4 papers
SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation
Sijia Gu, Noor Nashid, Ali Mesbah
While autonomous coding agents have significantly advanced automated test generation, they remain fundamentally limited by lazy generation, a phenomenon where agents prematurely te…
LLM Test Generation via Iterative Hybrid Program Analysis
Sijia Gu, Noor Nashid, Ali Mesbah
Automating unit test generation remains a significant challenge, particularly for complex methods in real-world projects. While Large Language Models (LLMs) have made strides in co…
Fine-Grained Assertion-Based Test Selection
Sijia Gu, Ali Mesbah
For large software applications, running the whole test suite after each code change is time- and resource-intensive. Regression test selection techniques aim at reducing test exec…
Scalable Similarity-Aware Test Suite Minimization with Reinforcement Learning
Sijia Gu, Ali Mesbah
The Multi-Criteria Test Suite Minimization (MCTSM) problem aims to remove redundant test cases, guided by adequacy criteria such as code coverage or fault detection capability. How…