SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning

2026-07-20

AI Summary

This work addresses the challenge in long-horizon planning where the exponential growth of the action sequence search space with planning horizon leads to poor-quality candidates, limiting the performance of latent-variable world models. To overcome this, the authors propose a multi-scale subgoal-conditioned planning method that decomposes long-term goals into achievable latent subgoals at varying temporal granularities, thereby guiding structured action generation. Leveraging a frozen world model for sequence evaluation and refinement, the approach replaces random initialization with semantic subgoal priors. Evaluated on PushT and OGBench Cube tasks under a 150-unit goal displacement, the method significantly improves success rates—from 12.7% to 64.7% and from 26.7% to 67.3%, respectively—demonstrating a balanced capability in both precise local control and effective long-horizon goal progression.

Abstract

Latent world models have emerged as a powerful planning paradigm by learning action-conditioned predictive dynamics and using them as internal simulators to imagine and evaluate candidate action sequences. However, as the planning horizon grows, performance becomes increasingly constrained by proposal quality: a fixed candidate budget must search an exponentially larger action space, making it difficult to expose the world model to high-quality candidate futures for evaluation. In this paper, we introduce a prior-conditioned planner that replaces random proposal initialization with structured guidance. At each planning stage, a goal-conditioned generator predicts the next reachable latent subgoal for a specified duration, which is then used to condition the generation of candidate action sequences. To capture semantic information across temporal scales, we use subgoals of varying durations as priors, balancing fine-grained local control with higher-level long-horizon progress. Then the frozen world model evaluates and refines these subgoal-conditioned proposals before execution. Experiments on PushT and OGBench Cube show that coupling latent subgoal decomposition with prior-conditioned action generation substantially improves long-horizon planning while preserving strong short-horizon performance. To be specific, when the target offset is $150$, it raises PushT success from $12.7\%$ to $64.7\%$ and OGBench Cube success from $26.7\%$ to $67.3\%$.

Problem

• latent world models
• long-horizon planning
• action proposal
• subgoal decomposition
• planning efficiency

Innovation

• subgoal-conditioned planning
• latent world models
• prior-conditioned action generation
• hierarchical planning
• model-based reinforcement learning