arXiv cs.AI· Elizaveta Zinovyeva, Aiham Taleb, Nikita Kozodoi, Daniel Schleicher, Amir Mahdi Namazi, Martin Kraus, Levent Kent, Brian Jensen·· 4 小时前AI 评分39
面向安全关键汽车软件的生成与验证：AUMOVIO 人机协作编码助手
Generation and Verification: Human-Agent Collaboration for Safety-Critical Automotive Software Engineering
AI 导读
AUMOVIO 推出面向汽车 C/C++ 的编码助手，通过 MCP 暴露 generate、edit、verify 三个工具，让开发者可随时验证任意代码，并基于生产代码数据集通过提示词工程与微调定制底层 LLM。两周试点中 verify 是开发者使用最多的工具，75% 更偏好更快的提示词工程配置；检查显示提示词工程在 C 上违规更少，微调在 C++ 架构模式上更符合规范。
正文 · 原文
Abstract:Research on coding agents mainly focuses on generation quality. Yet, safety-critical automotive software makes two additional demands. It prioritizes verification, since every change is reviewed, traced to a requirement, and checked against industry standards such as MISRA and AUTOSAR before it can be committed. It is also a narrow domain, written against layered architectures, embedded resource constraints, and organization-specific interface conventions that are scarce in the data general-purpose LLMs are trained on. We present a coding assistant for automotive C/C++ that addresses both demands. First, it exposes three tools to the user over the Model Context Protocol (generate, edit, and verify), allowing developers to run verify on any code on demand rather than relying on the agent to check its own output. Second, rather than using a general-purpose model, we customize the underlying LLM for the automotive domain through prompt engineering and fine-tuning. We construct a dataset from automotive production code of AUMOVIO, where each function is paired with the requirement texts and Unified Modeling Language (UML) behavior it must satisfy. In a two-week pilot on active production projects, developers report verify as the most-used tool and confirm using it on their own code and not only on generated output. Comparing model customization strategies, 75% prefer the faster prompt-engineered configuration. MISRA- and AUTOSAR-inspired pattern checkers indicate that prompt engineering achieves a lower number of violations on C, while fine-tuning shows better conformance with architecture patterns for C++.
| Comments: | Accepted to EMNLP 2026 REALM Workshop |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35982 [cs.SE] |
| (or arXiv:2610.35982v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35982 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Nikita Kozodoi [view email]
[v1]
Mon, 26 Oct 2026 11:04:55 UTC (124 KB)
来源：arXiv cs.AI · arxiv.org