# WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving

arXiv: https://arxiv.org/abs/2512.19133 · HTML: https://mlsanity.com/paper/2512.19133/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in World models for autonomous driving, one of 11 directions in World models.
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 22 Dec 2025.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/)
- End-to-end autonomous driving / [Generative simulation for driving](https://mlsanity.com/driving/generative-simulation-for-driving/)

## Builds on (most cited first, 22 of 22)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021)
- [ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning](https://mlsanity.com/paper/2207.07601/) (2022)
- [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](https://mlsanity.com/paper/2406.15349/) (2024)
- [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024)
- [Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation](https://mlsanity.com/paper/2406.06978/) (2024)
- [SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation](https://mlsanity.com/paper/2405.19620/) (2024)
- [Enhancing End-to-End Autonomous Driving with Latent World Model](https://mlsanity.com/paper/2406.08481/) (2024)
- [DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation](https://mlsanity.com/paper/2410.13571/) (2024)
- [Epona: Autoregressive Diffusion World Model for Autonomous Driving](https://mlsanity.com/paper/2506.24113/) (2025)
- [AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning](https://mlsanity.com/paper/2503.07608/) (2025)
- [DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving](https://mlsanity.com/paper/2405.04390/) (2024)
- [DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model](https://mlsanity.com/paper/2410.10429/) (2024)
- [Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving](https://mlsanity.com/paper/2502.07309/) (2025)
- [DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving](https://mlsanity.com/paper/2505.19239/) (2025)
- [UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty](https://mlsanity.com/paper/2504.12826/) (2025)
- [Dream to Drive with Predictive Individual World Model](https://mlsanity.com/paper/2501.16733/) (2025)
- [OccTENS: 3D Occupancy World Model via Temporal Next-Scale Prediction](https://mlsanity.com/paper/2509.03887/) (2025)

## Built on by (most cited first, 20 of 20)

- [Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving](https://mlsanity.com/paper/2603.24581/) (2026)
- [DriveFuture: Future-Aware Latent World Models for Autonomous Driving](https://mlsanity.com/paper/2605.09701/) (2026)
- [DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving](https://mlsanity.com/paper/2603.24587/) (2026)
- [Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation](https://mlsanity.com/paper/2603.14948/) (2026)
- [Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation](https://mlsanity.com/paper/2606.15869/) (2026)
- [SimWAM: A Simple World Action Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2608.07468/) (2026)
- [Learning from Mistakes: Post-Training for Driving VLA with Takeover Data](https://mlsanity.com/paper/2603.14972/) (2026)
- [RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework](https://mlsanity.com/paper/2604.15308/) (2026)
- [Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives](https://mlsanity.com/paper/2605.19771/) (2026)
- [GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving](https://mlsanity.com/paper/2606.16274/) (2026)
- [Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challenges](https://mlsanity.com/paper/2603.09086/) (2026)
- [DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving](https://mlsanity.com/paper/2603.19675/) (2026)
- [PerlAD: Towards Enhanced Closed-loop End-to-end Autonomous Driving with Pseudo-simulation-based Reinforcement Learning](https://mlsanity.com/paper/2603.14908/) (2026)
- [From Digital Twins to World Models:Opportunities, Challenges, and Applications for Mobile Edge General Intelligence](https://mlsanity.com/paper/2603.17420/) (2026)
- [Towards Viewpoint-Robust End-to-End Autonomous Driving with 3D Foundation Model Priors](https://mlsanity.com/paper/2604.00597/) (2026)
- [ConsistencyPlanner: Real-time Planning with Fast-Sampling Consistency Models](https://mlsanity.com/paper/2606.11569/) (2026)
- [A Stitch in Time Saves Nine: Preserving Policy Compatibility Under Perception Updates in End-to-End Autonomous Driving](https://mlsanity.com/paper/2606.21509/) (2026)
- [WALT: Learning World-Model-Aligned Latent Trajectories for Autonomous Driving](https://mlsanity.com/paper/2609.30436/) (2026)
- [A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform](https://mlsanity.com/paper/2610.00926/) (2026)
- [MORE: Learning Motion-Oriented Registers for Driving World Models and Planning](https://mlsanity.com/paper/2610.14871/) (2026)

## Abstract (arXiv)

Latent World Models enhance scene representation through temporal self-supervised learning, presenting a perception annotation-free paradigm for end-to-end autonomous driving. However, the reconstruction-oriented representation learning tangles perception with planning tasks, leading to suboptimal optimization for planning. To address this challenge, we propose WorldRFT, a planning-oriented latent world model framework that aligns scene representation learning with planning via a hierarchical planning decomposition and local-aware interactive refinement mechanism, augmented by reinforcement learning fine-tuning (RFT) to enhance safety-critical policy performance. Specifically, WorldRFT integrates a vision-geometry foundation model to improve 3D spatial awareness, employs hierarchical planning task decomposition to guide representation optimization, and utilizes local-aware iterative refinement to derive a planning-oriented driving policy. Furthermore, we introduce Group Relative Policy Optimization (GRPO), which applies trajectory Gaussianization and collision-aware rewards to fine-tune the driving policy, yielding systematic improvements in safety. WorldRFT achieves state-of-the-art (SOTA) performance on both open-loop nuScenes and closed-loop NavSim benchmarks. On nuScenes, it reduces collision rates by 83% (0.30% -> 0.05%). On NavSim, using camera-only sensors input, it attains competitive performance with the LiDAR-based SOTA method DiffusionDrive (87.8 vs. 88.1 PDMS).