LLMs for Optimization: Modeling, Solving, and Validating with Generative AI

Optimization is a foundational pillar of artificial intelligence (AI), underpinning core techniques in planning, scheduling, decision-making, and machine learning. Yet despite decades of algorithmic advances, widespread adoption of state-of-the-art optimization solvers remains limited by the substantial expertise required for effective modeling and solving. This expertise barrier means that powerful optimization tools remain largely inaccessible to non-experts, with most users of leading solvers holding advanced degrees.

Recent advances in generative AI, particularly large language models (LLMs), offer a promising new path for democratizing optimization. By automating key steps in the optimization pipeline – from model formulation through solver configuration to model validation – LLMs promise to broaden access to powerful optimization tools. However, these models rarely work out of the box for complex reasoning tasks like optimization.

This tutorial surveys emerging research on LLMs for mathematical optimization, highlighting both practical systems and open research questions. We will provide a comprehensive overview of how LLMs can support each stage of the optimization pipeline, including model formulation, solver configuration, and validation. The tutorial is designed to be accessible to attendees without prior experience in either field, offering both conceptual frameworks and practical insights for this rapidly evolving area of research.

Tutorial

AAAI 2026 Schedule — January 20th, 2026

Section	Speaker	Duration	Slides
Introduction to Optimization and LLMs	Connor Lawless	30 minutes	Slides
Model Formulation	Connor Lawless	90 minutes	Slides
Break		30 minutes
Model Solving	Ellen Vitercik	60 minutes	Slides
Model Validation and Open Questions	Connor Lawless	30 minutes	Slides

Recommended Reading

This is a subset of the (growing) body of work on LLMs for optimization. If you see anything missing or have a suggestion, feel free to reach out!
Year	Title	Author	Topic	Link
Overview and Position Papers
2024	From Large Language Models and Optimization to Decision Optimization CoPilot: A Research Manifesto	Segev Wasserkrug, Leonard Boussioux, Dick den Hertog, Farzaneh Mirzazadeh, Ilker Birbil, Jannis Kurtz, Donato Maragno	Position paper on combining large language models and optimization	arXiv:
2025	"It Was a Magical Box": Understanding Practitioner Workflows and Needs in Optimization	Connor Lawless, Jakob Schoeffer, Madeleine Udell	Qualitative study of optimization practitioners	arXiv:
2025	Democratizing Optimization with Generative AI	David Simchi-Levi, Tinglong Dai, Ishai Menache, Michelle Xiao Wu	Position paper on benefits of combining optimization and generative AI	SSRN:
Model Formulation
2024	"I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming	Connor Lawless, Jakob Schoeffer, Lindy Le, Kael Rowan, Shilad Sen, Cristina St. Hill, Jina Suh, Bahareh Sarrafzadeh	Includes application to meeting scheduling	arXiv:
2025	OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale	Ali AhmadiTeshnizi, Wenzhi Gao, Herman Brunborg, Shayan Talaei, Connor Lawless, Madeleine Udell	Agentic framework	arXiv:
2025	Autoformulation of Mathematical Optimization Models Using LLMs	Nicolas Astorga, Tennison Liu, Yuanzhang Xiao, Mihaela van der Schaar	Uses Monte-Carlo Tree Search to explore formulation space	arXiv:
2025	ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling	Chenyu Huang, Zhengyang Tang, Shixi Hu, Ruoqing Jiang, Xin Zheng, Dongdong Ge, Benyou Wang, Zizhuo Wang	Fine-tuning based approach	arXiv:
2025	Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generation	Vinicius Lima, Dzung T. Phan, Jayant Kalagnanam, Dhaval Patel, Nianjun Zhou	Improved synthetic data generation pipeline	arXiv:
2025	OptiMind: Teaching LLMs to Think Like Optimization Experts	Xinzhi Zhang, Zeyi Chen, Humishka Zope, Hugo Barbalho, Konstantina Mellou, Marco Molinaro, Janardhan Kulkarni, Ishai Menache, Sirui Li	Integrates optimization expertise into pipeline	arXiv:
2025	OptiHive: Ensemble Selection for LLM-Based Optimization via Statistical Modeling	Maxime Bouscary, Saurabh Amin	Ensembling LLM-based models with statistical inference	arXiv:
Model Evaluation
2024	Towards Human-aligned Evaluation for Linear Programming Word Problems	Linzi Xing, Xinglu Wang, Yuxi Feng, Zhenan Fan, Jing Xiong, Zhijiang Guo, Xiaojin Fu, Rindra Ramamonjison, Mahdi Mostajabdaveh, Xiongwei Han, Zirui Zhou, Yong Zhang	Graph-edit based definition	arXiv:
2025	EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations	Haotian Zhai, Connor Lawless, Ellen Vitercik, Liu Leqi	Introduces a formal definition for checking equivalent formulations	arXiv:
Model Solving
2024	Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model	Fei Liu, Xialiang Tong, Mingxuan Yuan, Xi Lin, Fu Luo, Zhenkun Wang, Zhichao Lu, Qingfu Zhang	Evolutionary search applied to heuristics	arXiv:
2025	LLMs for Cold-Start Cutting Plane Separator Configuration	Connor Lawless, Yingxi Li, Anders Wikum, Madeleine Udell, Ellen Vitercik	Investigates LLMs for solver configuration	arXiv:
2025	EvoCut: Strengthening Integer Programs via Evolution-Guided Language Models	Milad Yazdani, Mahdi Mostajabdaveh, Samin Aref, Zirui Zhou	Evolutionary search applied to cutting planes	arXiv:
2025	DHEvo: Data-Algorithm Based Heuristic Evolution for Generalizable MILP Solving	Zhihao Zhang, Siyuan Li, Chenxi Li, Feifan Liu, Mengjing Chen, Kai Li, Tao Zhong, Bo An, Peng Liu	Investigates LLMs for primal heuristics	arXiv:
Model Validation
2023	Large Language Models for Supply Chain Optimization	Beibin Li, Konstantina Mellou, Bo Zhang, Jeevan Pathuri, Ishai Menache	Q&A for Supply Chain Optimization	arXiv:
2023	Diagnosing infeasible optimization problems using large language models	Hao Chen, Gonzalo E Constante-Flores, Can Li	Interface for infeasibility diagnosis	arXiv:
2025	OptiChat: Bridging Optimization Models and Practitioners with Large Language Models	Hao Chen, Gonzalo Esteban Constante-Flores, Krishna Sri Ipsit Mantri, Sai Madhukiran Kompalli, Akshdeep Singh Ahluwalia, Can Li	Q&A for General Optimization Models	arXiv:

About Us

Léonard Boussioux (University of Washington): Léonard Boussioux is an Assistant Professor of Information Systems at the University of Washington Foster School of Business and adjunct at the Allen School of Computer Science & Engineering. His research combines multimodal AI with optimization frameworks to develop human-AI collaboration systems for healthcare, sustainability, and innovation. He has received numerous awards, including the MIT Goodwin Medal.
Connor Lawless (Stanford): Connor Lawless is a Human-Centered AI postdoctoral researcher at Stanford, with a PhD in Operations Research and Information Engineering from Cornell. His work blends machine learning, computational optimization, and human–computer interaction to create human-centered artificial intelligence.
Madeleine Udell (Stanford): Madeleine Udell is an Assistant Professor of Management Science and Engineering at Stanford University. Her research uses optimization and machine learning to simplify large-scale data analysis, with real-world applications in healthcare, finance, marketing, and engineering systems. She has received numerous awards, including the Kavli Fellowship and the Alfred P. Sloan Research Fellowship.
Ellen Vitercik (Stanford): Ellen Vitercik is an Assistant Professor at Stanford with a joint appointment between the Management Science & Engineering and Computer Science departments. Her research—which has been recognized with a Schmidt Sciences AI2050 Early Career Fellowship and an NSF CAREER award, among other honors—spans machine learning and discrete optimization.