用大模型驱动事件链生成汽车代码，提升准确性和实时性。
LLM-Empowered Event-Chain Driven Code Generation for ADAS in SDV systems
- 基于RAG从VSS库中检索信号，减少幻觉。
- 将信号转为带因果和时序约束的事件链。
- 无需重训大模型即可生成符合要求的代码。
本文提出一种事件链驱动、大语言模型赋能的工作流，从自然语言需求生成经验证的汽车代码。通过检索增强生成（RAG）层从大规模动态的车辆信号规范（VSS）目录中检索相关信号作为代码生成的上下文，降低幻觉并保证架构正确性。检索到的信号经映射与验证后转化为编码因果关系和时序约束的事件链，用以指导和约束基于大模型的代码合成，确保行为一致性和实时可行性。基于紧急制动案例的初步研究发现，采用该方法可实现有效信号使用与一致代码生成，且无需对大模型进行重新训练。
原文摘要 · Abstract (English)
This paper presents an event-chain-driven, LLM-empowered workflow for generating validated, automotive code from natural-language requirements. A Retrieval-Augmented Generation (RAG) layer retrieves relevant signals from large and evolving Vehicle Signal Specification (VSS) catalogs as code generation prompt context, reducing hallucinations and ensuring architectural correctness. Retrieved signals are mapped and validated before being transformed into event chains that encode causal and timing constraints. These event chains guide and constrain LLM-based code synthesis, ensuring behavioral consistency and real-time feasibility. Based on our initial findings from the emergency braking case study, with the proposed approach, we managed to achieve valid signal usage and consistent code generation without LLM retraining.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。