LSPAI: An IDE Plugin for LLM-Powered Multi-Language Unit Test Generation with Language Server Protocol
Unit testing is crucial to ensure the validity of the code, and research has been conducted to advance this domain. However, existing studies fail to address industry requirements, support for multi-language static analysis and real-time unit test generation. While integrating static analysis with a Large Language Model (LLM) could address these challenges, it typically requires effort to implement across programming languages. To address this, we propose LspAi, an automated unit test generation tool that leverages language analysis tools and integrates them into a unified development environment via the Language Server Protocol. This approach equips LLM with multi-language static analysis capabilities, allowing a single tool to support unit test generation across multiple languages. We evaluated our method by comparing line coverage across different LLMs and programming languages, demonstrating superior performance and broad applicability. In projects, LspAi achieved line coverage improvements of 145% for Java, 931% for Golang, and 95.62% for Python compared to Copilot. In addition, we also share our lessons learned from applying the tool in Tencent Ltd.
Mon 23 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
10:30 - 12:30 | Test GenerationResearch Papers / Industry Papers at Cosmos Hall Chair(s): Michael Pradel University of Stuttgart | ||
10:30 20mTalk | CoverUp: Effective High Coverage Test Generation for Python Research Papers Juan Altmayer Pizzorno University of Massachusetts Amherst, Emery D. Berger University of Massachusetts Amherst and Amazon Web Services DOI Pre-print | ||
11:00 20mTalk | Doc2OracLL: Investigating the Impact of Documentation on LLM-based Test Oracle Generation Research Papers Soneya Binta Hossain University of Virginia, Raygan Taylor Dillard University, Matthew B Dwyer University of Virginia DOI | ||
11:20 20mTalk | Less is More: On the Importance of Data Quality for Unit Test Generation Research Papers Junwei Zhang Zhejiang University, Xing Hu Zhejiang University, Shan Gao Huawei, Xin Xia Zhejiang University, David Lo Singapore Management University, Shanping Li Zhejiang University DOI | ||
11:40 20mTalk | Mutation-Guided LLM-based Test Generation at Meta Industry Papers Mark Harman Meta Platforms, Inc. and UCL, Jillian Ritchey Meta platforms, Inna Harper Meta, Shubho Sengupta Meta platforms, Ke Mao Meta, Abhishek Gulati Meta platforms, Christopher Foster Meta platforms, Hervé Robert Meta platforms | ||
12:00 10mTalk | LSPAI: An IDE Plugin for LLM-Powered Multi-Language Unit Test Generation with Language Server Protocol Industry Papers Gwihwan Go Tsinghua University, Chijin Zhou Tsinghua University, Quan Zhang Tsinghua University, Yu Jiang Tsinghua University, Zhao Wei Tencent | ||
12:10 20mTalk | Can Generative AI Produce Test Cases? An Experience from the Automotive Domain Industry Papers Stephen Wynn-Williams McMaster University, Canada, Ryan Tyrrell McMaster University, Vera Pantelic McMaster University, Mark Lawford McMaster University, Claudio Menghi University of Bergamo; McMaster University, Phaneendra Nalla FCA US LLC, Hassan Artail FCA US LLC | ||
This is the main event hall of Clarion Hotel, which will be used to host keynote talks and other plenary sessions. The FSE and ISSTA banquets will also happen in this room.
The room is just in front of the registration desk, on the other side of the main conference area. The large doors with numbers “1” and “2” provide access to the Cosmos Hall.