AutoMT: A Multi-Agent LLM Framework for Automated Metamorphic Testing of Autonomous Driving Systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liang, Linfeng, Tan, Chenkai, Deng, Yao, Cai, Yingfeng, Chen, T. Y, Zheng, Xi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908605981130752
author Liang, Linfeng
Tan, Chenkai
Deng, Yao
Cai, Yingfeng
Chen, T. Y
Zheng, Xi
author_facet Liang, Linfeng
Tan, Chenkai
Deng, Yao
Cai, Yingfeng
Chen, T. Y
Zheng, Xi
contents Autonomous Driving Systems (ADS) are safety-critical, where failures can be severe. While Metamorphic Testing (MT) is effective for fault detection in ADS, existing methods rely heavily on manual effort and lack automation. We present AutoMT, a multi-agent MT framework powered by Large Language Models (LLMs) that automates the extraction of Metamorphic Relations (MRs) from local traffic rules and the generation of valid follow-up test cases. AutoMT leverages LLMs to extract MRs from traffic rules in Gherkin syntax using a predefined ontology. A vision-language agent analyzes scenarios, and a search agent retrieves suitable MRs from a RAG-based database to generate follow-up cases via computer vision. Experiments show that AutoMT achieves up to 5 x higher test diversity in follow-up case generation compared to the best baseline (manual expert-defined MRs) in terms of validation rate, and detects up to 20.55% more behavioral violations. While manual MT relies on a fixed set of predefined rules, AutoMT automatically extracts diverse metamorphic relations that augment real-world datasets and help uncover corner cases often missed during in-field testing and data collection. Its modular architecture separating MR extraction, filtering, and test generation supports integration into industrial pipelines and potentially enables simulation-based testing to systematically cover underrepresented or safety-critical scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19438
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AutoMT: A Multi-Agent LLM Framework for Automated Metamorphic Testing of Autonomous Driving Systems
Liang, Linfeng
Tan, Chenkai
Deng, Yao
Cai, Yingfeng
Chen, T. Y
Zheng, Xi
Software Engineering
Autonomous Driving Systems (ADS) are safety-critical, where failures can be severe. While Metamorphic Testing (MT) is effective for fault detection in ADS, existing methods rely heavily on manual effort and lack automation. We present AutoMT, a multi-agent MT framework powered by Large Language Models (LLMs) that automates the extraction of Metamorphic Relations (MRs) from local traffic rules and the generation of valid follow-up test cases. AutoMT leverages LLMs to extract MRs from traffic rules in Gherkin syntax using a predefined ontology. A vision-language agent analyzes scenarios, and a search agent retrieves suitable MRs from a RAG-based database to generate follow-up cases via computer vision. Experiments show that AutoMT achieves up to 5 x higher test diversity in follow-up case generation compared to the best baseline (manual expert-defined MRs) in terms of validation rate, and detects up to 20.55% more behavioral violations. While manual MT relies on a fixed set of predefined rules, AutoMT automatically extracts diverse metamorphic relations that augment real-world datasets and help uncover corner cases often missed during in-field testing and data collection. Its modular architecture separating MR extraction, filtering, and test generation supports integration into industrial pipelines and potentially enables simulation-based testing to systematically cover underrepresented or safety-critical scenarios.
title AutoMT: A Multi-Agent LLM Framework for Automated Metamorphic Testing of Autonomous Driving Systems
topic Software Engineering
url https://arxiv.org/abs/2510.19438