# MR-Coupler: Automated Metamorphic Test Generation via Functional Coupling Analysis

arXiv: https://arxiv.org/abs/2604.10126 · HTML: https://mlsanity.com/paper/2604.10126/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 79 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation](https://mlsanity.com/paper/2302.06527/) (2023)
- [Chain of Code: Reasoning with a Language Model-Augmented Code Emulator](https://mlsanity.com/paper/2312.04474/) (2023)
- [ChatUniTest: A Framework for LLM-Based Test Generation](https://mlsanity.com/paper/2305.04764/) (2023)
- [LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation](https://mlsanity.com/paper/2409.20550/) (2024)
- [Exploring and Unleashing the Power of Large Language Models in Automated Code Translation](https://mlsanity.com/paper/2404.14646/) (2024)
- [CoverUp: Effective High Coverage Test Generation for Python](https://mlsanity.com/paper/2403.16218/) (2024)
- [ChatGPT vs SBST: A Comparative Assessment of Unit Test Suite Generation](https://mlsanity.com/paper/2307.00588/) (2023)
- [The Future of AI-Driven Software Engineering](https://mlsanity.com/paper/2406.07737/) (2024)
- [Concerned with Data Contamination? Assessing Countermeasures in Code Language Model](https://mlsanity.com/paper/2403.16898/) (2024)
- [An Empirical Study of Usages, Updates and Risks of Third-Party Libraries in Java Projects](https://mlsanity.com/paper/2002.11028/) (2020)
- [Neural-Based Test Oracle Generation: A Large-scale Evaluation and Lessons Learned](https://mlsanity.com/paper/2307.16023/) (2023)
- [LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops](https://mlsanity.com/paper/2603.23613/) (2026)
- [Fuzzing Deep Learning Compilers with HirGen](https://mlsanity.com/paper/2208.02193/) (2022)
- [Towards Generating Executable Metamorphic Relations Using Large Language Models](https://mlsanity.com/paper/2401.17019/) (2024)
- [Can ChatGPT advance software testing intelligence? An experience report on metamorphic testing](https://mlsanity.com/paper/2310.19204/) (2023)
- [MR-Adopt: Automatic Deduction of Input Transformation Function for Metamorphic Testing](https://mlsanity.com/paper/2408.15815/) (2024)
- [SemMT: A Semantic-based Testing Approach for Machine Translation Systems](https://mlsanity.com/paper/2012.01815/) (2020)
- [MR-Scout: Automated Synthesis of Metamorphic Relations from Existing Test Cases](https://mlsanity.com/paper/2304.07548/) (2023)
- [Word Closure-Based Metamorphic Testing for Machine Translation](https://mlsanity.com/paper/2312.12056/) (2023)
- [GenMorph: Automatically Generating Metamorphic Relations via Genetic Programming](https://mlsanity.com/paper/2312.15302/) (2023)
- [Understanding LLM-Driven Test Oracle Generation](https://mlsanity.com/paper/2601.05542/) (2026)
- [LLMORPH: Automated Metamorphic Testing of Large Language Models](https://mlsanity.com/paper/2603.23611/) (2026)

## Built on by (most cited first, 1 of 1)

- [Multi-Large Language Model Orchestrated Severity Assessment of Clinical Records (MOSAIC)](https://mlsanity.com/paper/2607.05032/) (2026)

## Abstract (arXiv)

Metamorphic testing (MT) is a widely recognized technique for alleviating the oracle problem in software testing. However, its adoption is hindered by the difficulty of constructing effective metamorphic relations (MRs), which often require domain-specific or hard-to-obtain knowledge. In this work, we propose a novel approach that leverages the functional coupling between methods, which is readily available in source code, to automatically construct MRs and generate metamorphic test cases (MTCs). Our technique, MR-Coupler, identifies functionally coupled method pairs, employs large language models to generate candidate MTCs, and validates them through test amplification and mutation analysis. In particular, we leverage three functional coupling features to avoid expensive enumeration of possible method pairs, and a novel validation mechanism to reduce false alarms. Our evaluation of MR-Coupler on 100 human-written MTCs and 50 real-world bugs shows that it generates valid MTCs for over 90% of tasks, improves valid MTC generation by 64.90%, and reduces false alarms by 36.56% compared to baselines. Furthermore, the MTCs generated by MR-Coupler detect 44% of the real bugs. Our results highlight the effectiveness of leveraging functional coupling for automated MR construction and the potential of MR-Coupler to facilitate the adoption of MT in practice. We also released the tool and experimental data to support future research.