Abstract
This study explores prompt engineering for automated white-box integration testing of RESTful APIs using Large Language Models (LLMs). Four versions of prompts were designed and tested across three OpenAI models (GPT-3.5 Turbo, GPT-4 Turbo, and GPT-4o) to assess their impact on code coverage, token consumption, execution time, and financial cost. The results indicate that different prompt versions, especially with more advanced models, achieved up to 90% coverage, although at higher costs. Additionally, combining test sets from different models increased coverage, reaching 96% in some cases. We also compared the results with EvoMaster, a specialized tool for generating tests for REST APIs, where LLM-generated tests achieved comparable or higher coverage in the benchmark projects. Despite higher execution costs, LLMs demonstrated superior adaptability and flexibility in test generation. © 2025 IEEE.

Abstract

Abstract
Recent verification tools aim to make formal verification more accessible for software engineers by automating most of the verification process. However, the manual work and expertise required to write verification helper code, such as loop invariants and auxiliary lemmas and assertions, remains a barrier. This paper explores the use of Large Language Models (LLMs) to automate the generation of loop invariants for programs in Dafny. We tested the approach on a curated dataset of 100 programs in Dafny involving arrays, strings, and numeric types. Using a multimodel approach that combines GPT-4o and Claude 3.5 Sonnet, correct loop invariants (passing the Dafny verifier) were generated at the first attempt for 92% of the programs, and in at most five attempts for 95% of the programs. Additionally, we developed an extension to the Dafny plugin for Visual Studio Code to incorporate automatic loop invariant generation into the IDE. Our work stands out from related approaches by handling a broader class of problems and offering IDE integration. © IFIP International Federation for Information Processing 2025.

Abstract

Abstract
Histology is a preclinical subject transversal in medical, dental, and veterinary curricula. Classical teaching approaches in histology are often undermined by lower motivation and engagement of students, which may be addressed by innovative learning environments. Herein, we developed a serious game approach and compared it with a classical teaching style. The students' feedback was evaluated by questionnaires, and their performance on quizzes and exam's scores were assessed. The serious game (Histopoly) consisted of a game-based web application for the teacher/game master, a digital gaming application used by the students as a controller, and a projected digital board game. The board featured rows for the four fundamental tissues (epithelial, connective, muscular, and nervous) paired with question tiles and additional tiles with more demanding activities (e.g., drawing, presenting slides, and making a syllabus). Participants included all veterinary students enrolled in the first year. Paired laboratory sessions were split with four sections (n = 94 students) playing Histopoly at the end of all sessions and two sections (n = 28 students) completing small evaluations every three weeks at the beginning of sessions. According to the questionnaires, students that played the serious game were more motivated, engaged, and more interconnected with classmates. The activity was considered fun, and students enjoyed the classes more. No differences in the final examination scores were found, but the percentage of correct answers provided throughout the serious game was significantly higher. Overall, these findings argue for the inclusion of serious games in modern histology teaching to promote student engagement in learning.

Abstract
The potential of Augmented Reality (AR) has been harnessed to create immersive game settings, present layers of relevant information in museums, streamline procedures in healthcare and industry, and captivate consumers through innovative marketing strategies. Certain artifacts lend themselves well to representation in AR, especially those requiring a seamless fusion of the information layer with physical space. This integration underscores the suitability of information design artifacts for AR implementation. This study aims to delineate the distinctive attributes of AR in remediating information design, effectively catering to the user's informational needs. To this end, we analyzed the Google Translate app, examining it through the analytical lens of body schema and haptic engagement. The findings reveal that AR manifests as a performative, personalized, crafted image that fosters involvement through agency. The performative nature of the image directs attention, while individual images collectively form a collection. It is recommended that AR design be centered around achieving harmony among body, media, and space.