Robert Gieselmann

I am an AI Researcher at Amazon in Berlin developing fast, verifiable, and self-improving reasoning systems, primarily leveraging Large Language Models (LLMs). Previously, I completed a PhD in Computer Science at KTH Royal Institute of Technology in Stockholm, supervised by Florian T. Pokorny, and supported by WASP, the Wallenberg AI, Autonomous Systems and Software Program. I completed several internships, including at Meta and Bosch AI. Before my PhD, I worked as a Research Assistant within machine learning and robotics at the Technical University of Hamburg (TUHH). I received my M.Sc. in Robotics, Cognition, Intelligence from the Technical University of Munich (TUM).

Selected Publications

• Efficient Test-time Inference for Generative Planning Models
  Robert Gieselmann, Mihai Samson, Federico Pecora, Jeremy L. Wyatt
  International Conference on Machine Learning (ICML), 2026
  [Paper]
• Self-Improvement for Fast, High-Quality Plan Generation
  Robert Gieselmann, Henrike von Huelsen, Mihai Samson, Marie-Christine Meyer, Dariusz Piotrowski, Oleksandr Radomskyi, Justin Okamoto, Turan Gojayev, Michael Painter, Gavin Brown, Federico Pecora, Jeremy L. Wyatt
  International Conference on Automated Planning and Scheduling (ICAPS), 2026
  [Paper]
• Expansive Latent Planning for Sparse Reward Offline Reinforcement Learning
  Robert Gieselmann, Florian T. Pokorny
  Conference on Robot Learning (CoRL), 2023 (oral presentation 6.6%)
  [Paper]
• Latent Planning via Expansive Space Trees
  Robert Gieselmann, Florian T. Pokorny
  Neural Information Processing Systems (NeurIPS), 2022
  [Paper]