面向汽车基于模型的系统工程的有状态多智能体大语言模型，用于跨视图接口对齐
Stateful Multi-Agent LLMs for Cross-View Interface Alignment in Automotive Model-Based Systems Engineering
AI总结：
针对LLMs在汽车MBSE中引发的架构漂移问题，提出有状态多智能体验证流水线，在ADAS场景中实现97%实体可追溯性等指标，证明对抗性审核可让LLMs可靠生成零错误MBSE架构。
AI中文摘要：
尽管大语言模型（LLMs）可加速软件定义车辆的基于模型的系统工程（MBSE），但其概率特性会引发“架构漂移”，在行为视图中生成缺乏结构基础的接口。为实现确定性接口对齐，我们提出一种有状态多智能体验证流水线，该框架采用顺序生成矩阵（类→活动→序列）和基于车辆信号规范（VSS）的检索增强生成（RAG），独立的AI验证智能体会依据严格错误分类动态审核输出，触发保留状态的回溯循环以解决不兼容问题。在高级驾驶辅助系统（ADAS）场景评估中，标准RAG的实体可追溯性为0%，而我们的多智能体工作流消除了跨阶段幻觉，实现97%的实体可追溯性、87%的信号保留率和85%的F1分数，证明对抗性审核可使LLMs可靠合成零错误MBSE架构。
英文摘要：
While Large Language Models (LLMs) can accelerate Model-Based Systems Engineering (MBSE) for software-defined vehicles, their probabilistic nature causes "architectural drift", fabricating interfaces in behavioral views that lack structural foundations. To enforce deterministic interface alignment, we propose a stateful, multi-agent validation pipeline. The framework utilizes a sequential generation matrix (Class->Activity->Sequence) and Vehicle Signal Specification (VSS)-grounded Retrieval-Augmented Generation (RAG). An independent AI Validator Agent dynamically audits outputs against a strict error taxonomy, triggering state-preserving backtracking loops to resolve incompatibilities. Evaluated on an Advanced Driver Assistance System (ADAS) scenario, standard RAG yielded 0% Entity Traceability. Conversely, our multi-agent workflow eradicated cross-phase hallucinations, achieving 97% Entity Traceability, 87% Signal Conservation, and an 85% F1-score. This proves adversarial auditing enables LLMs to reliably synthesize zero-error MBSE architectures.
