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

arXiv: https://arxiv.org/abs/2607.17973 · HTML: https://mlsanity.com/paper/2607.17973/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 18 of its 23 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 18 of 18)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [OGBench: Benchmarking Offline Goal-Conditioned RL](https://mlsanity.com/paper/2410.20092/) (2024)
- [Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models](https://mlsanity.com/paper/2502.14819/) (2025)
- [Hierarchical Planning with Latent World Models](https://mlsanity.com/paper/2604.03208/) (2026)
- [PRISM: PRior-guided Imagination Sampling in world Models](https://mlsanity.com/paper/2606.07974/) (2026)
- [Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning](https://mlsanity.com/paper/2606.21775/) (2026)
- [FF-JEPA: Long-Horizon Planning in World Models with Latent Planners](https://mlsanity.com/paper/2606.09311/) (2026)

## Built on by (most cited first, 7 of 7)

- [Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Models](https://mlsanity.com/paper/2607.23602/) (2026)
- [FIRM-WM: State-factorized factual-interventional recurrent modeling for reward-free visual planning](https://mlsanity.com/paper/2609.22816/) (2026)
- [Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think](https://mlsanity.com/paper/2609.30036/) (2026)
- [What Must a World Model Distinguish for Planning?](https://mlsanity.com/paper/2609.33030/) (2026)
- [Beyond a single latent space: a dual-latent world model for long-horizon planning](https://mlsanity.com/paper/2609.37644/) (2026)
- [Keeping JEPA World Models Plannable When Little of the Frame Moves](https://mlsanity.com/paper/2610.03137/) (2026)
- [How Long, Not How Close: A Learned Temporal Metric for Planning in Latent World Models](https://mlsanity.com/paper/2610.04988/) (2026)

## Abstract (arXiv)

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 SAGE, a prior-conditioned planner that replaces random proposal initialization with structured guidance. At each planning stage, a goal-conditioned generator predicts the next intermediate 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 these proposals against the same subgoal and guides their refinement 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 4.7% to 64.7% and OGBench Cube success from 20.7% to 67.3%. We further extend latent world-model planning to LIBERO, where SAGE improves full-episode success from 0% with the vanilla LeWM planner to 48.7% on Scene2 and 58% on Caddy.