collaborators

8 papers

cs.AI2026

Evolving Parallel Algorithm Portfolios via Potential-Aware Instance Generation with LLMs

Shaofeng Zhang, Shengcai Liu, Zhiyuan Wang +1

The Automatic Construction of Portfolios via Large Language Models (LLM-ACP) suffers from poor generalization in practical few-shot scenarios when solving complex combinatorial opt…

cs.AI2026

Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training

Zhiyuan Wang, Shengcai Liu, Jiahao Wu +5

Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive. Evolution strategies (ES) enable memory-ef…

cs.NE2026

MEGO: Learning Mixture-of-Experts for General-Purpose Binary Optimization

Shengcai Liu, Zhiyuan Wang, Yew-Soon Ong +2

Discrete optimization is ubiquitous in science and engineering. The vast array of existing discrete optimization problems, coupled with the continuous emergence of new ones, necess…

cs.NE2026

General-Purpose Co-Evolutionary Construction of Parallel Algorithm Portfolios for Multi-Objective Binary Optimization

Zhiyuan Wang, Shengcai Liu, Shaofeng Zhang +1

Despite recent progress in constructing generalizable parallel algorithm portfolios (PAPs), no general-purpose approach is yet available for multi-objective binary optimization pro…

cs.NE2025

A Novel Population Initialization Method via Adaptive Experience Transfer for General-Purpose Binary Evolutionary Optimization

Zhiyuan Wang, Shengcai Liu, Shaofeng Zhang +1

Evolutionary Algorithms (EAs) are widely used general-purpose optimization methods due to their domain independence. However, under a limited number of function evaluations (#FEs),…

cs.NE2025

Evolving Generalizable Parallel Algorithm Portfolios for Binary Optimization Problems via Domain-Agnostic Instance Generation

Zhiyuan Wang, Shengcai Liu, Peng Yang +1

Generalization is the core objective when training optimizers from data. However, limited training instances often constrain the generalization capability of the trained optimizers…