# Canonical Intermediate Representation for LLM-based optimization problem formulation and code generation

arXiv: https://arxiv.org/abs/2602.02029 · HTML: https://mlsanity.com/paper/2602.02029/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 53 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 24 of 24)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [LeanDojo: Theorem Proving with Retrieval-Augmented Language Models](https://mlsanity.com/paper/2306.15626/) (2023)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [Retrieval Augmented Code Generation and Summarization](https://mlsanity.com/paper/2108.11601/) (2021)
- [ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling](https://mlsanity.com/paper/2405.17743/) (2024)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch](https://mlsanity.com/paper/2410.13213/) (2024)
- [Entities as Experts: Sparse Memory Access with Entity Supervision](https://mlsanity.com/paper/2004.07202/) (2020)
- [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://mlsanity.com/paper/2208.11640/) (2022)
- [Large Language Models for Supply Chain Optimization](https://mlsanity.com/paper/2307.03875/) (2023)
- [Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions](https://mlsanity.com/paper/2209.15565/) (2022)
- [OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling](https://mlsanity.com/paper/2502.11102/) (2025)
- [Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference](https://mlsanity.com/paper/2310.03184/) (2023)
- [Auto-Formulating Dynamic Programming Problems with Large Language Models](https://mlsanity.com/paper/2507.11737/) (2025)
- [AutoSAT: Automatically Optimize SAT Solvers via Large Language Models](https://mlsanity.com/paper/2402.10705/) (2024)
- [Robust and Adaptive Optimization under a Large Language Model Lens](https://mlsanity.com/paper/2501.00568/) (2024)
- [OptiChat: Bridging Optimization Models and Practitioners with Large Language Models](https://mlsanity.com/paper/2501.08406/) (2025)

## Built on by (most cited first, 2 of 2)

- [Semantic Constraint Synthesis for Adaptive Trajectory Optimization via Large Language Models](https://mlsanity.com/paper/2606.04123/) (2026)
- [Position: Avoid Overstretching LLMs for every Enterprise Task](https://mlsanity.com/paper/2605.09365/) (2026)

## Abstract (arXiv)

Automatically formulating optimization models from natural language descriptions is a growing focus in operations research, yet current LLM-based approaches struggle with the composite constraints and appropriate modeling paradigms required by complex operational rules. To address this, we introduce the Canonical Intermediate Representation (CIR): a schema that LLMs explicitly generate between problem descriptions and optimization models. CIR encodes the semantics of operational rules through constraint archetypes and candidate modeling paradigms, thereby decoupling rule logic from its mathematical instantiation. Upon a newly generated CIR knowledge base, we develop the rule-to-constraint (R2C) framework, a multi-agent pipeline that parses problem texts, synthesizes CIR implementations by retrieving domain knowledge, and instantiates optimization models. To systematically evaluate rule-to-constraint reasoning, we test R2C on our newly constructed benchmark featuring rich operational rules, and benchmarks from prior work. Extensive experiments show that R2C achieves state-of-the-art accuracy on the proposed benchmark (47.2% Accuracy Rate). On established benchmarks from the literature, R2C delivers highly competitive results, approaching the performance of proprietary models (e.g., GPT-5). Moreover, with a reflection mechanism, R2C achieves further gains and sets new best-reported results on some benchmarks.