Author

Shao-Feng Zhang

h-index 2 View on Semantic Scholar

We have 5 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics

On-policy distillation (OPD) trains multi-turn language agents with dense teacher supervision on student-generated responses. However, standard think-then-act rollouts require lengthy reasoning before each short action, delaying environment transitions and experience collection. Generating actions directly reduces this...

Zu-Bin Zheng, Jiahao Wu, Shao-Feng Zhang et al. · 1 citation

Preprint Aug 2026

Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training

CoPES is introduced, a cooperative coevolutionary method that decomposes the full parameter space into lower-dimensional subspaces and searches over them cooperatively to improve optimization efficiency and demonstrate an improved trade-off between memory requirements and training time for agentic LLM post-training und...

Zhiyuan Wang, Sheng-Cai Liu, Jiahao Wu et al. · 2 citations

Preprint Aug 2026

Not All Problems Are Best Modeled as MILP: A DSL-Centric Framework for Flexible and Accurate Optimization Modeling

OptiDSL is proposed, a framework that shifts the focus from rigid MILP formulations to domain-specific language (DSL) representations, and enables seamless integration with a diverse library of specialized solvers, ranging from traditional heuristics to modern learning-based methods.

Shao-Feng Zhang, Hongyuan Su, Qing Peng et al. · 0 citations

Preprint Aug 2026

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

The potential gain metric is proposed, a novel metric that eliminates the need for reference solutions and consistently outperforms state-of-the-art LLM-ACP baselines, notably achieving a 19.76% relative improvement for TSP Greedy Constructive portfolios.

Shao-Feng Zhang, Sheng-Cai Liu, Zhi-Yuan Wang et al. · 0 citations

Preprint Aug 2026

MuEvo: LLM-Driven Evolution of Multi-Heuristic Ensemble

Large language model-based automated heuristic design (LLM-AHD) has shown strong potential in discovering effective heuristics for combinatorial optimization problems. However, existing methods primarily optimize a single heuristic, whereas practical optimization frameworks often rely on multiple interacting components...

Haoze Lv, Ning Lu, Shengcai Liu et al. · 0 citations