Combinatorial Optimization — Selected Works

Overview

Combinatorial optimization underpins routing, scheduling, assignment, packing and resource-allocation systems. This research develops learning-based optimizers that complement exact mathematical programming and hand-crafted heuristics with evolutionary learning, genetic programming, neural solvers and large language models. The goal is to create solvers that adapt to dynamic environments, generalize across problem variants, remain robust under distribution shift and scale to industrial problem sizes.

Vehicle routingDynamic schedulingGenetic programmingNeural combinatorial optimizationReinforcement learningLLMs for optimization

Research Directions

• Evolutionary learning of heuristics: automatically discover routing, sequencing and dispatching rules rather than relying only on fixed human-designed heuristics.
• Quality and diversity: learn libraries of high-performing yet behaviorally different heuristics, giving decision makers robust alternatives as operating conditions change.
• Neural optimizer learning: train policies that infer high-quality solutions quickly and adapt offline knowledge during online deployment.
• Unified multitask solvers: share representations across related routing and scheduling variants while controlling task interference.
• Scalable graph learning: exploit hierarchical and non-Euclidean representations to capture global and local structure in large instances.
• LLM-assisted optimization: use language models for problem formulation, solution generation, automatic heuristic design, and coordinated formulation–algorithm co-design.

Keynotes

• Ong, Y. S., Multifactorial Evolutionary Computation with Applications in Machine Learning and Scientific Discovery (Keynote, 2024 IEEE World Congress on Computational Intelligence - Congress on Evolutionary Computation (IEEE WCCI-CEC 2024), Jun 30 - Jul 5, 2024, Yokohama, Japan). Details.
• Ong, Y. S., Multifactorial Optimization: Towards Evolutionary Multitasking (Keynote, Australasian Conference on Artificial Life and Computational Intelligence (ACALCI 2016), Canberra, Australia, 2-5 February 2016). Details.
• Ong, Y. S., Towards Evolutionary Multitasking: A New Paradigm in Evolutionary Computation (Keynote, The 6th International Symposium on Information and Communication Technology (SoICT 2015), Hue Royal city, Vietnam, 3 - 4 Dec 2015). Details.

Selected Publications

• 2026
  M. Xu, J. Chen, D. N. C. Nam, J. W. E. Tay, P. S. Tan, and Y. S. Ong.
  Niching Genetic Programming for Co-Joint Optimization: A Case Study on Replenishment and Transshipment Policies in Dynamic Multi-Site Inventory Management, Memetic Computing, 18(1).
• 2026
  N. Zhang, Z. Cao, J. Zhou, C. Zhang, and Y. S. Ong.
  An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems, International Conference on Learning Representations (ICLR 2026).
• 2026
  S. Liu, Z. Cao, N. Yin, and Y. S. Ong.
  Scale-Net: A Hierarchical U-Net Framework for Cross-Scale Generalization in Multi-Task Vehicle Routing, Proceedings of the AAAI Conference on Artificial Intelligence(AAAI 2026), 40(17), 14295–14303.
• 2026
  M. Xu, Y. Mei, F. Zhang, Y. S. Ong, and M. Zhang.
  Pareto Set Learning Through Genetic Programming for Multi-Objective Dynamic Scheduling, IEEE Transactions on Evolutionary Computation(TEVC 2026), 30(3), 942–956.
• 2025
  S. Liu, Z. Cao, S. Feng, and Y. S. Ong.
  A Mixed-Curvature Based Pre-Training Paradigm for Multi-Task Vehicle Routing Solver, Proceedings of the 42nd International Conference on Machine Learning(ICML 2025), PMLR 267, 38066–38101.
• 2025
  M. Xu, F. Neumann, A. Neumann, and Y. S. Ong.
  Quality Diversity Genetic Programming for Learning Scheduling Heuristics, Genetic and Evolutionary Computation Conference (GECCO 2025), 1090–1098.
• 2025
  J. Liu, Z. Sun, S. Feng, C. Chen, and Y. S. Ong.
  Language Model Evolutionary Algorithms for Recommender Systems: Benchmarks and Algorithm Comparisons, IEEE Transactions on Evolutionary Computation(TEVC 2025).
• 2024
  S. Liu, C. Chen, X. Qu, K. Tang, and Y. S. Ong.
  Large Language Models as Evolutionary Optimizers, IEEE Congress on Evolutionary Computation(CEC 2024), 1–8.
• 2024
  X. Chen, R. Bai, R. Qu, Y. S. Ong, H. Dong, J. Jang.
  Deep Reinforcement Learning Assisted Genetic Programming Ensemble Hyper-Heuristics for Dynamic Scheduling of Container Port Trucks, IEEE Transactions on Evolutionary Computation(TEVC 2024), 29(4), 1371-1385.
• 2022
  L. Feng, Y. Huang, I. W. Tsang, A. Gupta, K. Tang, K. C. Tan, and Y. S. Ong.
  Towards Faster Vehicle Routing by Transferring Knowledge From Customer Representation, IEEE Transactions on Intelligent Transportation Systems, 23(2), 952–965.
• 2019
  L. Feng, A. Gupta, and Y. S. Ong.
  Compressed Representation for Higher-Level Meme Space Evolution: A Case Study on Big Knapsack Problems, Memetic Computing, 11(1), 3–17.
• 2016
  G. Kim, Y. S. Ong, T. Cheong, and P. S. Tan.
  Solving the Dynamic Vehicle Routing Problem Under Traffic Congestion, IEEE Transactions on Intelligent Transportation Systems, 17(8), 2367–2380.
• 2016
  Y. Yuan, Y. S. Ong, A. Gupta, P. S. Tan, and H. Xu.
  Evolutionary Multitasking in Permutation-Based Combinatorial Optimization Problems: Realization With TSP, QAP, LOP, and JSP, IEEE Region 10 Conference (TENCON 2016), 3157–3164.
• 2015
  L. Feng, Y. S. Ong, M. H. Lim, and I. W. Tsang.
  Memetic Search With Interdomain Learning: A Realization Between CVRP and CARP, IEEE Transactions on Evolutionary Computation(TEVC 2015), 19(5), 644–658.
• 2015
  L. Feng, Y. S. Ong, A. H. Tan, and I. W. Tsang.
  Memes as Building Blocks: A Case Study on Evolutionary Optimization + Transfer Learning for Routing Problems, Memetic Computing, 7(3), 159–180.