Testing is an essential part of software development. Test generation tools attempt to automate the otherwise labor-intensive task of test creation, but generating high-coverage tests remains a challenge. This paper proposes CoverUp, a novel approach to driving the generation of high-coverage Python regression tests. CoverUp iteratively improves test coverage, interleaving coverage analysis with dialogs with the LLM that steer it to refine tests so that they increase coverage of lines and branches. We evaluate our prototype CoverUp implementation across a benchmark of challenging code derived from open-source Python projects, and show that CoverUp substantially improves on the state of the art. Compared to CodaMosa, a hybrid search/LLM-based test generator, CoverUp achieves a per-module median line+branch coverage of 80% (vs. 47%). Compared to MuTAP, a mutation/LLM-based test generator, CoverUp achieves an overall line+branch coverage of 90% (vs. 77%). We show that CoverUp’s iterative, coverage-guided approach is crucial to its effectiveness, contributing to nearly 40% of its successes.
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.