# Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think

arXiv: https://arxiv.org/abs/2609.30036 · HTML: https://mlsanity.com/paper/2609.30036/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 28 of its 37 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [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)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [OGBench: Benchmarking Offline Goal-Conditioned RL](https://mlsanity.com/paper/2410.20092/) (2024)
- [Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control](https://mlsanity.com/paper/1812.00568/) (2018)
- [Semi-parametric Topological Memory for Navigation](https://mlsanity.com/paper/1803.00653/) (2018)
- [Search on the Replay Buffer: Bridging Planning and Reinforcement Learning](https://mlsanity.com/paper/1906.05253/) (2019)
- [The Surprising Effectiveness of Representation Learning for Visual Imitation](https://mlsanity.com/paper/2112.01511/) (2021)
- [Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos](https://mlsanity.com/paper/2103.16817/) (2021)
- [Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models](https://mlsanity.com/paper/2502.14819/) (2025)
- [What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?](https://mlsanity.com/paper/2512.24497/) (2025)
- [Hierarchical Planning with Latent World Models](https://mlsanity.com/paper/2604.03208/) (2026)
- [SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning](https://mlsanity.com/paper/2607.17973/) (2026)
- [PALMER: Perception-Action Loop with Memory for Long-Horizon Planning](https://mlsanity.com/paper/2212.04581/) (2022)
- [Latent World Models with Monotone Planning Costs for Image-Goal Navigation](https://mlsanity.com/paper/2608.09073/) (2026)
- [IMWM: Intuition Models Complement World Models for Latent Planning](https://mlsanity.com/paper/2606.01626/) (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)
- [Zero-shot World Models via Search in Memory](https://mlsanity.com/paper/2510.16123/) (2025)

## Abstract (arXiv)

Latent world models plan toward goal images with a frozen pretrained predictor, without task rewards or extra trained heads. However, their planners struggle with long-range goals, and prior work addresses this by training extra components such as value functions or subgoal models. We show that the planning target itself can cause this failure: even with exact dynamics and globally optimal short-horizon search, scoring predictions by their distance to the final goal rejects the first steps of a route that initially moves away from the goal. Building on this insight, we propose Anchored Planning (AP), a training-free method that reuses the world model's own offline trajectories. AP retrieves a segment that leads from the current observation toward the goal and aims the frozen planner at an observation shortly after the segment's start. Across four diverse tasks, AP substantially improves frozen LeWM planners for both action synthesis and action ranking, and it outperforms both additional final-goal search and the LeWM planner on long-range goals.