mlsanityData to 7 Oct 2026

Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions

arXiv 2209.15565 ↗First posted 30 Sep 2022cs.CL cs.AIcited by 54

Not on the map. Why?

Abstract (arXiv)

We describe an augmented intelligence system for simplifying and enhancing the modeling experience for operations research. Using this system, the user receives a suggested formulation of an optimization problem based on its description. To facilitate this process, we build an intuitive user interface system that enables the users to validate and edit the suggestions. We investigate controlled generation techniques to obtain an automatic suggestion of formulation. Then, we evaluate their effectiveness with a newly created dataset of linear programming problems drawn from various application domains.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 19 of its 46 references that are in the map. First posted on arXiv 30 Sep 2022.

Builds on

19 of 46 references.

References · 19

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  6. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  7. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  8. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  9. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  10. 2016Solving General Arithmetic Word Problemscited by 353
  11. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 234
  12. 2016Language to Logical Form with Neural Attentioncited by 158
7 more
  1. 2018Coarse-to-Fine Decoding for Neural Semantic Parsingcited by 110
  2. 2018A Survey on Semantic Parsingcited by 62
  3. 2021Text-to-Table: A New Way of Information Extractioncited by 47
  4. 2020AI Song Contest: Human-AI Co-Creation in Songwritingcited by 25
  5. 2022Text Generation with Text-Editing Modelscited by 21
  6. 2022An End-to-End Dialogue Summarization System for Sales Callscited by 7
  7. 2021Augmenting Poetry Composition with Verse by Versecited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 10; 2025: 15; 2026: 19.

54 papers.

Sort:

By area:

  1. 2023NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptionscited by 133
  2. 2024OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Modelscited by 105
  3. 2024OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modelingcited by 66
  4. 2025Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modelingcited by 44
  5. 2024Synthetic Dialogue Dataset Generation using LLM Agentscited by 39
  6. 2024OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scalecited by 37
  7. 2025StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Modelscited by 26
  8. 2023Holy Grail 2.0: From Natural Language to Constraint Modelscited by 24
  9. 2024Solving General Natural-Language-Description Optimization Problems with Large Language Modelscited by 22
  10. 2024From Large Language Models and Optimization to Decision Optimization CoPilot: A Research Manifestocited by 11
  11. 2025A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solvingcited by 9
  12. 2022Highlighting Named Entities in Input for Auto-Formulation of Optimization Problemscited by 8
38 more
  1. 2023Synthesis of Mathematical programs from Natural Language Specificationscited by 8
  2. 2024LLMs for Cold-Start Cutting Plane Separator Configurationcited by 8
  3. 2023A Novel Approach for Auto-Formulation of Optimization Problemscited by 7
  4. 2025Text2Zinc: A Cross-Domain Dataset for Modeling Optimization and Satisfaction Problems in MiniZinccited by 7
  5. 2025ORGEval: Graph-Theoretic Evaluation of LLMs in Optimization Modelingcited by 7
  6. 2024ATG: Benchmarking Automated Theorem Generation for Generative Language Modelscited by 6
  7. 2022Tag Embedding and Well-defined Intermediate Representation improve Auto-Formulation of Problem Descriptioncited by 5
  8. 2022VTCC-NLP at NL4Opt competition subtask 1: An Ensemble Pre-trained language models for Named Entity Recognitioncited by 5
  9. 2026OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scalingcited by 5
  10. 2022Linear programming word problems formulation using EnsembleCRF NER labeler and T5 text generator with data augmentationscited by 4
  11. 2023OPD@NL4Opt: An ensemble approach for the NER task of the optimization problemcited by 4
  12. 2023Language Models for Business Optimisation with a Real World Case Study in Production Schedulingcited by 4
  13. 2024Abstract Operations Research Modeling Using Natural Language Inputscited by 4
  14. 2024Accelerating process control and optimization via machine learning: A reviewcited by 3
  15. 2025DualSchool: How Reliable are LLMs for Optimization Education?cited by 3
  16. 2025DCP-Bench-Open: Evaluating LLMs for Constraint Modelling of Discrete Combinatorial Problemscited by 3
  17. 2025Performance of LLMs on Stochastic Modeling Operations Research Problems: From Theory to Practicecited by 3
  18. 2025LLM-QUBO: An End-to-End Framework for Automated QUBO Transformation from Natural Language Problem Descriptionscited by 3
  19. 2026From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modelingcited by 3
  20. 2026Canonical Intermediate Representation for LLM-based optimization problem formulation and code generationcited by 2
  21. 2026Execution-Verified Reinforcement Learning for Optimization Modelingcited by 2
  22. 2026Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive Optimizationcited by 2
  23. 2025Large Language Model-Based Automatic Formulation for Stochastic Optimization Modelscited by 1
  24. 2025Automated Constraint Specification for Job Scheduling by Regulating Generative Model with Domain-Specific Representationcited by 1
  25. 2025Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Designcited by 1
  26. 2026Grammar-Aware Literate Generative Mathematical Programming with Compiler-in-the-Loopcited by 1
  27. 2026AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problemscited by 1
  28. 2026Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Modelscited by 1
  29. 2026Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesiscited by 1
  30. 2025From User Preferences to Optimization Constraints Using Large Language Modelscited by 0
  31. 2025Optimization Problem Solving Can Transition to Evolutionary Agentic Workflowscited by 0
  32. 2025SMARTAPS: Tool-augmented LLMs for Operations Managementcited by 0
  33. 2026Text2Model: Modeling Copilots for Text-to-Model Translationcited by 0
  34. 2026Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimizationcited by 0
  35. 2026PARM: Pipeline-Adapted Reward Modelcited by 0
  36. 2026StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modelingcited by 0
  37. 2026LP Mining with LP2Graph: A Use Case for Railway Reschedulingcited by 0
  38. 2026Learn2Zinc: Fine-tuning Small Language Models for Text-to-Model Translation in MiniZinccited by 0

50 most cited of 54 All 54 (JSON)