标题： InfGen：场景生成作为下一个标记组预测 显示英文标题

标题： InfGen: Scenario Generation as Next Token Group Prediction

摘要： 真实且交互式的交通模拟对于训练和评估自动驾驶系统至关重要。 然而，大多数现有的数据驱动模拟方法依赖于静态初始化或日志回放数据，限制了它们对动态、长时程场景以及不断变化的智能体群体进行建模的能力。 我们提出了InfGen，一种场景生成框架，能够以自回归的方式输出智能体状态和轨迹。 InfGen将整个场景表示为一系列标记，包括交通信号灯信号、智能体状态和运动向量，并使用Transformer模型来模拟交通随时间的变化。 这种设计使InfGen能够持续地将新智能体插入交通中，支持无限场景生成。 实验表明，InfGen能够生成真实、多样且适应性强的交通行为。 此外，在InfGen生成的场景中训练的强化学习策略实现了更优的鲁棒性和泛化能力，验证了其作为自动驾驶高保真模拟环境的实用性。 更多信息请访问 https://metadriverse.github.io/infgen/。 显示英文摘要

摘要： Realistic and interactive traffic simulation is essential for training and evaluating autonomous driving systems. However, most existing data-driven simulation methods rely on static initialization or log-replay data, limiting their ability to model dynamic, long-horizon scenarios with evolving agent populations. We propose InfGen, a scenario generation framework that outputs agent states and trajectories in an autoregressive manner. InfGen represents the entire scene as a sequence of tokens, including traffic light signals, agent states, and motion vectors, and uses a transformer model to simulate traffic over time. This design enables InfGen to continuously insert new agents into traffic, supporting infinite scene generation. Experiments demonstrate that InfGen produces realistic, diverse, and adaptive traffic behaviors. Furthermore, reinforcement learning policies trained in InfGen-generated scenarios achieve superior robustness and generalization, validating its utility as a high-fidelity simulation environment for autonomous driving. More information is available at https://metadriverse.github.io/infgen/.