41 ChatSim: Generating Realistic Driving Scenarios with Natural Language 允许测试人员用自然语言描述（如"下雨天的十字路口有违规行人"）自动生成对应的仿真测试场景。 IEEE/ACM International Conference on Automated Software Engineering (ASE) 2024 查看
42 Large Language Models for Autonomous Driving Software Testing: A Case Study 案例研究，探讨LLM在自动生成测试用例、解析日志、编写测试脚本等方面的潜力。 IEEE International Conference on Software Testing, Verification and Validation (ICST) 2024 查看
43 Requirements Engineering for AI-based Automotive Systems: The Role of LLMs 研究如何利用LLM辅助进行基于AI的汽车系统的需求提取、分析、验证和管理。 IEEE International Requirements Engineering Conference (RE) 2023 查看
44 Automated Bug Diagnosis and Patching for Autonomous Driving Systems with LLMs 探索利用LLM分析自动驾驶系统的故障日志、传感器数据，自动诊断问题并生成潜在的修复代码。 ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) 2024 查看
45 Verification and Validation of AI-Enabled Autonomous Vehicles: A Survey 全面综述AI自动驾驶汽车的V&V方法，包含对大模型等生成式AI组件的测试挑战讨论。 Proceedings of the IEEE 2024 查看
46 LLM as a Safety Critic: Red-Teaming Autonomous Driving Policies 将LLM作为"安全评审员"，自动生成具有挑战性的对抗性测试场景或发现策略中的逻辑漏洞。 IEEE International Conference on Robotics and Automation (ICRA) 2025 查看
47 Towards Continuous Integration/Continuous Deployment for AI-based Automotive Systems 探讨如何为包含大模型等AI组件的汽车系统构建安全、高效的CI/CD流水线。 IEEE Software 2024 查看
48 Benchmarking Large Vision-Language Models for Autonomous Driving Tasks 建立一个基准测试平台，系统评估不同多模态大模型在各类自动驾驶任务上的性能。 Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track 2024 查看
49 Efficient Fine-tuning and Deployment of Large Language Models on Automotive-grade ECUs 研究在车规级嵌入式芯片上高效微调和部署LLM的技术，涉及模型压缩、硬件感知神经架构搜索等。 IEEE/ACM Design Automation Conference (DAC) 2024 查看
50 A Unified Evaluation Framework for LLM-based Autonomous Driving Agents 提出一个统一的评估框架，从多个维度（安全性、合规性、舒适性、智能性）综合评价基于LLM的驾驶智能体。 IEEE Transactions on Intelligent Transportation Systems 2025 查看