6 papers · 1 filter
Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics
Zubin Zheng, Jiahao Wu, Shaofeng Zhang +3
On-policy distillation (OPD) trains multi-turn language agents with dense teacher supervision on student-generated responses. However, standard think-then-act rollouts require leng…
Not All Problems Are Best Modeled as MILP: A DSL-Centric Framework for Flexible and Accurate Optimization Modeling
Shaofeng Zhang, Hongyuan Su, Qingwen Peng +4
Solving combinatorial optimization problems (COPs) requires not only efficient algorithms but also carefully crafted formulations. While recent works have leveraged LLMs to automat…
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…
MuEvo: LLM-Driven Evolution of Multi-Heuristic Ensemble
Haoze Lv, Ning Lu, Shengcai Liu +2
Large language model-based automated heuristic design (LLM-AHD) has shown strong potential in discovering effective heuristics for combinatorial optimization problems. However, exi…
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…
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…