@inproceedings{wang-etal-2026-multifiletest,
    title = "{M}ulti{F}ile{T}est: A Multi-File-Level {LLM} Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms",
    author = "Wang, Yibo  and
      Xia, Congying  and
      Zhao, Wenting  and
      Du, Jiangshu  and
      Miao, Chunyu  and
      Deng, Zhongfen  and
      Yu, Philip S.  and
      Xing, Chen",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1403/",
    pages = "28151--28172",
    ISBN = "979-8-89176-395-1",
    abstract = "Unit test generation has become a promising and important use case for Large Language Models (LLMs). However, existing evaluation benchmarks for LLM unit test generation primarily focus on function- or class-level code (single-file) rather than on more practical, challenging multi-file codebases.To address this limitation, we propose \textbf{MultiFileTest}, a multi-file-level benchmark for unit test generation covering Python, Java, and JavaScript. MultiFileTest features 20 high-quality, moderate-sized projects per language. We evaluate eleven frontier LLMs on MultiFileTest, and the results show that most tested LLMs exhibit moderate performance on MultiFileTest, highlighting the benchmark{'}s inherent difficulty.We also conduct a thorough error analysis, which shows that even advanced LLMs, such as Gemini 3.0 Pro, exhibit basic yet critical errors, including executability and cascade errors. Motivated by this observation, we further evaluate these frontier LLMs under manual error-fixing and self-error-fixing scenarios to assess their potential when equipped with error-fixing mechanisms.Our dataset is available at MultiFileTest."
}