Metraipolis › archive › dc_54e920bc009e

FACT: Failure-Aware Causal Training for World-Action Models — arXiv:2608.10232

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10232
License (as archived)
CC0-1.0
Archived
2026-10-19T06:08:57.395Z
SHA-256 of the archived text
b4825283407fbf28b410b2c1406d3f6e174419c731fa8e6fa8b7576ac23d7852
Stable URL of this page
https://metraipolis.com/documento/dc_54e920bc009e

How to cite

FACT: Failure-Aware Causal Training for World-Action Models — arXiv:2608.10232 — arXiv (en), https://arxiv.org/abs/2608.10232 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_54e920bc009e (Metraipolis archive dc_54e920bc009e, sha256 b4825283407fbf28b410b2c1406d3f6e174419c731fa8e6fa8b7576ac23d7852)
BibTeX
@misc{dc54e920bc009e,
  title = {FACT: Failure-Aware Causal Training for World-Action Models — arXiv:2608.10232},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10232},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_54e920bc009e; sha256 b4825283407fbf28b410b2c1406d3f6e174419c731fa8e6fa8b7576ac23d7852},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10232. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent world-action models (WAMs) show that co-training policies with future prediction can provide physical priors for action generation. Building on the future-prediction ability of video models, many WAMs generate future videos and recover actions with inverse-dynamics models, or use these predicted videos as goal conditions for action generation. In both cases, the world model is trained mostly on successful demonstrations and has little reason to predict the consequences of bad actions. We introduce FACT, a causal World-Action Model that predicts future video and task progress conditioned on the executed action. This action-conditioned interface allows failure rollouts to supervise action consequences, turning bad actions into valid future targets rather than being discarded. Failure-aware training makes the progress predictor aware of both successful and failed action outcomes, which can optionally be used to score sampled action candidates at inference. Extensive experiments on simulation and real-world bimanual manipulation tasks show that FACT outperforms many existing baselines, improves as failure data are incorporated into training, and reduces success-biased future hallucination under bad actions. See more details at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.10232 — 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 2026-10-19T05:57:28.341Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).