Nicolas Leins

Nicolas Leins

My research focuses on human-computer interaction with agentic AI systems in the areas of learning, collaboration, and decision-making. Through prototyping and experimental evaluation, I investigate how people collaborate with and experience AI in applied contexts (e.g., AR and VR), addressing interaction design, user experience, and broader societal implications.

Contact

office
Room 3023 at ZIB
e-mail
homepage
nicolasleins.com/

Curriculum vitae

since 2025
Researcher at ZIB
Sep 2025
M.Sc. in Business Information Systems and Digital Transformation at UP
2020 to 2025
Research Assistant at UP
Sep 2022
B.Sc. in Business Information Systems at UP

Publications and preprints

Preprints and reports

  1. Gonnermann-Müller, J., Haase, J., Leins, N., Kosch, T., and Pokutta, S. (2026). LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD Profiles. [arXiv]
    [BibTeX]
    @misc{2026_GonnermannmuellerEtAl_Llmstudentsimulation_2605-06307,
      archiveprefix = {arXiv},
      eprint = {2605.06307},
      arxiv = {arXiv:2605.06307},
      primaryclass = {cs.HC},
      author = {Gonnermann-Müller, Jana and Haase, Jennifer and Leins, Nicolas and Kosch, Thomas and Pokutta, Sebastian},
      title = {LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD Profiles},
      date = {2026-05-07}
    }
  2. Haase, J., Gonnermann-Müller, J., Yim, S. H., Leins, N., Mendling, J., and Pokutta, S. (2026). Simulating Eating Disorder Patients with LLMs: Evaluating Psychological Persona Stability in Multi-Turn Conversations. [arXiv]
    [BibTeX]
    @misc{2026_HaaseEtAl_Llmstability_2606-26109,
      archiveprefix = {arXiv},
      eprint = {2606.26109},
      arxiv = {arXiv:2606.26109},
      primaryclass = {cs.CY},
      author = {Haase, Jennifer and Gonnermann-Müller, Jana and Yim, See Heng and Leins, Nicolas and Mendling, Jan and Pokutta, Sebastian},
      title = {Simulating Eating Disorder Patients with LLMs: Evaluating Psychological Persona Stability in Multi-Turn Conversations},
      date = {2026-05-12}
    }
  3. Leins, N., Haase, J., Geronimus, V., Gonnermann-Müller, J., and Pokutta, S. (2026). Prompting Against Persona Drift: Comparing Intervention Timing and Content in LLM-Simulated Conversations. [arXiv]
    [BibTeX]
    @misc{2026_LeinsEtAl_PersonaDriftIntervention_2609-24532,
      archiveprefix = {arXiv},
      eprint = {2609.24532},
      arxiv = {arXiv:2609.24532},
      primaryclass = {cs.HC},
      author = {Leins, Nicolas and Haase, Jennifer and Geronimus, Varvara and Gonnermann-Müller, Jana and Pokutta, Sebastian},
      title = {Prompting Against Persona Drift: Comparing Intervention Timing and Content in LLM-Simulated Conversations},
      date = {2026-09-21}
    }
  4. Leins, N., Fischer, M., Teichmann, M., Gonnermann-Müller, J., and Pokutta, S. (2026). Robot Programming with Augmented Reality: The Role of Spatial Ability. [arXiv]
    [BibTeX]
    @misc{2026_LeinsGonnermannmuellerTeichmannPokutta_Spatialabilityar_2602-03544,
      archiveprefix = {arXiv},
      eprint = {2602.03544},
      arxiv = {arXiv:2602.03544},
      primaryclass = {cs.RO},
      author = {Leins, Nicolas and Fischer, Muriel and Teichmann, Malte and Gonnermann-Müller, Jana and Pokutta, Sebastian},
      title = {Robot Programming with Augmented Reality: The Role of Spatial Ability},
      date = {2026-02-03}
    }
  5. Leins, N., Pelleriti, N., Gonnermann-Müller, J., and Pokutta, S. (2026). When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Cost, and Task Difficulty. [arXiv]
    [BibTeX]
    @misc{2026_LeinsPelleritiGonnermannmuellerPokutta_Llmorchestration_2608-00685,
      archiveprefix = {arXiv},
      eprint = {2608.00685},
      arxiv = {arXiv:2608.00685},
      primaryclass = {cs.AI},
      author = {Leins, Nicolas and Pelleriti, Nico and Gonnermann-Müller, Jana and Pokutta, Sebastian},
      title = {When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Cost, and Task Difficulty},
      date = {2026-08-01}
    }

Conference contributions

  1. Haase, J., Gonnermann-Müller, J., Hanel, P. H. P., Leins, N., Kosch, T., Mendling, J., and Pokutta, S. Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks. Advances in Neural Information Processing Systems, 39. To appear. Associated with NeurIPS 2026. [arXiv]
    [BibTeX]
    @inproceedings{2026_HaaseEtAl_Promptvariability_2601-21339:1,
      booktitle = {Advances in Neural Information Processing Systems},
      series = {Advances in Neural Information Processing Systems},
      volume = {39},
      publisher = {Curran Associates},
      note = {To appear},
      archiveprefix = {arXiv},
      eprint = {2601.21339},
      arxiv = {arXiv:2601.21339},
      primaryclass = {cs.AI},
      author = {Haase, Jennifer and Gonnermann-Müller, Jana and Hanel, Paul H. P. and Leins, Nicolas and Kosch, Thomas and Mendling, Jan and Pokutta, Sebastian},
      title = {Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks}
    }
  2. Leins, N., Gonnermann-Müller, J., Teichmann, M., and Pokutta, S. (2026). Beyond Static Instruction: A Multi-agent AI Framework for Adaptive Augmented Reality Robot Training. Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction, 989–993. Associated with LBR @ HRI 2026. DOI: 10.1145/3776734.3794542 [URL] [arXiv]
    [BibTeX]
    @inproceedings{2026_LeinsGonnermannmuellerTeichmannPokutta_Multiagentar_2603-00016,
      year = {2026},
      date = {2026-03-04},
      booktitle = {Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction},
      publisher = {Association for Computing Machinery},
      month = mar,
      pages = {989--993},
      doi = {10.1145/3776734.3794542},
      url = {https://dl.acm.org/doi/10.1145/3776734.3794542},
      archiveprefix = {arXiv},
      eprint = {2603.00016},
      arxiv = {arXiv:2603.00016},
      primaryclass = {cs.RO},
      author = {Leins, Nicolas and Gonnermann-Müller, Jana and Teichmann, Malte and Pokutta, Sebastian},
      title = {Beyond Static Instruction: A Multi-agent AI Framework for Adaptive Augmented Reality Robot Training}
    }
  3. Gonnermann-Müller, J., Haase, J., Leins, N., Igel, M., Fackeldey, K., and Pokutta, S. (2026). FACET: Multi-Agent AI Supporting Teachers in Scaling Differentiated Learning for Diverse Students. Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, 7165–7173. Associated with IJCAI 2026. DOI: 10.24963/ijcai.2026/797 [arXiv]
    [BibTeX]
    @inproceedings{2026_GonnermannmuellerEtAl_Facetmultiagent_2601-22788,
      year = {2026},
      booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence},
      publisher = {International Joint Conferences on Artificial Intelligence Organization},
      pages = {7165--7173},
      doi = {10.24963/ijcai.2026/797},
      archiveprefix = {arXiv},
      eprint = {2601.22788},
      arxiv = {arXiv:2601.22788},
      primaryclass = {cs.HC},
      author = {Gonnermann-Müller, Jana and Haase, Jennifer and Leins, Nicolas and Igel, Moritz and Fackeldey, Konstantin and Pokutta, Sebastian},
      title = {FACET: Multi-Agent AI Supporting Teachers in Scaling Differentiated Learning for Diverse Students}
    }
  4. Gonnermann-Müller, J., Haase, J., Leins, N., Kosch, T., and Pokutta, S. (2026). Maintaining Stable Personas? Examining Temporal Stability in LLM-Based Human Simulation. Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems, 1–6. Associated with CHI EA 2026. DOI: 10.1145/3772363.3799334 [arXiv]
    [BibTeX]
    @inproceedings{2026_GonnermannmuellerEtAl_Stablepersonas_2601-22812,
      year = {2026},
      booktitle = {Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems},
      publisher = {Association for Computing Machinery},
      pages = {1--6},
      doi = {10.1145/3772363.3799334},
      archiveprefix = {arXiv},
      eprint = {2601.22812},
      arxiv = {arXiv:2601.22812},
      primaryclass = {cs.HC},
      author = {Gonnermann-Müller, Jana and Haase, Jennifer and Leins, Nicolas and Kosch, Thomas and Pokutta, Sebastian},
      title = {Maintaining Stable Personas? Examining Temporal Stability in LLM-Based Human Simulation}
    }
  5. Haase, J., Gonnermann-Müller, J., Hanel, P. H. P., Leins, N., Kosch, T., Mendling, J., and Pokutta, S. (2026). It’s Not Just the Prompt: Model Choice Dominates LLM Creative Output. Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems, 1–5. Associated with CHI EA 2026. DOI: 10.1145/3772363.3799284 [arXiv]
    [BibTeX]
    @inproceedings{2026_HaaseEtAl_Promptvariability_2601-21339,
      year = {2026},
      booktitle = {Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems},
      publisher = {Association for Computing Machinery},
      pages = {1--5},
      doi = {10.1145/3772363.3799284},
      archiveprefix = {arXiv},
      eprint = {2601.21339},
      arxiv = {arXiv:2601.21339},
      primaryclass = {cs.AI},
      author = {Haase, Jennifer and Gonnermann-Müller, Jana and Hanel, Paul H. P. and Leins, Nicolas and Kosch, Thomas and Mendling, Jan and Pokutta, Sebastian},
      title = {It's Not Just the Prompt: Model Choice Dominates LLM Creative Output}
    }
  6. Leins, N., Pelleriti, N., Gonnermann-Müller, J., and Pokutta, S. (2026). When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Resources, and Task Difficulty. Accepted at NeurIPS 2026 Workshop on Resource-Aware Agentic AI. [arXiv]
    [BibTeX]
    @misc{2026_LeinsPelleritiGonnermannmuellerPokutta_Llmorchestration_2608-00685:1,
      howpublished = {Accepted at NeurIPS 2026 Workshop on Resource-Aware Agentic AI},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2608.00685},
      arxiv = {arXiv:2608.00685},
      primaryclass = {cs.AI},
      author = {Leins, Nicolas and Pelleriti, Nico and Gonnermann-Müller, Jana and Pokutta, Sebastian},
      title = {When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Resources, and Task Difficulty}
    }
  7. Gonnermann-Müller, J., Leins, N., Gronau, N., and Kosch, T. (2024, December 15). Value by Design: Reducing Cognitive Load by Using Visual Guidance in Augmented Reality - An Eye-Tracking Study. ICIS 2024 Proceedings. Associated with ICIS 2024. [URL]
    [BibTeX]
    @inproceedings{2024_GonnermannLeinsGronauKosch_Valuebydesign,
      year = {2024},
      date = {2024-12-15},
      booktitle = {ICIS 2024 Proceedings},
      publisher = {Association for Information Systems (AIS eLibrary)},
      url = {https://aisel.aisnet.org/icis2024/humtechinter/humtechinter/18/},
      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 Reality - An Eye-Tracking Study}
    }

Articles, chapters and books

  1. Leins, N., Gonnermann-Müller, J., and Teichmann, M. (2024). Comparing head-mounted and handheld augmented reality for guided assembly. Journal on Multimodal User Interfaces, 18(4), 313–328. DOI: 10.1007/s12193-024-00440-1
    [BibTeX]
    @article{2024_LeinsGonnermann_ComparingHMD,
      year = {2024},
      date = {2024-09-27},
      journal = {Journal on Multimodal User Interfaces},
      month = sep,
      volume = {18},
      number = {4},
      pages = {313--328},
      doi = {10.1007/s12193-024-00440-1},
      author = {Leins, Nicolas and Gonnermann-Müller, Jana and Teichmann, Malte},
      title = {Comparing head-mounted and handheld augmented reality for guided assembly}
    }

Projects

AIPsySys
AI Meets Psychology and Systems

This project investigates how advanced AI systems can augment human competence in creativity, learning, and scientific reasoning, combining psychological research on human–AI interaction with algorithmic modeling and multi-agent system design.

AIPsySys
since Aug 2025
9
13

FACET
Framework for Agent-Based Classroom Enhancement for Teacher

FACET is a teacher-facing multi-agent AI framework developed jointly by ZIB, the Weizenbaum Institute, and partner schools in Berlin to support differentiated instruction in heterogeneous classrooms. The project combines psychological research on human–AI interaction with algorithmic modeling and multi-agent system design.

FACET
since Aug 2025
8
3

Talks and posters

Conference and workshop talks

Aug 2026
FACET: Multi-Agent AI Supporting Teachers in Scaling Differentiated Learning for Diverse Students by Nicolas Leins
IJCAI Conference, Bremen

Poster presentations

Aug 2026
FACET: Multi-Agent AI Supporting Teachers in Scaling Differentiated Learning for Diverse Students by Nicolas Leins
IJCAI Conference, Bremen
Apr 2026
Stable Personas: Dual-Assessment of Temporal Stability in LLM-Based Human Simulation by Jana Gonnermann-Müller and Nicolas Leins
CHI Conference, Barcelona
Apr 2026
Within-Model Vs Between-Prompt Variability in Large Language Models for Creative Tasks by Jana Gonnermann-Müller and Nicolas Leins
CHI Conference, Barcelona
Mar 2026
Beyond Static Instruction: A Multi-Agent AI Framework for Adaptive Augmented Reality Robot Training by Nicolas Leins
21st HRI Conference, Edinburgh

Events

Aug 2026
IJCAI Conference, Bremen
Apr 2026
CHI Conference, Barcelona
Mar 2026
21st HRI Conference, Edinburgh
Jan 2026
40th AAAI Conference on Artificial Intelligence (AAAI), Singapore
summer 2025
Organizational Knowledge Management, Potsdam
summer 2024
Organizational Knowledge Management, Potsdam

Teaching

summer 2025
Teaching Assistant for Organizational Knowledge Management at UP
summer 2024
Teaching Assistant for Organizational Knowledge Management at UP