Structural-Test Geometry as an Inductive Bias for Partially Observable World Models
cs.LG
Submitted: 2026-10-28
Updated: 2026-10-28
License: http://creativecommons.org/licenses/by/4.0/
The gist: Predictive world-model objectives need not organize latent histories according to distinctions required for later control.
Terminology
Abstract
Predictive world-model objectives need not organize latent histories according to distinctions required for later control. With privileged simulator access during training, should response-derived structural information be predicted, decoded, or imposed directly on latent geometry--and how do these choices compare with structured belief distillation? We define posterior-marginalized structural tests whose response distributions induce a pseudometric over histories, then train quotient-preserving (QP) world models by aligning shared latent Euclidean distances to that metric. Across a fixed six-task diagnostic suite, the largest differences appear under held-out structural variation: QP improves planning success by 26.1 points [21.5,30.7] over metric decoding and 6.4 points [3.8,9.0] over structured belief distillation. On GridWorld, metric decoding accurately recovers held-out structural distances (ρ=.91) while its native latent geometry remains more distorted than QP's (paired IQD difference.22 [.20,.24]), showing that relational recoverability and direct geometric alignment can diverge.
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis