6 papers
Improving Dynamic Specification Inference with LLM-Generated Counterexamples
AgustÃn Balestra, AgustÃn Nolasco, Facundo Molina +3
Contract assertions, such as preconditions, postconditions, and invariants, play a crucial role in software development, enabling applications such as program verification, test ge…
How well LLM-based test generation techniques perform with newer LLM versions?
Michael Konstantinou, Renzo Degiovanni, Mike Papadakis
The rapid evolution of Large Language Models (LLMs) has strongly impacted software engineering, leading to a growing number of studies on automated unit test generation. However, t…
Evaluating LLMs for One-Shot Patching of Real and Artificial Vulnerabilities
Aayush Garg, Zanis Ali Khan, Renzo Degiovanni +1
Automated vulnerability patching is crucial for software security, and recent advancements in Large Language Models (LLMs) present promising capabilities for automating this task.…
YATE: The Role of Test Repair in LLM-Based Unit Test Generation
Michael Konstantinou, Renzo Degiovanni, Jie M. Zhang +2
Recent advances in automated test generation utilises language models to produce unit tests. While effective, language models tend to generate many incorrect tests with respect to…
Bounded Synthesis of Synchronized Distributed Models from Lightweight Specifications
Pablo F. Castro, Luciano Putruele, Renzo Degiovanni +1
We present an approach to automatically synthesize synchronized models from lightweight formal specifications. Our approach takes as input a specification of a distributed system a…
Do LLMs generate test oracles that capture the actual or the expected program behaviour?
Michael Konstantinou, Renzo Degiovanni, Mike Papadakis
Software testing is an essential part of the software development cycle to improve the code quality. Typically, a unit test consists of a test prefix and a test oracle which captur…