Adding project-dependency awareness and C++-specific knowledge to LLM prompts raises average compilation success from roughly 32% to 83% and more than doubles line and branch coverage across ten C++ projects.
Taming the Beast: Fully Automated Unit Testing with Coyote C++
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this paper, we present Coyote C++, a fully automated white-box unit testing tool for C and C++. Whereas existing tools have struggled to realize unit test generation for C++, Coyote C++ is able to produce high coverage results from unit test generation at a testing speed of over 10,000 statements per hour. This impressive feat is made possible by the combination of a powerful concolic execution engine with sophisticated automated test harness generation. Additionally, the GUI of Coyote C++ displays detailed code coverage visualizations and provides various configuration features for users seeking to manually optimize their coverage results. Combining potent one-click automated testing with rich support for manual tweaking, Coyote C++ is the first automated testing tool that is practical enough to make automated testing of C++ code truly viable in industrial applications.
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
CITYWALK: Enhancing LLM-Based C++ Unit Test Generation via Project-Dependency Awareness and Language-Specific Knowledge
Adding project-dependency awareness and C++-specific knowledge to LLM prompts raises average compilation success from roughly 32% to 83% and more than doubles line and branch coverage across ten C++ projects.