Preprint · 2025 · Open access
ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization
arXiv (Cornell University) · Published 3 October 2025 · DOI 10.48550/arxiv.2510.03051
In brief
“ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization” is a 2025 preprint by Meindl, Jamison and 8 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 3
- Most cited in
- 2026 (2)
- References
- 31
- Authors
- 9
Abstract
Global optimization of expensive, derivative-free black-box functions requires extreme sample efficiency. While Bayesian optimization (BO) is the current state-of-the-art, its performance hinges on surrogate and acquisition function hyper-parameters that are often hand-tuned and fail to generalize across problem landscapes. We present ZeroShotOpt, a general-purpose, pretrained model for continuous black-box optimization tasks ranging from 2D to 20D. Our approach leverages offline reinforcement learning on large-scale optimization trajectories collected from 12 BO variants. To scale pretraining, we generate millions of synthetic Gaussian process-based functions with diverse landscapes, enabling the model to learn transferable optimization policies. As a result, ZeroShotOpt achieves robust zero-shot generalization on a wide array of unseen benchmarks, matching or surpassing the sample efficiency of leading global optimizers, including BO, while also offering a reusable foundation for future extensions and improvements. Our open-source code, dataset, and model are available at: https://github.com/jamisonmeindl/zeroshotopt
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Jamison, M., Tian, Y., Cui, T., Thost, V., Hong, Z.-W., Dürholt, J. P., Chen, J., Matusik, W., & Luković, M. K. (2025). ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.03051
MLA 9
Jamison, Meindl,, et al. “ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2510.03051.
Chicago
Jamison, Meindl,, Yunsheng Tian, Tony Cui, Veronika Thost, Zhang-Wei Hong, Johannes Peter Dürholt, Jie Chen, Wojciech Matusik, and Mina Konaković Luković. 2025. “ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.03051.
Harvard
Jamison, M. et al. (2025) ‘ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization’, arXiv (Cornell University). doi:10.48550/arxiv.2510.03051.
IEEE
M. Jamison et al., “ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2510.03051.
BibTeX
@misc{jamison2025zeroshotopt,
title = {{ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization}},
author = {Jamison, Meindl, and Tian, Yunsheng and Cui, Tony and Thost, Veronika and Hong, Zhang-Wei and Dürholt, Johannes Peter and Chen, Jie and Matusik, Wojciech and Luković, Mina Konaković},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2510.03051},
url = {https://doi.org/10.48550/arxiv.2510.03051}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research
- black-box optimization
- zero-shot generalization
- offline reinforcement learning
- derivative-free optimization
- Bayesian optimization
- sample efficiency
- high-dimensional optimization
Work with this paper
Most-cited papers in Decision Sciences
- The PRISMA 2020 statement: an updated guideline for reporting systematic reviewsMatthew James Page, Joanne E. McKenzie, Patrick M. Bossuyt and 23 more · BMJ · 2021 · 144,919 citations
- Evaluating Structural Equation Models with Unobservable Variables and Measurement ErrorClaes Fornell, David F. Larcker · Journal of Marketing Research · 1981 · 118,336 citations
- Cutoff criteria for fit indexes in covariance structure analysis: Conventional criteria versus new alternativesLi‐tze Hu, Peter M. Bentler · Structural Equation Modeling A Multidisciplinary Journal · 1999 · 117,461 citations
- Common method biases in behavioral research: A critical review of the literature and recommended remedies.Philip M. Podsakoff, SCOTT B. MACKENZIE, Jeong Yeon Lee and 1 more · Journal of Applied Psychology · 2003 · 89,248 citations
- Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statementDavid Moher, Alessandro Liberati, Jennifer Tetzlaff and 2 more · BMJ · 2009 · 85,524 citations
Questions about this paper
How do I cite this paper in APA style?
Jamison, M., Tian, Y., Cui, T., Thost, V., Hong, Z.-W., Dürholt, J. P., Chen, J., Matusik, W., & Luković, M. K. (2025). ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.03051
How many times has this paper been cited?
3 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Meindl, Jamison, Yunsheng Tian, Tony Cui, Veronika Thost, Zhang-Wei Hong, Johannes Peter Dürholt, Jie Chen, Wojciech Matusik, Mina Konaković Luković.
What is the DOI of this paper?
10.48550/arxiv.2510.03051, permanently at https://doi.org/10.48550/arxiv.2510.03051. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.