This prestigious event brings together researchers, engineers, and industry professionals from around the world to explore the latest advancements in software testing, verification, and validation. During the conference, Diogo and Stevan showcased their research that push the boundaries of GUI test automation.
Dr. Stevan Tomic, AI/ML developer and researcher at Synteda, has conducted a study on PathFinder, accepted for ICST 2025, a Multi-Agent LLM framework designed to automate GUI testing. The research evaluates how different LLMs—Mistral-Nemo, Gemma2, and Llama3.1—impact test automation across e-commerce sites. Findings reveal that while a single LLM works best for specific platforms, a hybrid approach improves performance across diverse environments. This study underscores the critical role of LLM selection in AI-driven software testing.
Dr. Diogo Buarque, AI/ML developer and researcher at Synteda, to be published in ICST 2025, on a new study that explores how LLMs enhance GUI test automation by automatically labeling test states and improving reports. Integrated into the HiveMind tool, this approach reduces manual effort and improves readability. Experiments show that LLM-enhanced reports match expert-written ones, making testing faster and more efficient.
We specialize in developing smart systems that are designed to streamline workflows, reduce manual processes and boost productivity.
EyeAutomate is a powerful all-in-one solution for automating any application, on any platform, through intelligent image recognition and visual scripting.
HiveMind utilizes visual, scriptless, test modelling that reduces the cognitive load and the amount of required technical knowledge and skills to create automated test cases.
Manage your conference rooms, visitors and employees with Ingress our simple to use booking system. Ingress is an effective tool to organize meetings, allowing employees to view the availability of the rooms and book meeting spaces in minutes.
We want books to be used, not on the bookshelf. We want to give books life - many lives - and a story that can be explored and experienced.
We analyze your machine learning applications to ensure they comply with current laws and regulations, as well as being technically secure and reliable.
The aim of T.A.R.G.E.T. is to address these core challenges with GUI testing through innovation, realization and validation of demonstrators that incorporate state-of-the-art solutions in Augmented testing and generative AI.