What we are interested in
At iol.human we investigate the integration of agentic AI, machine learning, and human-centered design to create adaptive, personalized systems for learning, decision-making, and societal change. Our research spans personalized education, where we develop LLM-based simulations and AI agents that support teachers in generating differentiated instructional materials for diverse learners; context-aware AI tutors, which dynamically adapt their instructional strategies by perceiving learners’ knowledge, motivation, and environment, moving beyond static recommendation models; and adaptive AR/VR for vocational training, where immersive technologies are tailored to individual learner characteristics to enhance skill development. In addition, we study human-AI decision-making, with a particular emphasis on how human and AI capabilities complement one another in practice, advancing our understanding of interaction, trust, and shared agency.
Researchers
📝 Publications and preprints
Preprints
- Haase, J., Klessascheck, F., Mendling, J., and Pokutta, S. (2025). Sustainability Via LLM Right-sizing.
[arXiv]
[BibTeX]
@misc{2025_HaaseFinnJanPokutta_Sustainabilityllm, archiveprefix = {arXiv}, eprint = {2504.13217}, primaryclass = {cs.CL}, year = {2025}, author = {Haase, Jennifer and Klessascheck, Finn and Mendling, Jan and Pokutta, Sebastian}, title = {Sustainability Via LLM Right-sizing}, date = {2025-04-17} }
- Haase, J., Hanel, P. H. P., and Pokutta, S. (2025). Has the Creativity of Large-Language Models Peaked? An Analysis of Inter- and Intra-LLM Variability.
[arXiv]
[BibTeX]
@misc{2025_HaasePPokutta_Llmvariability, archiveprefix = {arXiv}, eprint = {2504.12320}, primaryclass = {cs.CL}, year = {2025}, author = {Haase, Jennifer and Hanel, Paul H. P. and Pokutta, Sebastian}, title = {Has the Creativity of Large-Language Models Peaked? An Analysis of Inter- and Intra-LLM Variability}, date = {2025-04-10} }
- Haase, J., and Pokutta, S. (2025). Beyond Static Responses: Multi-Agent LLM Systems As a New Paradigm for Social Science Research.
[arXiv]
[BibTeX]
@misc{2025_HaasePokutta_Multiagentllm_2506-01839, archiveprefix = {arXiv}, eprint = {2506.01839}, primaryclass = {cs.MA}, year = {2025}, author = {Haase, Jennifer and Pokutta, Sebastian}, title = {Beyond Static Responses: Multi-Agent LLM Systems As a New Paradigm for Social Science Research}, date = {2025-06-02} }
- Gonnermann-Müller, J., Haase, J., Fackeldey, K., and Pokutta, S. (2025). FACET:Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational Worksheets.
[arXiv]
[BibTeX]
@misc{2025_JanaHaaseFackeldeyPokutta_Facetllm_2508-11401, archiveprefix = {arXiv}, eprint = {2508.11401}, primaryclass = {cs.HC}, year = {2025}, author = {Gonnermann-Müller, Jana and Haase, Jennifer and Fackeldey, Konstantin and Pokutta, Sebastian}, title = {FACET:Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational Worksheets}, date = {2025-08-15} }
Conference proceedings
- Gonnermann-Müller, J., Sahling, K., and Haase, J. (2025). Proceedings of the CHI Conference on Human Factors in Computing Systems.
[BibTeX]
@inproceedings{2025_GonnermannSahlingHaase_Letsberealistic, year = {2025}, booktitle = {Proceedings of the CHI Conference on Human Factors in Computing Systems}, author = {Gonnermann-Müller, Jana and Sahling, Kristina and Haase, Jennifer}, title = {} }
- Haase, J., Hanel, P. H. P., and Pokutta, S. (2025, May 14). S-DAT: a Multilingual, GenAI-driven Framework for Automated Divergent Thinking Assessment. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES).
[arXiv]
[BibTeX]
@inproceedings{2025_HaasePPokutta_SdatDivergentthinking, year = {2025}, booktitle = {Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES)}, archiveprefix = {arXiv}, eprint = {2505.09068}, primaryclass = {cs.CL}, author = {Haase, Jennifer and Hanel, Paul H. P. and Pokutta, Sebastian}, title = {S-DAT: a Multilingual, GenAI-driven Framework for Automated Divergent Thinking Assessment}, date = {2025-05-14} }
- Schummel, P., Teichmann, M., and Gonnermann-Müller, J. (2025). Specifying Ten Roles of Using Chatgpt in Secondary Education: a Teacher´s Perspective. Proceedings of the European Conference on Information Systems.
[BibTeX]
@inproceedings{2025_SchummelTeichmannGonnermann_Sepcifying, year = {2025}, booktitle = {Proceedings of the European Conference on Information Systems}, author = {Schummel, Philip and Teichmann, Malte and Gonnermann-Müller, Jana}, title = {Specifying Ten Roles of Using Chatgpt in Secondary Education: a Teacher´s Perspective} }
- Gonnermann-Müller, J., Leins, N., Gronau, N., and Kosch, T. (2024). Value by Design: Reducing Cognitive Load by Using Visual Guidance in Augmented RealityAn Eye-Tracking Study. Proceedings of the International Conference on Information Systems.
[BibTeX]
@inproceedings{2024_GonnermannLeinsGronauKosch_Valuebydesign, year = {2024}, booktitle = {Proceedings of the International Conference on Information Systems}, author = {Gonnermann-Müller, Jana and Leins, Nicolas and Gronau, Norbert and Kosch, Thomas}, title = {Value by Design: Reducing Cognitive Load by Using Visual Guidance in Augmented RealityAn Eye-Tracking Study} }
- Gonnermann-Müller, J., Brandenburger, B., Vladova, G., and Gronau, N. (2023). To What Extent Can Individualisation in Terms of Different Types of Mode Improve Learning Outcomes and Learner Satisfaction? A Pre-study. Proceedings of the Hawaii International Conference on System Sciences.
[BibTeX]
@inproceedings{2023_GonnermannBrandenburgerVladovaGronau_Towhatextendcanindividualisation, year = {2023}, booktitle = {Proceedings of the Hawaii International Conference on System Sciences}, author = {Gonnermann-Müller, Jana and Brandenburger, Bonny and Vladova, Gergana and Gronau, Norbert}, title = {To What Extent Can Individualisation in Terms of Different Types of Mode Improve Learning Outcomes and Learner Satisfaction? A Pre-study} }