arXiv cs.AI· Ke Zhao, Zixiang Di, Hong Qian, Xiang Shu, Yaolin Wen, Qitao Shi, Bingdong Li, Xingyu Lu, Xiangfeng Wang, Jun Zhou, Ke Tang, Yang Yu·· 3 小时前AI 评分39
MiniOpt：以有限资源通过推理建模求解通用优化问题
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources
AI 导读
MiniOpt 是一个轻量级优化专用大语言模型，采用推理建模求解范式与基于可验证奖励的强化学习（RLVR）两阶段训练框架。在 8 个优化基准上，其表现持续超越现有基于学习的优化模型，且所需参数与训练数据显著更少。参数解耦评测显示，其性能提升主要源于更强的优化结构理解，代码已开源。
正文 · 原文
Authors:Ke Zhao, Zixiang Di, Hong Qian, Xiang Shu, Yaolin Wen, Qitao Shi, Bingdong Li, Xingyu Lu, Xiangfeng Wang, Jun Zhou, Ke Tang, Yang Yu
Abstract:Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs). Existing learning-based methods, however, typically require large-scale supervised data, expensive intermediate step verification, and extensive computational resources, while exhibiting limited optimization generalization across diverse optimization structures. In this paper, we propose \textsc{MiniOpt}, a lightweight optimization-specialized LLM trained through a reasoning-to-model-and-solve paradigm and a two-stage training framework with reinforcement learning with verifiable rewards (RLVR). MiniOpt encourages structure-oriented optimization learning by reinforcing the completeness of optimization formulations and optimization outcomes. Extensive experiments on eight optimization benchmarks demonstrate that MiniOpt consistently outperforms existing learning-based optimization models while requiring substantially fewer parameters and training data. To further understand optimization generalization, we introduce a complementary parameter-decoupled evaluation protocol that disentangles optimization structure understanding from numerical parameter processing. The results reveal that MiniOpt preserves optimization capability under parameter-decoupled settings significantly better than previous optimization-specialized models, suggesting that its performance gains primarily originate from stronger optimization structure understanding. These findings demonstrate an effective pathway toward efficient and generalizable optimization-specialized LLMs. The code is available at this https URL.
| Comments: | 36 pages, 9 figures, 11 tables, project: this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.25832 [cs.LG] |
| (or arXiv:2606.25832v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2606.25832 arXiv-issued DOI via DataCite |
Submission history
From: Ke Zhao [view email]
[v1]
Wed, 24 Jun 2026 13:48:06 UTC (530 KB)
[v2]
Thu, 25 Jun 2026 05:38:04 UTC (530 KB)
[v3]
Thu, 12 Nov 2026 14:32:46 UTC (843 KB)
来源：arXiv cs.AI · arxiv.org