Track 4: Utilizing Runtime Information to Improve Development Processes

Track leader at TU Delft: Burcu Kulahcioglu Ozkan and Annibale Panichella
Track leader at JetBrains: Egor Klimov
Phd researcher(s): Zahra Seyedghorban (TU Delft) and Egor Klimov (JetBrains)

This track aims to seamlessly integrate runtime information into JetBrains IDEs, elevating the development experience by enhancing code quality, pinpointing and addressing performance issues, and providing precise code assistance within the IDE environment. To achieve this, we will bridge the gap between static and dynamic information within machine learning techniques.

Research Assistants:

• Andac Durmaz
• Ates Gorpelioglu

Track News

Publications

1. Authors anonymized for review. ATP: the Agentic Transfer Protocol. Submitted to the NeurIPS Workshop on Foundations of Agentic Systems Theory (FAST), 2026
2. Zahra Seyedghorban, Egor Klimov, Arie van Deursen, Annibale Panichella, and Burcu Kulahcioglu Ozkan. Observability and Fault Injection for LLM-Based Multi-Agent Systems in Software Engineering. IEEE International Conference on Software Testing, Verification and Validation (ICST — Testing Tools and Data Showcase), 2026
3. Roham Koohestani, Ateş Görpelioğlu, Egor Klimov, Burcu Kulahcioglu Ozkan, and Maliheh Izadi. TriCEGAR: A Trace-Driven Abstraction Mechanism for Agentic AI. arXiv preprint, 2026
4. Bob Brockbernd, Nikita Koval, Arie van Deursen, and Burcu Kulahcioglu Ozkan. Understanding Concurrency Bugs in Real-World Programs with Kotlin Coroutines. 38th European Conference on Object-Oriented Programming (ECOOP), 2024