Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2504.11243 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917986275688448 |
|---|---|
| author | Balu, Balahari Vignesh Geissler, Florian Carella, Francesco Zacchi, Joao-Vitor Jiru, Josef Mata, Nuria Stolle, Reinhard |
| author_facet | Balu, Balahari Vignesh Geissler, Florian Carella, Francesco Zacchi, Joao-Vitor Jiru, Josef Mata, Nuria Stolle, Reinhard |
| contents | We study the automated derivation of safety requirements in a self-driving vehicle use case, leveraging LLMs in combination with agent-based retrieval-augmented generation. Conventional approaches that utilise pre-trained LLMs to assist in safety analyses typically lack domain-specific knowledge. Existing RAG approaches address this issue, yet their performance deteriorates when handling complex queries and it becomes increasingly harder to retrieve the most relevant information. This is particularly relevant for safety-relevant applications. In this paper, we propose the use of agent-based RAG to derive safety requirements and show that the retrieved information is more relevant to the queries. We implement an agent-based approach on a document pool of automotive standards and the Apollo case study, as a representative example of an automated driving perception system. Our solution is tested on a data set of safety requirement questions and answers, extracted from the Apollo data. Evaluating a set of selected RAG metrics, we present and discuss advantages of a agent-based approach compared to default RAG methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11243 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Automated Safety Requirements Derivation Using Agent-based RAG Balu, Balahari Vignesh Geissler, Florian Carella, Francesco Zacchi, Joao-Vitor Jiru, Josef Mata, Nuria Stolle, Reinhard Artificial Intelligence Computation and Language Machine Learning We study the automated derivation of safety requirements in a self-driving vehicle use case, leveraging LLMs in combination with agent-based retrieval-augmented generation. Conventional approaches that utilise pre-trained LLMs to assist in safety analyses typically lack domain-specific knowledge. Existing RAG approaches address this issue, yet their performance deteriorates when handling complex queries and it becomes increasingly harder to retrieve the most relevant information. This is particularly relevant for safety-relevant applications. In this paper, we propose the use of agent-based RAG to derive safety requirements and show that the retrieved information is more relevant to the queries. We implement an agent-based approach on a document pool of automotive standards and the Apollo case study, as a representative example of an automated driving perception system. Our solution is tested on a data set of safety requirement questions and answers, extracted from the Apollo data. Evaluating a set of selected RAG metrics, we present and discuss advantages of a agent-based approach compared to default RAG methods. |
| title | Towards Automated Safety Requirements Derivation Using Agent-based RAG |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2504.11243 |