Help
Cart
Skip main navigation

Available Issues

July 20, 2022 - June 3, 2026

Available Issues

July 20, 2022 - June 3, 2026

OptiChat: Bridging Optimization Models and Practitioners with Large Language Models

Published Online:7 Nov 2025https://doi.org/10.1287/ijds.2025.0074

References

  • AhmadiTeshnizi A, Gao W, Udell M (2023) OptiMUS: Optimization modeling using MIP solvers and large language models. Accessed October 30, https://arxiv.org/abs/2310.06116.Google Scholar
  • Ahmaditeshnizi A, Gao W, Udell M (2024) OptiMUS: Scalable optimization modeling with (MI)LP solvers and large language models. Salakhutdinov R, Kolter Z, Heller K, Weller A, Oliver N, Scarlett J, Berkenkamp F, eds. Proc. 41st Internat. Conf. Machine Learn., vol. 235 (PMLR, New York), 577–596.Google Scholar
  • AhmadiTeshnizi A, Gao W, Brunborg H, Talaei S, Udell M (2025) OptiMUS-0.3: Using large language models to model and solve optimization problems at scale. Accessed August 27, https://arxiv.org/abs/2407.19633.Google Scholar
  • Astorga N, Liu T, Xiao Y, van der Schaar M (2024) Autoformulation of mathematical optimization models using LLMs. Preprint, submitted November 3, https://arxiv.org/abs/2411.01679.Google Scholar
  • Badini S, Regondi S, Frontoni E, Pugliese R (2023) Assessing the capabilities of ChatGPT to improve additive manufacturing troubleshooting. Advanced Indust. Engrg. Polymer Res. 6(3):278–287.Google Scholar
  • Bertsimas D, Stellato B (2021) The voice of optimization. Machine Learn. 110(2):249–277.Google Scholar
  • Bertsimas D, Tsitsiklis J (1997) Introduction to Linear Optimization, 1st ed. (Athena Scientific, Nashua, NH).Google Scholar
  • Boiko DA, MacKnight R, Kline B, Gomes G (2023) Autonomous chemical research with large language models. Nature 624(7992):570–578.Google Scholar
  • Bran AM, Cox S, Schilter O, Baldassari C, White AD, Schwaller P (2024) Augmenting large language models with chemistry tools. Nature Machine Intelligence 6(5):525–535.Google Scholar
  • Chen H, Constante-Flores GE, Li C (2024) Diagnosing infeasible optimization problems using large language models. INFOR Inform. Systems Oper. Res. 62(4):573–587.Google Scholar
  • Chinneck JW (2008) Feasibility and Infeasibility in Optimization, vol. 118 (Springer US, New York).Google Scholar
  • Chinneck JW, Dravnieks EW (1991) Locating minimal infeasible constraint sets in linear programs. ORSA J. Comput. 3(2):157–168.Link, Google Scholar
  • Collins A, Magazzeni D, Parsons S (2019) Towards an argumentation-based approach to explainable planning. ICAPS 2019 Workshop XAIP Program Chairs, vol. 16 (OpenReview.net).Google Scholar
  • Čyras K, Lee M, Letsios D (2021) Schedule explainer: An argumentation-supported tool for interactive explanations in makespan scheduling. Internat. Workshop Explainable Transparent Autonomous Agents Multi-Agent Systems (Springer-Verlag, Berlin, Heidelberg), 243–259.Google Scholar
  • Čyras K, Letsios D, Misener R, Toni F (2019) Argumentation for explainable scheduling. Proc. AAAI Conf. Artificial Intelligence, vol. 33 (AAAI Press, Palo Alto, CA), 2752–2759.Google Scholar
  • Dowling M, Lucey B (2023) ChatGPT for (finance) research: The Bananarama conjecture. Financial Res. Lett. 53:103662.Google Scholar
  • Forel A, Parmentier A, Vidal T (2023) Explainable data-driven optimization: From context to decision and back again. Krause A, Brunskill E, Cho K, Engelhardt B, Sabato S, Scarlett J, eds. Proc. 40th Internat. Conf. Machine Learn., vol. 202 (PMLR, New York), 10170–10187.Google Scholar
  • Goerigk M, Hartisch M (2023) A framework for inherently interpretable optimization models. Eur. J. Oper. Res. 310(3):1312–1324.Google Scholar
  • Greenberg H (1983) A functional description of ANALYZE: A computer-assisted analysis system for linear programming models. ACM Trans. Math. Software 9(1):18–56.Google Scholar
  • Greenberg HJ (1987) Analyze: A computer-assisted analysis system for linear programming models. Oper. Res. Lett. 6(5):249–255.Google Scholar
  • Guieu O, Chinneck JW (1999) Analyzing infeasible mixed-integer and integer linear programs. INFORMS J. Comput. 11(1):63–77.Link, Google Scholar
  • Gurobi Optimization LLC (2022) Gurobi innovation lab. Shaping the future of optimization, together. Accessed June 13, 2024, https://www.gurobi.com.Google Scholar
  • Hart WE, Watson J-P, Woodruff DL (2011) Pyomo: Modeling and solving mathematical programs in Python. Math. Programming Comput. 3(3):219–260.Google Scholar
  • Huang C, Tang Z, Hu S, Jiang R, Zheng X, Ge D, Wang B, Wang Z (2025) ORLM: A customizable framework in training large models for automated optimization modeling. Oper. Res., ePub ahead of print May 8, https://doi.org/10.1287/opre.2024.1233.Google Scholar
  • IBM (2022) IBM ILOG CPLEX 22.1.0. User’s manual for CPLEX. Accessed June 13, 2024, https://www.ibm.com/docs/en/icos/22.1.0?topic=optimizers-users-manual-cplex.Google Scholar
  • Jablonka KM, Schwaller P, Ortega-Guerrero A, Smit B (2024) Leveraging large language models for predictive chemistry. Nature Machine Intelligence 6(2):161–169.Google Scholar
  • Ji Z, Lee N, Frieske R, Yu T, Su D, Xu Y, Ishii E, Bang YJ, Madotto A, Fung P (2023) Survey of hallucination in natural language generation. ACM Comput. Surveys 55(12):248.Google Scholar
  • Ju D, Jiang S, Cohen A, Foss A, Mitts S, Zharmagambetov A, Amos B, et al. (2024) To the globe (TTG): Towards language-driven guaranteed travel planning. Preprint, submitted October 21, https://arxiv.org/abs/2410.16456.Google Scholar
  • Karimi AH, Barthe G, Balle B, Valera I (2020) Model-agnostic counterfactual explanations for consequential decisions. Chiappa S, Calandra R, eds. Proc. Twenty Third Internat. Conf. Artificial Intelligence Statist., vol. 108 (PMLR, New York), 895–905.Google Scholar
  • Kikuta D, Ikeuchi H, Tajiri K, Nakano Y (2024) RouteExplainer: An explanation framework for vehicle routing problem. Pacific-Asia Conf. Knowledge Discovery Data Mining (Springer-Verlag, Berlin, Heidelberg), 30–42.Google Scholar
  • Lawless C, Schoeffer J, Le L, Rowan K, Sen S, St. Hill C, Suh J, Sarrafzadeh B (2024) “I want it that way”: Enabling interactive decision support using large language models and constraint programming. ACM Trans. Interactive Intelligent Systems 14(3):22.Google Scholar
  • Li B, Mellou K, Zhang B, Pathuri J, Menache I (2023a) Large language models for supply chain optimization. Preprint, submitted July 13, https://arxiv.org/abs/2307.03875.Google Scholar
  • Li Y, Gao C, Song X, Wang X, Xu Y, Han S (2023b) DrugGPT: A GPT-based strategy for designing potential ligands targeting specific proteins. Preprint, submitted June 30, https://doi.org/10.1101/2023.06.29.543848.Google Scholar
  • Lin Z, Akin H, Rao R, Hie B, Zhu Z, Lu W, Smetanin N, et al. (2023) Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379(6637):1123–1130.Google Scholar
  • Lopez-Lira A, Tang Y (2024) Can ChatGPT forecast stock price movements? Return predictability and large language models. Preprint, submitted September 11, https://arxiv.org/abs/2304.07619.Google Scholar
  • Lumbreras S, Tejada D, Elechiguerra D (2024) Explaining the solutions of the unit commitment with interpretable machine learning. Internat. J. Electr. Power Energy Systems 160:110106.Google Scholar
  • Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. Proc. 31st Internat. Conf. Neural Inform. Processing Systems NIPS’17 (Curran Associates Inc., Red Hook, NY), 4768–4777.Google Scholar
  • Luo R, Sun L, Xia Y, Qin T, Zhang S, Poon H, Liu TY (2022) BioGPT: Generative pre-trained transformer for biomedical text generation and mining. Briefings Bioinformatics 23(6):bbac409.Google Scholar
  • MOSEK ApS (2023) MOSEK optimizer API for Python 10.1.8. Accessed June 13, 2024, https://docs.mosek.com/latest/capi/index.html.Google Scholar
  • OpenAI (2023) GPT-4 technical report. Preprint, submitted March 15, https://arxiv.org/abs/2303.08774.Google Scholar
  • Ramamonjison R, Yu TT, Li R, Li H, Carenini G, Ghaddar B, He S, et al. (2023) NL4Opt competition: Formulating optimization problems based on their natural language descriptions. Preprint, submitted March 27, https://arxiv.org/abs/2303.08233.Google Scholar
  • Rardin RL (2016) Optimization in Operations Research, 2nd ed. (Pearson Education, Hoboken, NJ).Google Scholar
  • Ribeiro MT, Singh S, Guestrin C (2016) “Why should I trust you?”: Explaining the predictions of any classifier. Proc. 22nd ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining KDD‘16 (Association for Computing Machinery, New York), 1135–1144.Google Scholar
  • Romera-Paredes B, Barekatain M, Novikov A, Balog M, Kumar MP, Dupont E, Ruiz FJR, et al. (2024) Mathematical discoveries from program search with large language models. Nature 625(7995):468–475.Google Scholar
  • Sallam M (2023) ChatGPT utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns. Healthcare (Basel) 11(6):887.Google Scholar
  • Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-CAM: Visual explanations from deep networks via gradient-based localization. 2017 IEEE Internat. Conf. Comput. Vision (ICCV) (IEEE, Piscataway, NJ), 618–626.Google Scholar
  • Slack D, Krishna S, Lakkaraju H, Singh S (2023) Explaining machine learning models with interactive natural language conversations using TalkToModel. Nature Machine Intelligence 5(8):873–883.Google Scholar
  • Tamiz M, Mardle SJ, Jones DF (1996) Detecting IIS in infeasible linear programmes using techniques from goal programming. Comput. Oper. Res. 23(2):113–119.Google Scholar
  • Tang Z, Huang C, Zheng X, Hu S, Wang Z, Ge D, Wang B (2025) ORLM: Training large language models for optimization modeling. Preprint, submitted April 4, https://arxiv.org/abs/2405.17743.Google Scholar
  • Thawkar O, Shaker A, Mullappilly SS, Cholakkal H, Anwer RM, Khan S, Laaksonen J, Khan FS (2025) XrayGPT: Chest radiographs summarization using medical vision-language models. Preprint, submitted May 7, https://arxiv.org/abs/2306.07971.Google Scholar
  • Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M-A, Lacroix T, Rozière B, et al. (2023) LLaMA: Open and efficient foundation language models. Preprint, submitted February 23, https://arxiv.org/abs/2302.13971.Google Scholar
  • van Stein N, Vermetten D, Bäck T (2025) In-the-loop hyper-parameter optimization for LLM-based automated design of heuristics. ACM Trans. Evolutionary Learn. (Association for Computing Machinery, New York).Google Scholar
  • Wang X, Anwer N, Dai Y, Liu A (2023) ChatGPT for design, manufacturing, and education. Procedia CIRP 119:7–14.Google Scholar
  • Wu S, Irsoy O, Lu S, Dabravolski V, Dredze M, Gehrmann S, Kambadur P, Rosenberg D, Mann G (2023b) BloombergGPT: A large language model for finance. Preprint, submitted December 21, https://arxiv.org/abs/2303.17564.Google Scholar
  • Wu Q, Bansal G, Zhang J, Wu Y, Li B, Zhu E, Jiang L, et al. (2023a) AutoGen: Enabling next-gen LLM applications via multi-agent conversation. Preprint, submitted October 3, https://arxiv.org/abs/2308.08155.Google Scholar
  • Xiao Z, Zhang D, Wu Y, Xu L, Wang YJ, Han X, Fu X, et al. (2024) Chain-of-experts: When LLMs meet complex operations research problems. Twelfth Internat. Conf. Learn. Representations (OpenReview.net).Google Scholar
  • Yang Z, Wang Y, Huang Y, Guo Z, Shi W, Han X, Feng L, Song L, Liang X, Tang J (2024) OptiBench meets resocratic: Measure and improve LLMs for optimization modeling. Preprint, submitted July 13, https://arxiv.org/abs/2407.09887.Google Scholar
Previous
Back to Top
INFORMS site uses cookies to store information on your computer. Some are essential to make our site work; Others help us improve the user experience. By using this site, you consent to the placement of these cookies. Please read our Privacy Statement to learn more.
Agree