ASE Research Group

Better Software. Smarter AI.

How can AI transform the way we build software – and how can Software Engineering make AI more reliable? The TU Graz Applied Software Engineering & AI Research Group (ASE) explores both directions. We combine Large Language Models, AI Agents, Machine Learning, and Constraint Reasoning to address challenges in software and AI-based systems development.

This two-way exchange between Software Engineering and Artificial Intelligence is at the heart of Bilateral Software Engineering. Bilateral Software Engineering investigates the reciprocal integration of AI and Software Engineering: using AI to advance Software Engineering methods and processes, and using Software Engineering principles to develop, test, and maintain reliable AI systems.

Explore our publications · Discover our projects · Meet our team

Our Research

AI for Software Engineering

From understanding requirements to improving user experiences. We investigate how large language models and AI agents can support requirements elicitation, specification, prioritization, and quality assurance. Our research also explores Vibe Programming, Automated UI/UX Analysis and LLM-based Recommendation for improving software artefacts.

Intelligent Configuration and Reasoning

Making complex choices work together. Configuring a complex system means finding combinations that satisfy requirements and constraints. We combine symbolic reasoning with machine learning to improve configuration, identify conflicts, and efficiently explain how problems can be resolved (for example, on the basis of efficient diagnosis algorithms).

Recommender Systems and Decision Support

Helping people make informed choices. We develop methods that support individuals and groups in finding suitable options and understanding the consequences of their decisions. Our research examines how preferences, explanations, cognitive biases, and sustainability aspects influence decisions.

Software Engineering for AI

Bringing systematic engineering to intelligent systems. AI systems need clear requirements, meaningful evaluation, and effective quality assurance. We explore how software engineering methods can help develop, test, and improve AI-based systems and agent-supported development processes.

From Research to Practice

We translate research questions into methods, prototypes, and tools, working with academic and industry partners to investigate practical challenges.

Automated Usability Analysis with AI. We develop AI-assisted methods that analyse screen recordings of software systems to identify usability issues and recommend actionable improvements.

Automated Quality Assurance in Requirements Engineering. The rise of generative AI makes clear, consistent, and complete requirements increasingly important, including those expressed through LLM prompts. We develop intelligent techniques to assess and improve requirements quality, helping teams detect ambiguities, inconsistencies, and missing information early.

Automated Testing and Debugging of AI Systems. Testing and debugging AI-based systems requires substantial effort. We develop methods to automatically generate test cases, detect and analyse unintended behaviour, and support targeted repairs.

AI-based Learning and Knowledge Sharing. KnowledgeCheckR combines recommendation technologies and gamification to support personalized learning and knowledge sharing (with applications in medicine and public administration).

Connect with ASE

Research advances through collaboration. Whether you are exploring a scientific question, addressing an industry challenge, or looking for a student thesis topic, we welcome the opportunity to exchange ideas.

Meet our team · Discuss a collaboration· Explore thesis opportunities