Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning

2026-06-19

AI Summary

Existing latent world models rely on single-step prediction, leading to error accumulation during recursive rollout in long-horizon planning and suffering from a mismatch between their training objective and the actual planning task. This work proposes the Variable-Length World Model (VLWM), which introduces, for the first time, a mechanism for predicting future latent states based on variable-length action sequences. VLWM employs a curriculum learning strategy that progressively optimizes the model from short- to long-horizon predictions and is accompanied by a tailored latent-space planning algorithm. Evaluated across multiple long-horizon control tasks, VLWM outperforms the current state-of-the-art method, LeWM, by an average of 13%, with particularly pronounced gains in tasks requiring extended planning horizons.

Abstract

Recently, world models have emerged as a promising paradigm for building intelligent agents by learning predictive models that estimate future environment states conditioned on observations and actions. In particular, JEPA-style latent world models provide an efficient alternative to pixel space prediction by learning action-conditioned dynamics in compact representation spaces. However, existing latent world models typically rely on one-step prediction and must be recursively rolled out for long-horizon planning, which leads to compounding errors and a mismatch between training objectives and downstream planning tasks. To address this limitation, we propose Variable-length Latent World Models (VLWMs), a framework that learns to predict future latent states conditioned on action sequences of variable lengths. Instead of training only on one-step transitions, VLWMs directly model temporally extended dynamics, allowing the same predictor to evaluate action plans over different horizons. We further introduce a curriculum training strategy that progressively expands the action horizon, stabilizing optimization from short-range dynamics to long-range prediction. At test time, we design planning methods tailored to VLWMs to better exploit their variable-length predictive capabilities. Experiments on long-horizon control tasks show that VLWMs significantly improve latent space world models, achieving 13\% average improvement over the state-of-the-art LeWM across different datasets, with especially large gains on tasks requiring extended planning. These results suggest that VLWM provides a simple yet effective paradigm for improving long-horizon prediction and planning in latent world models.

Problem

• long-horizon planning
• latent world models
• compounding errors
• temporal dynamics
• action-conditioned prediction

Innovation

• Variable-length Latent World Models
• long-horizon planning
• action-conditioned dynamics
• curriculum training
• latent world models