About

I am currently pursuing a PhD at the DTAI lab of KU Leuven, focusing on the intersection of Constraint Programming and Large Language Models, under the supervision of Prof. Tias Guns. My research combines symbolic reasoning with machine learning to address complex combinatorial optimization and satisfaction problems derived from natural language inputs.

Before starting my PhD, I worked as a software engineer in the industry, where I developed enterprise-level applications. I hold a Master's in Computer Science from KUL, majoring in AI, and a Bachelor's in Informatics & Telecommunications from NKUA, majoring in CS.

Publications

  • CP-Bench: Evaluating Large Language Models for Constraint Modelling. In European Conference on Artificial Intelligence (ECAI 2025). Frontiers in Artificial Intelligence and Applications, Volume 413, pp. 861-868 (2025). https://doi.org/10.3233/FAIA250890
    Kostis Michailidis, Dimos Tsouros, and Tias Guns.
    Paper (PDF) | Poster (PDF) | Code
  • Constraint Modelling with LLMs Using In-Context Learning. In 30th International Conference on Principles and Practice of Constraint Programming (CP 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 307, pp. 20:1-20:27, Schloss Dagstuhl -- Leibniz-Zentrum für Informatik (2024). https://doi.org/10.4230/LIPIcs.CP.2024.20
    Kostis Michailidis, Dimos Tsouros, and Tias Guns.
    Paper (PDF) | Presentation (Video) | Slides (PDF) | Poster (PDF) | Code

Talks & Presentations

  • CP-Bench: Benchmarking LLMs for CP Model Generation. Workshop: LLMs meet Constraint Solving (LLM-Solve), CP/SAT 2025, Glasgow, Scotland (August 11, 2025).
    Kostis Michailidis, Dimos Tsouros, and Tias Guns.
    Workshop | Slides (PDF)

Other

Teaching

  • Teaching Assistant (TA) for Constraint Solving (CoS), Master of Computer Science, KU Leuven, 2025.
  • Teaching Assistant (TA) for Declarative Problem Solving Paradigms for AI (DPSPAI), Master of Computer Science, KU Leuven, 2024.

Awards

  • Best Poster Award for the paper "Constraint Modelling with LLMs Using In-Context Learning", CP 2024, Doctoral Program.