# In CEM, a World Model Is Also a Proposal Mechanism

arXiv: https://arxiv.org/abs/2610.00921 · HTML: https://mlsanity.com/paper/2610.00921/

## Key facts

- No citing papers in the map yet (data through 14 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.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 15 of 15)

- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [DeepMDP: Learning Continuous Latent Space Models for Representation Learning](https://mlsanity.com/paper/1906.02736/) (2019)
- [Objective Mismatch in Model-based Reinforcement Learning](https://mlsanity.com/paper/2002.04523/) (2020)
- [The Value Equivalence Principle for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2011.03506/) (2020)
- [Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization](https://mlsanity.com/paper/2004.08763/) (2020)
- [How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position](https://mlsanity.com/paper/2606.15032/) (2026)
- [Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning](https://mlsanity.com/paper/2608.18746/) (2026)
- [Latent World Models with Monotone Planning Costs for Image-Goal Navigation](https://mlsanity.com/paper/2608.09073/) (2026)
- [Imperfect World Models are Exploitable](https://mlsanity.com/paper/2605.15960/) (2026)
- [The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use](https://mlsanity.com/paper/2608.12959/) (2026)
- [Traj-LeWM: Path-Aware World-Model Planning via Latent Trajectory Cost](https://mlsanity.com/paper/2608.14125/) (2026)
- [Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Models](https://mlsanity.com/paper/2607.23602/) (2026)
- [Reinforced Planning with Latent World Models](https://mlsanity.com/paper/2608.18669/) (2026)

## 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.