When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models

Jul 17, 2026

A new preprint demonstrates that large language model (LLM)-synthesized code world models can achieve perfect transition accuracy on sampled trajectories but still systematically fail during actual gameplay due to missing pivotal dynamics. The study quantifies this failure, showing it follows a specific law and persists even with additional data, as LLMs tend to translate rather than infer rules. The authors argue that adequacy for planning should be evaluated on the search distribution or through direct play, rather than relying solely on prediction accuracy.

Why it matters: This work reveals a fundamental gap in current validation practices for AI world models, with implications for the safety and reliability of planning systems.

Full story at: arXiv AI/ML ↗