arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.01455cs.AIcs.LGquant-ph
收藏

面向组合优化的可行性感知大语言模型

Infeasibility Aware Large Language Models for Combinatorial Optimization

Lehigh University(莱荷大学);University of Pittsburgh(匹兹堡大学);Johnson & Johnson(强生公司)

Yakun Wang, Min Chen, Zeguan Wu, Junyu Liu, Sitao Zhang, Zhenwen Shao

AI总结:

本文提出一种结合可验证数据集构建、监督微调和LLM辅助下游搜索的框架,用于解决组合优化问题中的可行性检测,实验显示模型在准确率和搜索速度上有显著提升。

摘要:

大型语言模型(LLMs)正被越来越多地用于NP难的组合优化问题,但现有方法大多强调可行实例的解决方案生成,而未明确处理不可行性检测。我们提出了一种感知可行性的框架,结合可验证数据集构建、监督微调和LLM辅助的下游搜索。针对minor-embedding问题,我们引入了新的数学规划公式,并提出了可证明的零相位不可行性筛查,从而实现了可扩展的训练实例构建,这些实例被标记为可行或可证明不可行。使用通过此精确优化管道生成的训练数据,我们展示了8B参数的LLM可以微调以联合执行解决方案生成和不可行性检测。我们进一步利用LLM输出作为下游局部搜索的预热启动,提供了一种在LLM输出不完美的情况下加速优化的实用方法。实验表明,微调后的模型在整体准确率上比GPT-5.2提高了高达30%;同时,LLM引导的预热启动在下游局部搜索中相比从头开始快了2倍。

英文摘要:

Large language models (LLMs) are increasingly explored for NP-hard combinatorial optimization problems, but most existing methods emphasize feasible-instance solution generation and do not explicitly address infeasibility detection. We propose an infeasibility-aware framework that combines certifiable dataset construction, supervised fine-tuning, and LLM-assisted downstream search. For the minor-embedding problem, we introduce a new mathematical programming formulation together with provable zero-phase infeasibility screening, which enables scalable construction of training instances labeled either as feasible with structured certificates or as certifiably infeasible. Using training data generated through this exact optimization pipeline, we show that an 8B-parameter LLM can be fine-tuned to jointly perform solution generation and infeasibility detection. We further utilize LLM outputs as warm starts for downstream local search, providing a practical way to accelerate optimization even when the LLM outputs are imperfect. Experiments show that our fine-tuned model improves overall accuracy by up to 30\% over GPT-5.2; meanwhile LLM-guided warm starts provide up to $2\times$ speedup compared with starting from scratch in downstream local search.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑