{"ID":2851652,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.19438","arxiv_id":"2510.19438","title":"AutoMT: A Multi-Agent LLM Framework for Automated Metamorphic Testing of Autonomous Driving Systems","abstract":"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.","short_abstract":"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 autom...","url_abs":"https://arxiv.org/abs/2510.19438","url_pdf":"https://arxiv.org/pdf/2510.19438v1","authors":"[\"Linfeng Liang\",\"Chenkai Tan\",\"Yao Deng\",\"Yingfeng Cai\",\"T. Y Chen\",\"Xi Zheng\"]","published":"2025-10-22T10:11:05Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}