mlsanityData to 7 Oct 2026

In CEM, a World Model Is Also a Proposal Mechanism

arXiv 2610.00921 ↗First posted 1 Oct 2026cs.LG cs.ROcited by 0

On the map: World models → World models for language agents also fits: Latent dynamics models and model-based RL

Abstract (arXiv)

The cross-entropy method (CEM) uses world-model scores to select action sequences and fit the distribution sampled in its next iteration. A scoring error can therefore change both the present decision and the candidates considered later. We evaluate these two roles separately. Four types of predictive model generate CEM traces, and every model rescores every saved candidate pool. Executing the same candidates in the environment provides a reference elite set and proposal update. Across twelve independently trained task-seed units on Walker and Cheetah, the pre-specified proposal distance falls from the first to the final CEM iteration in every unit. Proposal widths contract and fitted means separate relative to the remaining search width. Pairwise ranking agreement stays near chance on Walker and declines on Cheetah; elite-set agreement does not improve. This comparison shows greater variation between scorers than between pool sources on Cheetah; Walker has variation in both and in their pairings. We use the original six units to select Random nonlinear for a one-update intervention, without inspecting intervention outcomes. Replacing its first model-ranked update with an environment-ranked update lowers final realised selected-sequence cost in those six units and in six further units held out from the selection.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 15 of its 19 references that are in the map. First posted on arXiv 1 Oct 2026.

Builds on

15 of 19 references.

References · 15

  1. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  2. 2018DeepMind Control Suitecited by 935
  3. 2020dm_control: Software and Tasks for Continuous Controlcited by 368
  4. 2019DeepMDP: Learning Continuous Latent Space Models for Representation Learningcited by 204
  5. 2020The Value Equivalence Principle for Model-Based Reinforcement Learningcited by 88
  6. 2020Objective Mismatch in Model-based Reinforcement Learningcited by 87
  7. 2020Model-Predictive Control via Cross-Entropy and Gradient-Based Optimizationcited by 32
  8. 2026How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Positioncited by 9
  9. 2026Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planningcited by 5
  10. 2026Imperfect World Models are Exploitablecited by 4
  11. 2026Latent World Models with Monotone Planning Costs for Image-Goal Navigationcited by 4
  12. 2026The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Usecited by 2
3 more
  1. 2026Traj-LeWM: Path-Aware World-Model Planning via Latent Trajectory Costcited by 2
  2. 2026Reinforced Planning with Latent World Modelscited by 2
  3. 2026Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Modelscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026The Intervention Gap in Latent World Models
  2. 2026verdi: retrieval is not transfer for continual world model optimization
  3. 2026When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models
  4. 2026Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning
  5. 2022On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
  6. 2026Latent State Design for World Models under Sufficiency Constraints
  7. 2026LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning
  8. 2026Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training