5 papers
GraphBU: MILP Instance Generation with Graph-Native Block Units
Xiaolei Guo, Chenyu Zhou, Jianghao Lin +1
Mixed-integer linear programming (MILP) instances used for solver development are hard to obtain when models come from private or application-specific pipelines. A generator must k…
OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling
Yitian Chen, Cheng Cheng, Yinan Sun +2
We investigate the capabilities and scalability of Large Language Models (LLMs) in optimization modeling, a domain requiring structured reasoning and precise formulation. To this e…
Auto-Formulating Dynamic Programming Problems with Large Language Models
Chenyu Zhou, Jingyuan Yang, Linwei Xin +3
Dynamic programming (DP) is a fundamental method in operations research, but formulating DP models has traditionally required expert knowledge of both the problem context and DP te…
StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Models
Chenyu Zhou, Tianyi Xu, Jianghao Lin +1
Large Language Models (LLMs) have shown promising capabilities for solving Operations Research (OR) problems. While reinforcement learning serves as a powerful paradigm for LLM tra…
BenLOC: A Benchmark for Learning to Configure MIP Optimizers
Hongpei Li, Ziyan He, Yufei Wang +4
The automatic configuration of Mixed-Integer Programming (MIP) optimizers has become increasingly critical as the large number of configurations can significantly affect solver per…