Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch
arXiv preprint arXiv:2608.00316
Research internship at Meta
Paul Brunzema
PhD Student
Institute for Data Science in Mechanical Engineering (DSME), RWTH Aachen University
I am a PhD student at the Institute for Data Science in Mechanical Engineering (DSME) at RWTH Aachen University, supervised by Sebastian Trimpe, since March 2022. Since September 2023, I am also an associate doctoral researcher in the UnRAVel Research Training Group, funded by the DFG.
In summer 2026, I was a research scientist intern at Meta in New York, NY, developing the concept of agentic Bayesian optimization. In summer 2025, I joined the EPIC group at Toyota Research Institute (TRI) in Los Altos, CA as a research intern, working on vision-conditioned autonomous racing in changing conditions.
My research focuses on uncertainty quantification (Gaussian processes, Bayesian neural networks) and sequential decision-making (Bayesian optimization, control, reinforcement learning).
Selected Publications
All publications →
Vision-Conditioned Variational Bayesian Last Layer Dynamics Models
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Research internship at Toyota Research Institute (TRI)
BayeSQP: Bayesian Optimization through Sequential Quadratic Programming
Advances in Neural Information Processing Systems (NeurIPS)
Bayesian Optimization via Continual Variational Last Layer Training
International Conference on Learning Representations (ICLR)
Collaboration with Google DeepMind, Vector Institute, and DTU
Event-Triggered Time-Varying Bayesian Optimization
Transactions on Machine Learning Research (TMLR)