- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper argues that world models memorize environment rules in their weights rather than learn them from observations during an episode. When rules change between episodes, models fail to adapt their predictions, while fine-tuning and test-time adaptation introduce forgetting and interference. The authors propose PRISMO, an external memory that works with a frozen model. It stores each rule from a single observation, overrides predictions only for the variables governed by that rule, and resets between episodes. On two Craftax models, PRISMO improves rule-state accuracy from 29.4% to 87.2% and from 23.9% to 79.3%, without changing other predictions. On XLand-MiniGrid, it composes two individually observed rules into a two-step chain that the model never experienced, achieving 94.8% accuracy. With one rule withheld, accuracy drops to 0.6%, suggesting the model genuinely uses the stored rules.
Critical strengths
-
The authors compare predictions before and after a rule is first observed, using predict-unchanged baselines and encoder ceilings to separate memorisation from actual rule learning. This makes the core claim convincing. They also acknowledge unfavourable results, including cases where apparent in-episode gains are simply due to a shifting baseline.
-
The XLand experiment shows that rules learned from individual observations can be combined into a two-step chain the model has never executed. The negative control strengthens this result: accuracy drops to 0.6% when the second rule is withheld, compared with 93.1% when the full rule table is provided, suggesting the failure comes from the missing rule rather than the chain's complexity.
Critical weaknesses
-
PRISMO assumes the interaction types and the variables each rule affects are known, so it is not clear how well it works when this structure must be discovered. On TWM, a frozen-host latent baseline achieves similar accuracy (86.8% vs. 87.2%), suggesting PRISMO’s main advantage is avoiding roughly 200 gradient steps per observation, rather than improving accuracy.
-
The study uses two small Craftax models and XLand models trained on 2,700 episodes, with rule-event frequency deliberately increased. It remains unclear whether the findings hold for larger models, broader training data, or more natural environments. Other results also temper the claims: the fixed-mapping host achieves a longer rollout horizon than PRISMO (43 vs. 32 steps), while the decision-task advantage (61.6% vs. 45.5%) is based on just 36 episodes, with overlapping confidence intervals.
Questions for authors
-
PRISMO assumes the interaction types and governed variables are known in advance. How much of its benefit remains if either must be inferred from observations? If this is out of scope, could the paper clarify that its contribution is focused on rule acquisition given a known rule structure?
-
Appendix A.3 notes that default data collection produces too few rule events for evaluation. Could you vary the event density and report how the memorisation diagnosis and PRISMO’s gains change? This would clarify whether the findings hold across different densities or depend on the artificially increased frequency.
-
The current findings are limited to the tested models, training setups, and corpus sizes. Could this limitation be stated more clearly in the abstract and introduction, rather than presenting memorisation as a general property of world models?
-
Could PRISMO be tested with noisy or partially observed rule effects, or rules that change within an episode? These settings would help establish how well the approach works beyond the current assumption of observable rule effects and episode-level resets.