{"ID":5937708,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-08T14:15:37.741338847Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04331","arxiv_id":"2607.04331","title":"Agent-driven Long-tail Simulation for Autonomous Driving","abstract":"Evaluating autonomous driving systems in closed-loop settings requires realistic and interactive simulation, yet existing simulators largely rely on log replay or rule-based agents, limiting behavioral diversity and long-tail coverage. We propose an agent-driven simulation framework in which surrounding road participants are controlled by instruction-following large language models through a structured action interface, enabling intentional and reactive behaviors while preserving physical plausibility. Furthermore, we introduce SemanticPlan, a benchmark of closed-loop planning in long-tail and semantically rich scenarios that augment real nuPlan scenes with multiple interactive agents following diverse language instructions. Evaluation results show that state-of-the-art planners still struggle to consistently achieve safe and effective task completion, suggesting that these long-tail scenarios remain challenging.","short_abstract":"Evaluating autonomous driving systems in closed-loop settings requires realistic and interactive simulation, yet existing simulators largely rely on log replay or rule-based agents, limiting behavioral diversity and long-tail coverage. We propose an agent-driven simulation framework in which surrounding road participan...","url_abs":"https://arxiv.org/abs/2607.04331","url_pdf":"https://arxiv.org/pdf/2607.04331v1","authors":"[\"Junru Gu\",\"Lijin Yang\",\"Jianing Huang\",\"Shu Liu\",\"Zhongzhan Huang\",\"Hang Zhao\"]","published":"2026-07-05T14:27:47Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}