IEEE WCCI2026-CEC
Workshop on Generative and Adaptive
Surrogate Models for Evolutionary Algorithms

21-26 June 2026,

Maastricht, the Netherlands,

held in IEEE WCCI2026 - CEC

Motivations and Scopes

Evolutionary algorithms (EAs) remain a cornerstone of optimization research due to their flexibility, black-box compatibility, and applicability, with proven success in fields like shape design, scheduling, and electronic design. However, modern problems bring new challenges, including high evaluation costs, structural heterogeneity (e.g., continuous and discrete), and increasing complexity, including multi-objective, constrained, multi-modal, or dynamic characteristics.

To address these challenges, surrogate-assisted EAs have long been explored, where auxiliary models such as Gaussian processes (also know as Kriging), radial basis function (RBF) networks, support vector regression (SVR), and shallow neural networks approximate expensive evaluations. Recent developments also explore adaptive surrogates, involving online hyperparameter tuning, ensembles, and automated model selection.

At the same time, generative models, such as large language models (LLMs), generative adversarial networks (GANs), and diffusion models (DMs), have emerged as powerful tools in optimization. Unlike traditional surrogates, they act as reasoning-aware planners, capable of modeling complex solution distributions and capturing structural semantics beyond scalar fitness. Their integration with EAs opens up new possibilities for navigating complex search spaces and enabling more informed decision-making.

Despite growing interest, surrogate-assisted EAs are often developed in isolation for specific problem types. This workshop aims to unify perspectives across domains by asking: "Which surrogate models work best for which types of optimization problems and how should they be integrated into EA pipelines?" Moreover, we explore a timely and challenging topic: "What are the obstacles in leveraging generative models as surrogates within EAs?" We welcome contributions spanning from classical surrogate models to emerging generative approaches, with a particular emphasis on practical design principles that connect problem characteristics with appropriate modeling techniques and search strategies.

Topics and Keywords

We invite papers on surrogate-assisted and data-driven EAs, covering classical, adaptive, ensemble, and generative models for a wide range of optimization challenges.

Topics of interest include, but are not limited to:

Surrogate and Generative/Adaptive Models in EAs

Surrogate-assisted/Data-driven EAs
Adaptation and self-tuning of surrogate models
Ensemble surrogate models
LLM-assisted EAs for optimization
GAN-assisted EAs for optimization
DM-assisted EAs for optimization
EAs assisted by collaborating small and large surrogates

Optimization Problem Scenarios

Single/Multi-objective optimization
Dynamic optimization
Continuous/Combinatorial optimization
Multi-modal optimization
Constrained optimization
Bi-level/Hierarchical optimization
Expensive optimization

Techniques and Applications

Pareto learning and approximation
Generative solution modeling
Guided search and acquisition strategies

We warmly welcome both theoretical/methodological contributions and practical applications. Your contributions are highly encouraged to join the discussion on how modern modeling techniques can reshape evolutionary optimization.

Workshop Style

This workshop consists of two parts: invited talks and regular presentations. For the regular presentations, anyone who wishes is welcome to present the original contributions. Kindly submit your application via the form below by the specified deadline. We will announce the detailed guidelines later.

Important Dates

(Anywhere on Earth)

Deadline of title and abstract submissions: TBA (not earlier than March 2026)

Author/Participant Guidelines

Every participant in this workshop is required to complete registration for IEEE WCCI2026 since this workshop will be held as a part of the conference. No additional fee is needed for this workshop.

Submission Form

TBA (below, not opened yet)

Organizers

Xiangyu Wang

Bielefeld University, Germany

Dr. Kei Nishihara

Muroran Institute of Technology, Japan

Prof. Tomohiro Harada

Saitama University, Japan

Prof. Yaochu Jin

Westlake University, China

Xiangyu Wang received her B.Sc. and M.Sc. degrees in Mathematics and Applied Mathematics from China University of Petroleum, Qingdao, China, in 2020 and 2022, respectively. She is currently pursuing a Ph.D. degree in the Faculty of Technology at Bielefeld University, Germany. She completed a short-term research visit at the University of Manchester, U.K., in 2018, and studied as an exchange student at the University of Calgary, Canada, in 2020. She has organized workshops and special sessions at WCCI 2024, and served as a reviewer for journals such as TEVC, TCYB, TAI, TETCI, and CAIS. Her research interests include graph neural network-based optimization and multi-objective evolutionary optimization.
Kei Nishihara received the B.Eng., M.Eng., and PhD degrees from the (Graduate) School of Science and Engineering at Yokohama National University, Yokohama, Japan, in 2020, 2022, and 2025, respectively. He was also a Research Fellow (DC1) of the Japan Society for the Promotion of Science from 2022 to 2025, and a visiting researcher of the Trustworthy and General AI Laboratory at the School of Engineering, Westlake University, Hangzhou, China from 2023 to 2024. He is currently an assistant professor at the Graduate School of Engineering, Muroran Institute of Technology, Muroran, Japan. He served as a reviewer for journals such as TEVC, TCYB, TSMC(A), SWEVO, and KNOSYS. He received the IEEE Computational Intelligence Society Japan Chapter Young Researcher Award in 2022. His current research interest includes adaptation in evolutionary algorithms and surrogate-assisted evolutionary algorithms.
Tomohiro Harada received his Ph.D. in engineering from the University of Electro-Communications, Japan, in 2015. He was a Research Fellow (DC1) of the Japan Society for the Promotion of Science from 2012 to 2015. He served as an assistant professor at Ritsumeikan University, Japan (2015–2019), and was a visiting researcher at the University of Málaga, Spain, in 2018. From 2019 to 2023, he was an assistant professor at Tokyo Metropolitan University, Japan. Since 2023, he has been an associate professor at Saitama University, Japan.
His research interests include evolutionary computation, machine learning, and their applications. He is a member of IEEE, ACM, and several major academic societies in Japan related to AI and informatics. He has contributed to organizing major international conferences such as IEEE CoG 2020, ACM GECCO 2018, and IEEE WCCI 2024.
He received the Journal Paper Award from System and Information, the Society of Instrument and Control Engineers, in 2016, and the IEEE Computational Intelligence Society Japan Chapter Young Researcher Award in both 2018 and 2021.
Yaochu Jin received the BSc, MSc, and PhD degrees from the Electrical Engineering Department, Zhejiang University, Hangzhou, China, in 1988, 1991, and 1996, respectively. He received the Dr.-Ing. from the Institute of Neuroinformatics, Ruhr University Bochum, Germany, in 2001.
He is presently Chair Professor of AI, Head of the Artificial Intelligence Department, and Director of the Trustworthy and General AI Laboratory at the School of Engineering, Westlake University, Hangzhou, China. Prior to that, he was “Alexander von Humboldt Professor for Artificial Intelligence” endowed by the German Federal Ministry of Education and Research, with the Faculty of Technology, Bielefeld University, Germany, from 2021 to 2023, and Surrey Distinguished Chair, Professor in Computational Intelligence, Department of Computer Science, University of Surrey, Guildford, U.K., from 2010 to 2021. He was also “Finland Distinguished Professor” with the University of Jyväskylä, Finland, and “Changjiang Distinguished Visiting Professor” with Northeastern University, China, from 2015 to 2017. His main research interests include AI theory, algorithms, and applications to a wide range of scientific, technological, and industrial problems.
Prof. Jin is presently the President of the IEEE Computational Intelligence Society and the Editor-in-Chief of Complex \& Intelligent Systems. He is the recipient of the 2025 IEEE Frank Rosenblatt Award. He was named “Highly Cited Researcher” by Clarivate consecutively since 2019. He is a Member of Academia Europaea and Fellow of IEEE.

Contact

TBA

Page updated

Google Sites

Report abuse

IEEE WCCI2026-CEC Workshop on Generative and Adaptive Surrogate Models for Evolutionary Algorithms