Line of inquiry
Inquiring lines›How do training methods and scalin…›How do training methods and scalin…›this line of inquiry
Do language models develop actual world models or merely task heuristics?
A broader line of inquiry — a family of 30 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 30
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Why must world models be nested rather than flat and uniform?
- How do world models decompose between representation of facts versus generative mechanisms?
- Can a world model have rich representations without adequate data coverage?
- What distinguishes task-specific heuristics from genuine world models?
- Can world models simulate actionable possibilities instead of just predicting next states?
- Why do foundation models develop heuristics instead of world models?
- Why does integrating world models with decision-making systems matter?
- Do LLMs need world models to make accurate predictions?
- Can simulation fidelity limit what agents learn from trained world models?
- Does iterative computation for reasoning transfer to environment dynamics modeling?
- Can world models form from aggregated partial information across training distributions?
- Why do epistemic failure modes cluster around world model limitations?
- Does next-state prediction alone build mechanistic world models or just sophisticated interpolation?
- Can frozen world models from training cutoff remain adequate for real-world reasoning?
- How do foundation models develop task-specific heuristics instead of world models?
- Does sequence prediction accuracy prove an underlying world model exists?
- What architectural features enable counterfactual reasoning in world models?
- How small must the anchoring stream be to correct world model bias?
- Why has agent research prioritized policy over world model development?
- What's the difference between representing world facts and generating world mechanisms?
- How do implicit world models and self-reflection operationalize consequence-based learning?
- What makes open-schema state representation better than fixed schemas for diverse worlds?
- Can economic world models explain outcomes or only predict them?
- How do training objectives shape what a world model actually learns?
- How should world models represent what one person knows versus another?
- How do spectral-norm constraints prevent divergence in world model rollouts?
- What are the five inseparable design choices when building world models?
- How do institutions become endogenous in economic world models?
- What cognitive structures do realistic belief models need to include?
- How does iterative depth apply to world models and physical simulation?