FACT: Failure-Aware Causal Training for World-Action Models

arXiv:2608.10232v1 Announce Type: cross Abstract: 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 https://fact-wam.github.io/

Related

• Learning 4D Geometric Priors for Inference-Efficient World Action Models
• TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction
• Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
• SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models

Source: arXiv cs.AI | 2026-08-12