mlsanityData to 14 Oct 2026

Holy Grail 2.0: From Natural Language to Constraint Models

arXiv 2308.01589 ↗First posted 3 Aug 2023cs.AI cs.CL cs.HCcited by 26

Not on the map. Why?

Abstract (arXiv)

Twenty-seven years ago, E. Freuder highlighted that "Constraint programming represents one of the closest approaches computer science has yet made to the Holy Grail of programming: the user states the problem, the computer solves it". Nowadays, CP users have great modeling tools available (like Minizinc and CPMpy), allowing them to formulate the problem and then let a solver do the rest of the job, getting closer to the stated goal. However, this still requires the CP user to know the formalism and respect it. Another significant challenge lies in the expertise required to effectively model combinatorial problems. All this limits the wider adoption of CP. In this position paper, we investigate a possible approach to leverage pre-trained Large Language Models to extract models from textual problem descriptions. More specifically, we take inspiration from the Natural Language Processing for Optimization (NL4OPT) challenge and present early results with a decomposition-based prompting approach to GPT Models.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 17 of its 26 references that are in the map. First posted on arXiv 3 Aug 2023.

Builds on

17 of 26 references.

References · 17

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  6. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  7. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
  8. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  9. 2020Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stoppingcited by 384
  10. 2022A Systematic Evaluation of Large Language Models of Codecited by 363
  11. 2023Large Language Model Guided Tree-of-Thoughtcited by 221
  12. 2023NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptionscited by 135
5 more
  1. 2023An Analysis of the Automatic Bug Fixing Performance of ChatGPTcited by 110
  2. 2022Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptionscited by 54
  3. 2022Highlighting Named Entities in Input for Auto-Formulation of Optimization Problemscited by 8
  4. 2023A Novel Approach for Auto-Formulation of Optimization Problemscited by 7
  5. 2023Towards an Automatic Optimisation Model Generator Assisted with Generative Pre-trained Transformercited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 15; 2026: 5.

26 papers.

Sort:

By area:

  1. 2025Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modelingcited by 45
  2. 2024LM4OPT: Unveiling the Potential of Large Language Models in Formulating Mathematical Optimization Problemscited by 18
  3. 2024From Large Language Models and Optimization to Decision Optimization CoPilot: A Research Manifestocited by 11
  4. 2025A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solvingcited by 11
  5. 2024Combining Constraint Programming Reasoning with Large Language Model Predictionscited by 8
  6. 2024LLMs for Cold-Start Cutting Plane Separator Configurationcited by 8
  7. 2025SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modelingcited by 8
  8. 2025Text2Zinc: A Cross-Domain Dataset for Modeling Optimization and Satisfaction Problems in MiniZinccited by 7
  9. 2025CP-Agent: Agentic Constraint Programmingcited by 6
  10. 2024Abstract Operations Research Modeling Using Natural Language Inputscited by 4
  11. 2025DualSchool: How Reliable are LLMs for Optimization Education?cited by 4
  12. 2025DCP-Bench-Open: Evaluating LLMs for Constraint Modelling of Discrete Combinatorial Problemscited by 4
14 more
  1. 2025Distributed Multi-Agent Coordination Using Multi-Modal Foundation Modelscited by 3
  2. 2025CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Codecited by 3
  3. 2025LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMscited by 2
  4. 2025Gala: Global LLM Agents for Text-to-Model Translationcited by 2
  5. 2026MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modelingcited by 2
  6. 2026TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modelingcited by 2
  7. 2025Behavior and Representation in Open-Weight Large Language Models for Combinatorial Optimization: From Feature Extraction to Algorithm Selectioncited by 1
  8. 2026Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignmentcited by 1
  9. 2024Automatic Feature Learning for Essence: a Case Study on Car Sequencingcited by 0
  10. 2025Optimization Problem Solving Can Transition to Evolutionary Agentic Workflowscited by 0
  11. 2025CP-Model-Zoo: A Natural Language Query System for Constraint Programming Modelscited by 0
  12. 2025LM4Opt-RA: A Multi-Candidate LLM Framework with Structured Ranking for Automating Network Resource Allocationcited by 0
  13. 2026Learn2Zinc: Fine-tuning Small Language Models for Text-to-Model Translation in MiniZinccited by 0
  14. 2026Auto-Formalizing Neuro-Symbolic Predictorscited by 0