{"ID":2838747,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17496","arxiv_id":"2511.17496","title":"MDG: Masked Denoising Generation for Multi-Agent Behavior Modeling in Traffic Environments","abstract":"Modeling realistic and interactive multi-agent behavior is critical to autonomous driving and traffic simulation. However, existing diffusion and autoregressive approaches are limited by iterative sampling, sequential decoding, or task-specific designs, which hinder efficiency and reuse. We propose Masked Denoising Generation (MDG), a unified generative framework that reformulates multi-agent behavior modeling as the reconstruction of independently noised spatiotemporal tensors. Instead of relying on diffusion time steps or discrete tokenization, MDG applies continuous, per-agent and per-timestep noise masks that enable localized denoising and controllable trajectory generation in a single or few forward passes. This mask-driven formulation generalizes across open-loop prediction, closed-loop simulation, motion planning, and conditional generation within one model. Trained on large-scale real-world driving datasets, MDG achieves competitive closed-loop performance on the Waymo Sim Agents and nuPlan Planning benchmarks, while providing efficient, consistent, and controllable open-loop multi-agent trajectory generation. These results position MDG as a simple yet versatile paradigm for multi-agent behavior modeling.","short_abstract":"Modeling realistic and interactive multi-agent behavior is critical to autonomous driving and traffic simulation. However, existing diffusion and autoregressive approaches are limited by iterative sampling, sequential decoding, or task-specific designs, which hinder efficiency and reuse. We propose Masked Denoising Gen...","url_abs":"https://arxiv.org/abs/2511.17496","url_pdf":"https://arxiv.org/pdf/2511.17496v1","authors":"[\"Zhiyu Huang\",\"Zewei Zhou\",\"Tianhui Cai\",\"Yun Zhang\",\"Jiaqi Ma\"]","published":"2025-11-21T18:53:11Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.MA\"]","methods":"[\"Diffusion Model\"]","has_code":false}