Latent Chain-of-Thought World Modeling for End-to-End Driving

Latent-CoT-Drive (LCDrive) is a vision‑language‑action model for autonomous driving that replaces natural‑language chain‑of‑thought reasoning with a latent language capturing possible outcomes of driving actions. The model interleaves action‑proposal tokens, aligned with the model’s output actions, and world‑model tokens grounded in a learned latent world model to reason about future outcomes. After a supervised cold‑start using ground‑truth future rollouts, LCDrive is further refined with closed‑loop reinforcement learning, achieving faster inference, higher‑quality trajectories, and greater gains from interactive RL than both non‑reasoning and text‑reasoning baselines on a large‑scale end‑to‑end driving benchmark.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• agents
• diffusion
• reinforcement-learning
• robotics
• multimodal
• benchmarks
• safety