English

LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs

Artificial Intelligence 2026-05-12 v1 Optimization and Control

Abstract

Efficient branching policies are essential for accelerating Mixed Integer Linear Programming (MILP) solvers. Their design has long relied on hand-crafted heuristics, and now machine learning has emerged as a promising paradigm to automate this process. However, existing learning-based methods are often hindered by their dependence on expensive expert demonstrations and the gap between training objectives and the solver's end-to-end performance. In this work, we propose LLM4Branch, a novel framework that leverages Large Language Models (LLMs) to automate the discovery of efficient branching policies. Specifically, the discovered policy is an executable program with a program skeleton generated by the LLM and a parameter vector, which is optimized via a zeroth-order method over a few instances with their end-to-end performance feedback. Extensive experiments on standard MILP benchmarks demonstrate that LLM4Branch establishes a new state-of-the-art among CPU-based methods and achieves performance competitive with advanced GPU-based models. Codes are available at https://github.com/hzn18/LLM4Branch.

Keywords

Cite

@article{arxiv.2605.10401,
  title  = {LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs},
  author = {Zhinan Hou and Xingchen Li and Yankai Zhang and Tianxun Li and Keyou You},
  journal= {arXiv preprint arXiv:2605.10401},
  year   = {2026}
}

Comments

ICML2026 preprint, camera ready in progress

R2 v1 2026-07-22T07:04:11.097Z