Publications

IEEE - ICST 2026

How well LLM-based test generation techniques perform with newer LLM versions?

Screenshot 2026-02-20 at 13-11-20 How well LLM-based test generation techniques perform with newer LLM versions - 2601.09695v1.pdf
Authors: Michael Konstantinou, Renzo Degiovanni, Mike Papadakis
Abstract:

This study shows that modern LLMs using a simple test-generation approach can outperform more complex state-of-the-art techniques in code coverage and fault detection while maintaining comparable or lower costs.

Read more :  Link

ArXiv

On the risk of coding before testing: An empirical study on LLM-based test generation workflow

Screenshot 2026-09-14 at 11-06-48 On the risk of coding before testing An empirical study on LLM-based test generation workflow - 2607.05139v1.pdf
Authors: Michael Konstantinou, Florian Tambon, Mike Papadakis
Abstract:

The paper investigates error propagation in LLM-based software development, where mistakes in LLM-generated code can bias subsequently generated tests, causing both the implementation and tests to agree on incorrect behavior. Experiments show that tests generated after faulty code detect significantly fewer defects than independently generated tests (14% vs. 25%), and the problem persists across different prompting strategies and multi-step agentic workflows.

Read more :  Link

ArXiv

YATE: The Role of Test Repair in LLM-Based Unit Test Generation

box_plot_line_branch_gnu
Authors: Michael Konstantinou, Renzo Degiovanni, Jie M. Zhang, Mark Harman, Mike Papadakis
Abstract:

This study introduces YATE, a technique that repairs incorrect LLM-generated unit tests using static analysis and re-prompting, significantly improving code coverage and fault detection over existing LLM-based testing methods.

Read more :  Link

ArXiv

Do LLMs generate test oracles that capture the actual or the expected program behaviour?

diff_actual_wrong
Authors: Michael Konstantinou, Renzo Degiovanni, Mike Papadakis
Abstract:

This study evaluates LLMs for software test oracle generation and finds that, despite often capturing actual rather than expected behavior, LLM-generated oracles can outperform traditional tools like EvoSuite in fault detection.

Read more :  Link

Integrative Zoology, January 2025.

A Novel Multidisciplinary Approach for Reptile Movement and Behavior Analysis

inz212960-fig-0004-m
Authors: Savvas Zotos, Marilena Stamatiou, Sofia-Zacharenia Marketaki, Michael Konstantinou, Andreas Aristidou, Duncan J. Irschick, Jeremy A. Bot, Emily L. C. Shepard, Mark D. Holton, Ioannis N. Vogiatzakis
Abstract:

This study presents a multidisciplinary approach combining accelerometers, video, motion capture, 3D reconstruction, and behavioral databases to accurately record, visualize, and analyze complex behaviors in small reptiles.

Read more :  Link

IEEE Computer Graphics and Applications, May 2022

Digitizing Wildlife: The case of reptiles 3D virtual museum

ReptilesVR___preview_600_450
Authors: Savvas Zotos, Marilena Lemonari, Michael Konstantinou, Anastasios Yiannakidis, Georgios Pappas, Panayiotis Kyriakou, Ioannis N. Vogiatzakis, Andreas Aristidou.
Abstract:

The paper presents an interactive 3D virtual museum that uses realistic reptile models, motion-captured behaviors, and VR/AR technologies to support wildlife education, research, and preservation.

Read more :  Link