cs.LGNov 9, 2026

An Evaluation of Tabular Foundation Models as Training-Free World Models

Authors: Xian Yeow Lee, Ryoichi Takase, Ahmed Farahat

Organizations: Industrial AI Lab, Hitachi America, Ltd.

Abstract

World models are widely considered to be a potential key component of model-based reinforcement learning and robot planning, but typically require task-specific training on substantial interaction data. We investigate whether a pretrained tabular foundation model (TabFM) can serve as a training-free dynamics model for world modeling by framing next-state prediction as in-context regression over transition pairs, and where such a model helps and where it breaks. Across synthetic dynamical systems and robot locomotion benchmarks, TabFM is more accurate than LSTM and MLP models trained from scratch on the same limited transitions in almost all settings, and among regressors fitted to the same data it is the most accurate on locomotion, while a Gaussian process is more accurate on smooth low-dimensional systems. However, models trained on the full dataset remain substantially better on most systems. When rolled out autoregressively over multiple steps, TabFM's accuracy depends strongly on how much context it is given. With a short context, its rollouts quickly degrade to the level of a trivial baseline, whereas with a long context they improve substantially and, on one locomotion task, exceed a trained LSTM. Inference is also about three orders of magnitude slower than an LSTM. Overall, in their current state, we find that training-free priors are useful as predictors when data are scarce and enough context is available, but they are not yet a substitute for trained world models in planning.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. World Model for Robot Learning: A Comprehensive Survey

    Apr 30, 2026Bohan Hou, Gen Li, Jindou Jia +15World Model LearningWorld Models for Robotics

  2. Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations

    May 25, 2026Minghao Fu, Fan Feng, Nicklas Hansen +1World Model LearningWorld Models

  3. Reinforcement Learning Foundation Models Should Already Be A Thing

    Jun 17, 2026Abdelrahman Zighem, Jill-Jênn VieSynthetic Data PretrainingReinforcement Learning