loop refinement process that ensures the model is both robust to diverse scenarios and precise in its causal attribution. Extensive experiments demonstrate that OnlineWM significantly enhances action controllability and generalizes effectively to unseen domains.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.23753 — 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 2026-10-09T06:58:09.597Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).