{"ID":2846623,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01423","arxiv_id":"2511.01423","title":"LLM-Assisted Tool for Joint Generation of Formulas and Functions in Rule-Based Verification of Map Transformations","abstract":"High-definition map transformations are essential in autonomous driving systems, enabling interoperability across tools. Ensuring their semantic correctness is challenging, since existing rule-based frameworks rely on manually written formulas and domain-specific functions, limiting scalability. In this paper, We present an LLM-assisted pipeline that jointly generates logical formulas and corresponding executable predicates within a computational FOL framework, extending the map verifier in CommonRoad scenario designer with elevation support. The pipeline leverages prompt-based LLM generation to produce grammar-compliant rules and predicates that integrate directly into the existing system. We implemented a prototype and evaluated it on synthetic bridge and slope scenarios. The results indicate reduced manual engineering effort while preserving correctness, demonstrating the feasibility of a scalable, semi-automated human-in-the-loop approach to map-transformation verification.","short_abstract":"High-definition map transformations are essential in autonomous driving systems, enabling interoperability across tools. Ensuring their semantic correctness is challenging, since existing rule-based frameworks rely on manually written formulas and domain-specific functions, limiting scalability. In this paper, We prese...","url_abs":"https://arxiv.org/abs/2511.01423","url_pdf":"https://arxiv.org/pdf/2511.01423v1","authors":"[\"Ruidi He\",\"Yu Zhang\",\"Meng Zhang\",\"Andreas Rausch\"]","published":"2025-11-03T10:19:52Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\"]","has_code":false}