OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale
School of Management Science and Engineering, Stanford University(斯坦福大学管理科学与工程学院);Institute for Computational and Mathematical Engineering, Stanford University(斯坦福大学计算与数学工程研究所)
Ali AhmadiTeshnizi, Wenzhi Gao, Herman Brunborg, Shayan Talaei, Connor Lawless, Madeleine Udell
备注:
This paper documents OptiMUS-0.3, improving on OptiMUS-0.1 (arXiv:2310.06116) and OptiMUS-0.2 (arXiv:2402.10172). arXiv admin note: text overlap with arXiv:2402.10172
优化问题广泛存在于制造、分销到医疗等领域,但大多数问题仍通过启发式方法手工解决,而非最优的求解器。本文介绍一个基于大语言模型的系统,能够从自然语言描述中构建和解决(混合整数)线性规划问题。系统可生成数学模型、编写并调试求解器代码、评估生成的解决方案,并根据评估结果改进模型和代码的效率与正确性。OptiMUS-0.3采用模块化结构处理问题,可处理长描述和复杂数据而无需长提示。实验表明,OptiMUS-0.3在易实例中比直接提示基线高出43%,在难实例中高出18%。在基准问题上,它与微调专家模型竞争,但在实际案例中表现更优(28.6% vs. 0%)。消融研究显示,模块化架构与错误纠正是性能提升的关键。关键发现是系统架构比模型能力更能驱动性能。结构分解与针对性错误纠正使弱模型在简单提示下可匹配强模型,并在不重新训练的情况下与微调专家模型竞争。
英文摘要:
Optimization problems are pervasive in sectors from manufacturing and distribution to healthcare. However, most such problems are still solved heuristically by hand rather than optimally by state-of-the-art solvers because the expertise required to formulate and solve these problems limits the widespread adoption of optimization tools and techniques. We introduce a Large Language Model (LLM)-based system designed to formulate and solve (mixed integer) linear programming problems from their natural language descriptions. Our system can develop mathematical models, write and debug solver code, evaluate the generated solutions, and improve efficiency and correctness of its model and code based on these evaluations. OptiMUS is designed as a productivity tool for optimization practitioners who understand the problem domain and can describe it precisely, but seek to accelerate the modeling and implementation workflow. OptiMUS-0.3 utilizes a modular structure to process problems, allowing it to handle problems with long descriptions and complex data without long prompts. Experiments demonstrate that OptiMUS-0.3 outperforms direct-prompting baselines by over 43% on easy and 18% on hard instances. It remains competitive with fine-tuned specialist models on benchmark problems, and outperforms them on real-world case studies (28.6% vs. 0%) where fine-tuned models fail to generalize. Ablation studies show that modular architecture with error correction is central to these gains. A key finding is that system architecture is a stronger driver of performance than model capability. Structured decomposition with targeted error correction enables weaker models to match stronger models under naive prompting, and remains competitive with fine-tuned specialist models without retraining costs.
Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization
School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen Campus)(计算机科学与技术学院,哈尔滨工业大学(深圳校区));Pengcheng Laboratory(鹏城实验室);School of Information Science and Technology, Harbin Institute of Technology (Shenzhen Campus)(信息科学与技术学院,哈尔滨工业大学(深圳校区));Shenzhen Loop Area Institute(深圳河套学院)
From Natural Language to Solver-Ready Power System Optimization: An LLM-Assisted, Validation-in-the-Loop Framework
Department of Electrical and Computer Engineering(电气与计算机工程系);University of Southern California(南加州大学);Department of Electrical Engineering(电气工程系);University of Texas at Arlington(德克萨斯大学阿灵顿分校);Interdisciplinary Science Department(跨学科科学系);Brookhaven National Laboratory(布鲁赫斯国家实验室)
Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling
Cardinal Operations, China(中国卡迪纳尔运营公司);Shanghai University of Finance and Economics(上海财经大学);The University of Hong Kong(香港大学);Antai School of Economics and Management, Shanghai Jiao Tong University(上海交通大学安泰经济管理学院);Department of Management Science and Engineering, Stanford University(斯坦福大学管理科学与工程系)
YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate
Hyperparameter Optimization of Constraint Programming Solvers
Interdisciplinary Centre for Security, Reliability and Trust (SnT)(安全、可靠性与信任跨学科中心);University of Luxembourg(卢森堡大学);Faculty of Science, Technology and Medicine (FSTM)(科学、技术与医学学院)
Learning to Model Optimization Problems from Solver Outcomes
School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
A general optimization solver based on OP-to-MaxSAT reduction
School of Software Engineering, South China University of Technology(华南理工大学软件学院);School of Software Engineering, Sun Yat-sen University(中山大学软件学院);Department of Mathematics, College of Science, Shantou University(汕头大学理学院数学系)