Track 3: Interactive and Aligned IDEs in the LLM Era

Track leader at TU Delft: Maliheh Izadi (Assistant Professor)
Track leader at JetBrains: Sergey Titov (Senior researcher)

An essential part of the success of tools like GitHub Copilot and ChatGPT is their interface. While some of these models’ capabilities were available before, the tools brought them to larger audiences without dramatically disrupting their workflow or requiring lots of additional steps. IDE users have their own workflows and the injection of new complex features, such as LLM-based ones, is a non-trivial task. We believe that there is significant space for innovation in the field of Human-AI interaction. While chat is a popular and user-friendly way of using LLMs, we believe there are better ways to utilize them in IDEs.

The goal of this project is to embed emerging LLM practices as code generation or code explanation into the developer workflow without disturbing the user and improving her productivity.

PhD Students:

  • Agnia Sergeyuk (JetBrains)
  • TBA (TU Delft)

MSc Students:

  • Remco Schrijver (graduated in 2024): Thesis
  • Frank van der Heijden (graduated in 2024): Thesis
  • Andrei Ionescu: Thesis
Track news
15 July 2024: MSc students graduated
14 July 2024: ACM Distinguished Paper Award at AIWare 2024
22 April 2024: Strong AI4SE presence at ICSE 2024

Publications
Agnia Sergeyuk, Ekaterina Koshchenko, Ilya Zakharov, Timofey Bryksin, and Maliheh Izadi. The Design Space of in-IDE Human-AI Experience. Preprint, 2024
Aral de Moor, Arie van Deursen, and Maliheh Izadi. A Transformer-Based Approach for Smart Invocation of Automatic Code Completion. Proceedings of the 1st ACM International Conference on AI-Powered Software (AIWare), ACM Distinguished Paper Award, 2024
Agnia Sergeyuk, Sergey Titov, and Maliheh Izadi. In-IDE Human-AI Experience in the Era of Large Language Models; A Literature Review. IDE Workshop (ICSE 2024), 2024

Projects
TU Delft Logo

JetBrains Logo