The paper investigates how incorporating intermediate responses—known as Composite modeling—into Multi‑Objective Bayesian Optimization (MOBO) can improve sampling efficiency for scientific design problems. It establishes theoretical conditions under which intermediate observations add no predictive value and then conducts controlled experiments across four MOBO methods and eight benchmarks to assess practical gains. Results indicate that Composite modeling is most beneficial when the mapping from intermediate responses to final objectives is non‑bijective and non‑affine.
By Ricky Ye, Sahas Goli, Muhammad Ali, Poompol Buathong, Peter I. Frazier
FoMEMO is a foundation model designed for expensive multi-objective optimization. It transforms the problem into preference-wise aggregated posterior learning tasks, allowing scalable pre-training on vast synthetic datasets without extensive real-world experiments. At inference, the model uses observed trajectories and user preferences to perform in-context posterior prediction and optimize acquisition functions, achieving strong generalization without further training.
By Yiming Yao, Fei Liu, Liang Zhao, Xi Lin, Yilu Liu, Qingfu Zhang
arXiv:2603. 29730v2 Announce Type: replace-cross Abstract: We present mlr3mbo, a modular toolbox for Bayesian optimization in R.
By Marc Becker, Lennart Schneider, Martin Binder, Lars Kotthoff, Bernd Bischl
arXiv:2608. 11713v1 Announce Type: cross Abstract: Multi-objective Bayesian optimization (MOBO) is effective in identifying the Pareto fronts for expensive black-box problems.
By Hongyan Wang, Jiayu Huang, Haotian Zheng, Xin Gao, Chi Ding, Ying Liu, Xia Wang, Qing Xu, Keqiang Li
MF-SCBO is a new multi‑fidelity extension of Scalable Constrained Bayesian Optimization designed for high‑dimensional black‑box functions with black‑box constraints. It handles an arbitrary number of fidelity levels and non‑nested sampling, addressing gaps in existing methods. Experiments on standard benchmarks and challenging problems show that MF‑SCBO generally converges faster than both single‑fidelity SCBO and other multi‑fidelity approaches in high‑dimensional constrained settings.
By Lucas Palazzolo, Micka\"el Binois, La\"etitia Giraldi
arXiv:2608. 04113v1 Announce Type: cross Abstract: Black-box optimization is a ubiquitous problem in science and engineering, often dealing with expensive objective functions with cheaper lower-fidelity proxies available.
By Gustavo Sutter, Hao Wang, Luis Ricardez-Sandoval, Pascal Poupart, Agustinus Kristiadi
arXiv:2610.08969v1 Announce Type: new
Abstract: Black-box optimization problems are ubiquitous across science and engineering, often dealing with expensive objective functions. This objective latency...
By Gustavo Sutter, Alejandro Comas-Leon, David Holzm\"uller, Hao Wang, Luis Ricardez-Sandoval, Pascal Poupart, Agustinus Kristiadi
arXiv:2608. 14264v1 Announce Type: cross Abstract: Model merging combines trained models directly in weight space, offering a compute-efficient alternative to additional fine-tuning.
By Utkarsh Agarwal, Vamshi Bonagiri, Raul Astudillo, Monojit Choudhury
BoLT is a new benchmark designed to make black-box optimization research for large language model (LLM) tasks more accessible. It presents a suite of realistic LLM optimization problems—covering multi‑fidelity, multi‑objective, heteroscedastic noise, and high‑dimensional search spaces—grounded in thousands of real experiments and represented by lightweight surrogate models. The authors evaluate a wide range of Bayesian and other black‑box optimization methods on BoLT, finding that some BO techniques consistently outperform others and revealing gaps in current methods for LLM optimization.
By Ruth Wan Theng Chew, Zhiliang Chen, Apivich Hemachandra, Bryan Kian Hsiang Low
arXiv:2606. 06984v1 Announce Type: new Abstract: This paper presents a general acceleration mechanism for multi-objective Bayesian optimisation (MOBO) that leverages Gaussian process predictive gradients as auxiliary signals.
By Alma Rahat, Tinkle Chugh, Jonathan Fieldsend, Richard Allmendinger
arXiv:2610.10186v1 Announce Type: new
Abstract: Bayesian optimization (BO) is widely used as a standard approach for expensive black-box optimization. However, BO algorithms often involve parameters...
By Satoshi Katayama, Shoyo Hunt, Shintaro Masuda, Masayuki Karasuyama
The paper introduces a unified information‑theoretic framework for Bayesian optimization that simultaneously handles multiple objectives, constraints, and fidelity levels. It defines query utility as the information gain about the highest‑fidelity feasible Pareto frontier and derives a tractable variational lower bound using truncated approximations. The resulting cost‑aware acquisition function leverages multi‑fidelity surrogate models, eliminating the need for separate heuristics, and is validated on synthetic, benchmark, and real‑world experiments.
By Rikuto Matsumoto, Masanori Ishikura, Masayuki Karasuyama