About me
I'm a PhD student in the Machine Reasoning Lab supervised by Jendrik Seipp and co-supervised by Marco Kuhlmann. My research focuses on combining large language models (LLMs) with classical planning systems with the aim of creating a powerful but easy to use planner.
Short bio
I have a Master of Science in Applied Physics and Electrical Engineering from Linköping University with a specialisation in Data Driven Analysis and Machine Intelligence which will be completed in June 2024.
Awards
- Winner of the Explainability Challenge of the Beluga Competition organized by the TUPLES Consortium.
Publications
2026
Arnaud Lequen, Oliver Joergensen, Windy Phung, Elliot Gestrin, Damien Van Meerbeeck, Markus Fritzsche, Dominik Drexler and Jendrik Seipp.
Planner Museum: Evaluating Classical Planners Over Time.
In Proceedings of the Thirty-Sixth International Conference on Automated Planning and Scheduling (ICAPS 2026). 2026.
paper | citationElliot Gestrin and Jendrik Seipp.
LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planning.
In ICAPS 2026 Workshop on Planning in the Era of LLMs (LM4Plan). 2026.
paper | citationMarkus Fritzsche, Elliot Gestrin and Jendrik Seipp.
Symmetry-Aware Transformer Training for Automated Planning.
In ICAPS 2026 Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL). 2026.
paper | slides | citationElliot Gestrin, Johannes Fichte and Jendrik Seipp.
Automatically Uncovering Intended Domain Constraints in Automated Planning.
In ICAPS 2026 Workshop on Knowledge Engineering for Planning and Scheduling (KEPS). 2026.
paper | citationMarkus Fritzsche, Elliot Gestrin and Jendrik Seipp.
Symmetry-Aware Transformer Training for Automated Planning.
In Proceedings of the Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026), pp. 36236–36244. 2026.
paper | slides | poster | citation
2025
Elliot Gestrin, Gustaf Söderholm, Paul Höft, Mauricio Salerno, Jendrik Seipp and Daniel Gnad.
Explainable Planning via Counterfactual Task Analysis for the Beluga Challenge and Beyond.
In ICAPS 2025 Workshop on Human-Aware and Explainable Planning (HAXP). 2025.
paper | slides | citationMarkus Fritzsche, Elliot Gestrin and Jendrik Seipp.
Symmetry-Aware Transformer Training for Automated Planning.
In arXiv:2508.07743 [cs.AI]. 2025.
preprint | citation
2024
Elliot Gestrin, Marco Kuhlmann and Jendrik Seipp.
NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions.
In ICAPS 2024 Workshop on Human-Aware and Explainable Planning (HAXP). 2024.
paper | preprint | slides | code | citation