[2603.28963] AutoWorld: Scaling Multi-Agent Traffic Simulation with Self-Supervised World Models

Computer Science > Robotics arXiv:2603.28963 (cs) [Submitted on 30 Mar 2026] Title:AutoWorld: Scaling Multi-Agent Traffic Simulation with Self-Supervised World Models Authors:Mozhgan Pourkeshavatz, Tianran Liu, Nicholas Rhinehart View a PDF of the paper titled AutoWorld: Scaling Multi-Agent Traffic Simulation with Self-Supervised World Models, by Mozhgan Pourkeshavatz and Tianran Liu and Nicholas Rhinehart View PDF HTML (experimental) Abstract:Multi-agent traffic simulation is central to developing and testing autonomous driving systems. Recent data-driven simulators have achieved promising results, but rely heavily on supervised learning from labeled trajectories or semantic annotations, making it costly to scale their performance. Meanwhile, large amounts of unlabeled sensor data can be collected at scale but remain largely unused by existing traffic simulation frameworks. This raises a key question: How can a method harness unlabeled data to improve traffic simulation performance? In this work, we propose AutoWorld, a traffic simulation framework that employs a world model learned from unlabeled occupancy representations of LiDAR data. Given world model samples, AutoWorld constructs a coarse-to-fine predictive scene context as input to a multi-agent motion generation model. To promote sample diversity, AutoWorld uses a cascaded Determinantal Point Process framework to guide the sampling processes of both the world model and the motion model. Furthermore, we designed a m...