method · first seen 5 Oct 2026
Bayesian optimization
Also: BO, Bayesian optimisation, Bayesian data augmentation
Sequential model-based optimization using a surrogate model to pick informative evaluations.
Bayesian optimization fits a probabilistic surrogate, usually a Gaussian process, to expensive black-box evaluations and uses an acquisition function to choose the next query. The sources are mostly arXiv papers applying or refining this long-standing method rather than introducing it. They include isotropic GP priors for high-dimensional BO, trust-region molecular design (TRACE), tabular foundation models such as TabPFN as surrogates in materials discovery, LLM-guided configuration of BO (STaSBO), and BO set against agentic optimization in self-driving lab testbeds. There is also one protein-engineering repo. The spread across chemistry, materials, NAS and protein design reflects routine use of the method.
The method itself has been mainstream for over a decade, so the rise is noise. The more specific threads are worth watching separately: foundation-model surrogates, LLM meta-controllers for BO, and BO inside self-driving laboratories.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 135 on 14 Nov 2026 · 36 mentions in 28 days · 34 independent groups · papers → code · first seen 6 weeks ago · acceleration +0.27
Earliest sources
- Bayesian Data Augmentation for DNN Retraining with Binomial Outcomes in Vision-Based UAV LandingPapers · 5 Oct 2026 · Ashik E Rasul, Hyung-Jin Yoon
- Isotropic Gaussian Processes Improve Vanilla Bayesian Optimization in High DimensionsPapers · 5 Oct 2026 · Wei-Ting Tang, Madhav Muthyala, Joel A. Paulson
- Bayesian Optimization in Sequence-to-Architecture Latent Space for Zero-Shot NASPapers · 5 Oct 2026 · Ondrej Tybl, Lukas Neumann
- Linear Fitness Subspace in Protein Language Models Enables Sample-Efficient Directed EvolutionPapers · 6 Oct 2026 · SiYuan Ma, Canran Xiao, Zikai Xiao, Albert Gao, Liang He, Xuan-Yu Wang, Shuying…
- Information-Dense Synthesis for Molecular DiscoveryPapers · 6 Oct 2026 · Kasper K. Jakobsen, Eli N. Weinstein
- Work While They Sleep: Exploiting Evaluation Latency for Fully Bayesian OptimizationPapers · 6 Oct 2026 · Gustavo Sutter, Alejandro Comas-Leon, David Holzmüller, Hao Wang, Luis Ricardez…
Latest sources
- STaSBO: LLM-Guided Strategy Planning and Configuration Selection for Bayesian OptimizationPapers · 14 Nov 2026 · Youngseok Yoon, Peng Li
- Sample-efficient prediction of high-entropy alloy strength through outcome-aware robust sequential learningPapers · 13 Nov 2026 · Ahmed Shoyeb Raihan, Md Habibor Rahman, Ashish Nimbarte, Imtiaz Ahmed
- TRACE: Adaptive Trust-Region Bayesian Optimization for Open-Ended Molecular DesignPapers · 9 Nov 2026 · Madhav R. Muthyala, Mahsa Askari, Farshud Sorourifar, Evan Zhou, Joe Gauthier, J…
- Out-of-the-Box Tabular Foundation Models for Bayesian Optimization in Materials DiscoveryPapers · 9 Nov 2026 · Klemens Flöge, Simon Bing, Leo Grinsztajn, Eliott Kalfon, Lennart Purucker, Noa…
- Scalable Bayesian Optimization for Efficient Exploration of Moire PatternsPapers · 9 Nov 2026 · Panagiotis Krokidas, Christos Lazaridis, Vassilis Sioros, Efi-Maria Papia, Vassi…
- A Physical Testbed for Self-Driving Laboratories: Comparing Bayesian and Agentic Optimization in a Minimal Closed-Loop Color Formulation TaskPapers · 8 Nov 2026 · Tony Qin, Ziheng Wu, Maximilian Schommer, Roya Amini-Naieni, Aldair Gongora
- Chatter Attack: Resource Consumption Attack for Large Language ModelsPapers · 8 Nov 2026 · Yibo Miao, Yichuan Cao, Xiao-Shan Gao, Yinpeng Dong
- Embodied Science Agents: Making Embodied Experimental Design LearnablePapers · 7 Nov 2026 · Yihang Che, Zhongwei Yu, Yang Li, Xingyu Lu, Hongxia Yu, Jun Wang
- Match the Geometry Before the Surrogate: Extreme Low-Budget Optimization in High DimensionsPapers · 6 Nov 2026 · Michal Průšek, Adam Novozámský, Filip Šroubek
- BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian OptimisationPapers · 6 Nov 2026 · Colin Doumont, Thomas Christie, Henry Moss, Philipp Hennig
- Data-Efficient Scaling-Law Discovery for Recommendation Systems via Coupled Hyperparameter ScalingPapers · 3 Nov 2026 · John Martabano Landy, Louis C. Tiao, Yao Xuan, Luc Kien Hang, Rupinder P. Khandp…
- Forgetting to Improve: Principled Data Removal in Active LearningPapers · 2 Nov 2026 · Manuel Wendl, Erik Englesson, Andreas Krause, Carl Henrik Ek