Learning Agent-Centric Vision-Language-Action World Models for Autonomous Driving
Organizations: MoE Key Lab of Artificial Intelligence, Institute of AI, Shanghai Jiao Tong University, Shanghai, China
Abstract
Recent progress in integrating vision-language-action (VLA) models with world modeling has significantly advanced end-to-end autonomous driving by allowing systems to reason about imagined futures instead of merely reacting to current observations. However, most world VLA models generate future frames at the pixel level with plenty of dense visual tokens. Although such generated futures can be visually plausible, they preserve many driving-irrelevant appearance details, i.e., only a small portion of the tokens directly encode critical planning-relevant factors, such as agent geometry, motion dynamics, and interactions. This introduces a significant performance bottleneck. An important question thus arises: what world state should a world VLA model reason over to support planning beyond pixel-level prediction? We argue that planning-oriented world modeling should focus on a compact and structured agent-centric latent state that captures the interactions between objects in the driving scene over time. As such, we introduce AgentWorld, an agent-centric VLA world model that uses discrete agent tokens jointly for reasoning and trajectory planning. Each token is dynamically grounded to a surrounding agent associated with its object's state, such as semantic identity, 3D geometry, motion, and interaction context. AgentWorld learns these tokens through three key processes: explicit geometric grounding, reasoning-oriented supervised fine-tuning, and agent-oriented reinforcement learning. Extensive open-loop and closed-loop experiments under diverse driving scenarios show that AgentWorld enhances planning capabilities, fully exploits visual evidence and agent dynamics, and yields interpretable agent-centric world states.
Figures & tables
| Method | ST-P3 metrics | UniAD metrics | VLM | ||||||||||||||
| L2 (m) | Collision (%) | L2 (m) | Collision (%) | ||||||||||||||
| 1s | 2s | 3s | Avg. | 1s | 2s | 3s | Avg. | 1s | 2s | 3s | Avg. | 1s | 2s | 3s | Avg. | ||
| ELM [ 94 ] | - | - | - | - | - | - | - | - | 0.34 | 1.23 | 2.57 | 1.38 | 0.12 | 0.50 | 2.36 | 0.99 | BLIP2-2.7B |
| FeD* [ 95 ] | - | - | - | - | - | - | - | - | 0.27 | 0.53 | 0.94 | 0.58 | 0.00 | 0.04 | 0.52 | 0.19 | LLaVA-7B |
| OccWorld [ 56 ] | 0.39 | 0.73 | 1.18 | 0.77 | 0.11 | 0.19 | 0.67 | 0.32 | 0.52 | 1.27 | 2.41 | 1.40 | 0.12 | 0.40 | 2.08 | 0.87 | GPT3-like |
| Doe-1 [ 55 ] | 0.37 | 0.67 | 1.07 | 0.70 | 0.02 | 0.14 | 0.47 | 0.21 | 0.50 | 1.18 | 2.11 | 1.26 | 0.04 | 0.37 | 1.19 | 0.53 | Lumina-mGPT-7B |
| Method | Driving Score | Success Rate (%) | Efficiency | Comfortness |
| AD-MLP [ 103 ] | 18.05 | 0.00 | 48.45 | 22.63 |
| UniAD-Base [ 18 ] | 45.81 | 16.36 | 129.21 | 43.58 |
| VAD [ 19 ] | 42.35 | 15.00 | 157.94 | 46.01 |
| TCP-traj [ 104 ] | 59.90 | 30.00 | 76.54 | 18.08 |
| DriveAdapter [ 105 ] | 64.22 | 33.08 | 70.22 | 16.01 |
| Orion [ 106 ] | 77.74 | 54.62 | 151.48 | 17.38 |
Appendix figures & tables6 assets
Supplementary material from the paper’s appendix.
Appendix
World Models for Autonomous Driving
World models for autonomous driving predict how scenes and traffic evolve under candidate actions to support planning, control, and simulation.
See all 167 papers