mlsanityData to 14 Oct 2026

ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling

arXiv 2405.17743 ↗First posted 28 May 2024cs.CL cs.AI cs.CEcited by 124

Not on the map. Why?

Cited by 20 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Optimization modeling plays a critical role in the application of Operations Research (OR) tools to address real-world problems, yet they pose challenges and require extensive expertise from OR experts. With the advent of large language models (LLMs), new opportunities have emerged to streamline and automate such task. However, current research predominantly relies on closed-source LLMs such as GPT-4, along with extensive prompt engineering techniques. This reliance stems from the scarcity of high-quality training datasets for optimization modeling, resulting in elevated costs, prolonged processing times, and privacy concerns. To address these challenges, our work is the first to propose a viable path for training open-source LLMs that are capable of optimization modeling and developing solver codes, eventually leading to a superior ability for automating optimization modeling and solving. Particularly, we design the sc OR-Instruct, a semi-automated data synthesis framework for optimization modeling that enables customizable enhancements for specific scenarios or model types. This work also introduces IndustryOR, the first industrial benchmark for evaluating LLMs in solving practical OR problems. We train several 7B-scale open-source LLMs using synthesized data (dubbed ORLMshttps://github.com/Cardinal-Operations/ORLM), which exhibit significantly enhanced optimization modeling capabilities, achieving competitive performance across the NL4OPT, MAMO, and IndustryOR benchmarks. Additionally, our experiments highlight the potential of scaling law and reinforcement learning to further enhance the performance of ORLMs. The workflows and human-machine interaction paradigms of ORLMs in practical industrial applications are also discussed in the paper.

Key facts. Cited by 124 papers in the map (data through 14 Oct 2026). Builds on 2 of its 14 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

2 of 14 references.

References · 2

  1. 2019Probabilistic Forecasting with Temporal Convolutional Neural Networkcited by 63
  2. 2020Queueing Network Controls via Deep Reinforcement Learningcited by 41

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 41; 2026: 80.

124 papers.

Sort:

By area:

  1. 2024LLMOPT: Learning to Define and Solve General Optimization Problems from Scratchcited by 102
  2. 2024A Systematic Survey on Large Language Models for Algorithm Designcited by 69
  3. 2025Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modelingcited by 45
  4. 2025Large Language Models as End-to-end Combinatorial Optimization Solverscited by 28
  5. 2025StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Modelscited by 26
  6. 2025OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learningcited by 17
  7. 2025Auto-Formulating Dynamic Programming Problems with Large Language Modelscited by 16
  8. 2024BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solvingcited by 15
  9. 2025AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Librarycited by 14
  10. 2026Automated Optimization Modeling via a Localizable Error-Driven Perspectivecited by 14
  11. 2026Constructing Industrial-Scale Optimization Modeling Benchmarkcited by 12
  12. 2025A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solvingcited by 11
38 more
  1. 2025ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Researchcited by 10
  2. 2025Adaptively Robust LLM Inference Optimization under Prediction Uncertaintycited by 10
  3. 2025SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Searchcited by 10
  4. 2025ORGEval: Graph-Theoretic Evaluation of LLMs in Optimization Modelingcited by 10
  5. 2025OptiChat: Bridging Optimization Models and Practitioners with Large Language Modelscited by 8
  6. 2025EvoCut: Strengthening Integer Programs via Evolution-Guided Language Modelscited by 8
  7. 2025SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modelingcited by 8
  8. 2026AI Agents for Inventory Control: Human-LLM-OR Complementaritycited by 8
  9. 2026ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimizationcited by 8
  10. 2025LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Mergingcited by 7
  11. 2025Text2Zinc: A Cross-Domain Dataset for Modeling Optimization and Satisfaction Problems in MiniZinccited by 7
  12. 2026ConstraintBench: Benchmarking LLM Constraint Reasoning on Direct Optimizationcited by 7
  13. 2025Fine-tuning Large Language Model for Automated Algorithm Designcited by 6
  14. 2025Large Language Models in Operations Research: Methods, Applications, and Challengescited by 6
  15. 2026FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimizationcited by 6
  16. 2025Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generationcited by 5
  17. 2025R-ConstraintBench: Evaluating LLMs on NP-Complete Schedulingcited by 5
  18. 2025PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactionscited by 5
  19. 2026OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scalingcited by 5
  20. 2026NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agentscited by 5
  21. 2026OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agentscited by 5
  22. 2026Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verificationcited by 5
  23. 2025DualSchool: How Reliable are LLMs for Optimization Education?cited by 4
  24. 2025Cooperative Design Optimization through Natural Language Interactioncited by 4
  25. 2025Performance of LLMs on Stochastic Modeling Operations Research Problems: From Theory to Practicecited by 3
  26. 2025LLM-QUBO: An End-to-End Framework for Automated QUBO Transformation from Natural Language Problem Descriptionscited by 3
  27. 2026LLM-SAA: LLM-persona Generated Distributions for Decision-makingcited by 3
  28. 2026Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive Optimizationcited by 3
  29. 2026OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solvingcited by 3
  30. 2026From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modelingcited by 3
  31. 2025LLM-Enhanced Multi-Agent Reinforcement Learning with Expert Workflow for Real-Time P2P Energy Tradingcited by 2
  32. 2025REG: A Regularization Optimizer for Robust Training Dynamicscited by 2
  33. 2025LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selectioncited by 2
  34. 2025Perturbing the Derivative: Doubly Wild Refitting for Model-Free Evaluation of Opaque Machine Learning Predictorscited by 2
  35. 2026Canonical Intermediate Representation for LLM-based optimization problem formulation and code generationcited by 2
  36. 2026MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Researchcited by 2
  37. 2026ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modelingcited by 2
  38. 2026A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraintscited by 2

50 most cited of 124 All 124 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025OptiMind: Teaching LLMs to Think Like Optimization Experts
  2. 2025Peering Inside the Black Box: Uncovering LLM Errors in Optimization Modelling through Component-Level Evaluation
  3. 2025OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM
  4. 2026AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization
  5. 2026MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling
  6. 2026Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches
  7. 2024Evaluating LLM Reasoning in the Operations Research Domain with ORQA
  8. 2024OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling