# Generating Streamlining Constraints with Large Language Models

arXiv: https://arxiv.org/abs/2408.10268 · HTML: https://mlsanity.com/paper/2408.10268/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 53 references that are in the map.
- First posted on arXiv 16 Aug 2024.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022)
- [HyperTree Proof Search for Neural Theorem Proving](https://mlsanity.com/paper/2205.11491/) (2022)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [Formal Mathematics Statement Curriculum Learning](https://mlsanity.com/paper/2202.01344/) (2022)
- [Lemur: Integrating Large Language Models in Automated Program Verification](https://mlsanity.com/paper/2310.04870/) (2023)
- [Incomplete MaxSAT Approaches for Combinatorial Testing](https://mlsanity.com/paper/2105.12552/) (2021)
- [A Framework for Generating Informative Benchmark Instances](https://mlsanity.com/paper/2205.14753/) (2022)
- [Local Search for Fast Matrix Multiplication](https://mlsanity.com/paper/1903.11391/) (2019)
- [Towards Portfolios of Streamlined Constraint Models: A Case Study with the Balanced Academic Curriculum Problem](https://mlsanity.com/paper/2009.10152/) (2020)

## Built on by (most cited first, 7 of 7)

- [MCP-Solver: Integrating Language Models with Constraint Programming Systems](https://mlsanity.com/paper/2501.00539/) (2024)
- [R-ConstraintBench: Evaluating LLMs on NP-Complete Scheduling](https://mlsanity.com/paper/2508.15204/) (2025)
- [Using Reasoning Models to Generate Search Heuristics that Solve Open Instances of Combinatorial Design Problems](https://mlsanity.com/paper/2505.23881/) (2025)
- [CP-SynC: Multi-Agent Zero-Shot Constraint Modeling in MiniZinc with Synthesized Checkers](https://mlsanity.com/paper/2605.01675/) (2026)
- [Streamliners for Answer Set Programming](https://mlsanity.com/paper/2604.19251/) (2026)
- [Streamlined Constraint Reasoning via CNN Pattern Recognition on Enumerated Solutions](https://mlsanity.com/paper/2605.19895/) (2026)
- [Improving Constraint Models with LLM Agents](https://mlsanity.com/paper/2608.08127/) (2026)

## Abstract (arXiv)

Streamlining constraints (or streamliners, for short) narrow the search space, enhancing the speed and feasibility of solving complex constraint satisfaction problems. Traditionally, streamliners were crafted manually or generated through systematically combined atomic constraints with high-effort offline testing. Our approach utilizes the creativity of Large Language Models (LLMs) to propose effective streamliners for problems specified in the MiniZinc constraint programming language and integrates feedback to the LLM with quick empirical tests for validation. Evaluated across seven diverse constraint satisfaction problems, our method achieves substantial runtime reductions. We compare the results to obfuscated and disguised variants of the problem to see whether the results depend on LLM memorization. We also analyze whether longer off-line runs improve the quality of streamliners and whether the LLM can propose good combinations of streamliners.