The AI4SE Lab centers its research on the theme of the development of new AI techniques to support software development, including large language models for coding.
To drive these advancements, the lab leverages key technical AI components, focusing primarily on:
With a commitment to explainable AI.
The AI4SE Lab is dedicated to bridging the gap between advanced AI research and software engineering practice.
The lab’s mission and vision are to build the fundamental knowledge base, technological tools, and human capacities necessary to transition to a new generation of software development tools and environments supported and enhanced by generative AI and LLMs.
The impact of the lab lies in boosting software developer productivity and strengthening software engineering processes, achieved by validating breakthroughs directly within real-world developer tools alongside industrial partners, advancing programming education, and embedding explainable AI frameworks to build trust across the software development ecosystem.
Interactive & aligned integrated development environments – Focuses on designing developer environments (IDEs) that seamlessly integrate AI capabilities while staying aligned with developer intent and workflows.
Intelligent teaching assistant in programming education – Focuses on leveraging AI and language models to create intelligent tutoring tools that support students and educators in learning programming.
Code generation for validation and code validation through generation – Focuses on using generative AI models to automatically produce software test cases and using code validation techniques to verify generated code.
Utilizing runtime information to improve development processes – Focuses on analyzing execution and runtime data to inform and enhance AI-driven recommendations during the software development lifecycle.
Large language model adaptation and optimization – Focuses on customizing, fine-tuning, and optimizing Large Language Models specifically for code-related tasks and developer tools.
Developer Interaction Patterns with Proactive AI: A Five-Day Field Study Proceedings Article
In: Proceedings of the Annual ACM Conference on Intelligent User Interfaces (IUI), 2026.
Human-AI experience in integrated development environments: a systematic literature review Journal Article
In: Empirical Software Engineering, vol. 31, no. 3, pp. 55, 2026.
AgentGuard: Runtime Verification of AI Agents Proceedings Article
In: Proceedings of the First International Workshop on Autonomous Agents in Software Engineering (AgenticSE Workshop), 2025.
Prompt-with-Me: in-IDE Structured Prompt Management for LLM-Driven Software Engineering Proceedings Article
In: Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE 2025 - Industry Track), 2025.
Developer Needs and Feasible Features for AI Assistants in IDEs Proceedings Article
In: Proceedings of the IEEE/ACM International Conference on Software Engineering (ICSE 2026 - SEIP), 2025.
TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs Proceedings Article
In: Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE 2025 - Industry Track), 2025.
Metamorphic Testing of Deep Code Models: A Systematic Literature Review Journal Article
In: ACM Transactions on Software Engineering and Methodology (TOSEM), 2025.
Multimodal Analogy Generation in Programming Education Proceedings Article
In: Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education Vol. 2 (ITiCSE 2025), 2025.
Designing and Evaluating AI-Generated Multimodal Analogy-Based Explanations Proceedings Article
In: Proceedings of the 26th International Conference on Artificial Intelligence in Education (AIED 2025 - Doctoral Consortium), 2025.
Improving the Comprehensibility of Generated Test Suites Using Test Case Clustering Proceedings Article
In: Proceedings of the 18th IEEE International Conference on Software Testing, Verification and Validation (ICST 2025 - Short Papers, Vision and Emerging Results Track), 2025.
Test Wars: A Comparative Study of SBST, Symbolic Execution, and LLM-Based Approaches to Unit Test Generation Proceedings Article
In: Proceedings of the 18th IEEE International Conference on Software Testing, Verification and Validation (ICST 2025 - Research Papers Track), 2025.
When People Come First, A Human-Centered Approach to Computer Science Education Proceedings Article
In: Proceedings of the ACM Conference on Innovation and Technology in Computer Science Education (ITiCSE 2025 - Panel Contribution), 2025.
Enhancing Human-IDE Interaction in the SDLC using LLM-based Mediator Agents Proceedings Article
In: Proceedings of the 1st International Workshop on AI-Augmented SDLC (AI-SDLC Workshop), 2025.
Mediating between Human Programmers and Integrated Development Environments using LLM-based Agents Proceedings Article
In: Proceedings of the 2025 ACM International Conference on the Foundations of Software Engineering (FSE 2025 - Doctoral Symposium), 2025.
Enhancing Large Language Model Integration in Integrated Development Environments Proceedings Article
In: Proceedings of the ACM International Conference on the Foundations of Software Engineering (FSE 2025 - Doctoral Symposium), 2025.
HyperSeq: A Hyper-Adaptive Representation for Predictive Sequencing of States Proceedings Article
In: Proceedings of the ACM International Conference on the Foundations of Software Engineering (FSE 2025 - Ideas, Visions and Reflections), 2025.
A Multi-agent Onboarding Assistant based on Large Language Models, Retrieval Augmented Generation, and Chain-of-Thought Proceedings Article
In: Proceedings of the ACM International Conference on the Foundations of Software Engineering (FSE 2025 - Demonstration), 2025.
Metamorphic-Based Many-Objective Distillation of LLMs for Code-related Tasks Proceedings Article
In: Proceedings of the 47th IEEE/ACM International Conference on Software Engineering (ICSE 2025 - Research Track), 2025.
Rethinking IDE Customization for Enhanced HAX: A Hyperdimensional Perspective Proceedings Article
In: Proceedings of the 2nd Workshop on Integrated Development Environments (the IDE Workshop), 2025.
Understanding Concurrency Bugs in Real-World Programs with Kotlin Coroutines Proceedings Article
In: Proceedings of the 38th European Conference on Object-Oriented Programming (ECOOP 2024), 2024.
The Design Space of in-IDE Human-AI Experience Unpublished
2024, (Preprint).
Long Code Arena: a Set of Benchmarks for Long-Context Code Models Journal Article
In: arXiv preprint arXiv:2406.11612, 2024.
A Transformer-Based Approach for Smart Invocation of Automatic Code Completion Proceedings Article
In: Proceedings of the 1st ACM International Conference on AI-Powered Software (AIWare 2024), 2024, (ACM Distinguished Paper Award).
In-IDE Human-AI Experience in the Era of Large Language Models: A Literature Review Proceedings Article
In: Proceedings of the 1st Workshop on Integrated Development Environments (the IDE Workshop), 2024.
TestSpark: IntelliJ IDEA's Ultimate Test Generation Companion Proceedings Article
In: Proceedings of the 2024 ACM/IEEE 46th International Conference on Software Engineering (ICSE 2024), 2024.
Evolutionary Generative Fuzzing for Differential Testing of the Kotlin Compiler Proceedings Article
In: Proceedings of the ACM International Conference on the Foundations of Software Engineering (FSE 2024 - Industry Track), 2024.
Delft University of Technology (TU Delft) is a technical university in Delft. Top education and research are at the heart of the oldest and largest technical university in the Netherlands.
JetBrains is a cutting-edge software vendor specializing in the creation of intelligent development tools, including IntelliJ IDEA.
