Grammar-Aware Literate Generative Mathematical Programming with Compiler-in-the-Loop

• URL: http://arxiv.org/abs/2601.17670v1
• Date: Sun, 25 Jan 2026 03:19:49 GMT
• Title: Grammar-Aware Literate Generative Mathematical Programming with Compiler-in-the-Loop
• Authors: Roberto Rossi, Steven D. Prestwich,
• Abstract summary: We introduce SyntAGM, an end-to-end system that translates natural language problem descriptions into PyOPL models.<n> SyntAGM is grammar-aware thanks to in-context exposure to the PyOPL BNF grammar.<n>It achieves competitive accuracy with superior token, cost, and latency profiles.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work investigates generative mathematical programming through the lens of Algebraic Modelling Languages (AMLs) and compiler-guided model synthesis. By leveraging PyOPL, an OPL-like AML compiler that provides detailed syntax diagnostics, we introduce SyntAGM, an end-to-end system that translates natural language problem descriptions into PyOPL models via a generate--compile--assess--revise loop. SyntAGM is grammar-aware thanks to in-context exposure to the PyOPL BNF grammar, and benefits from few-shot retrieval of literate PyOPL model exemplars. To obtain a valid PyOPL model that matches the problem description, SyntAGM mobilises compiler feedback and an LLM-based alignment judge. In a comparative study against established prompting baselines SyntAGM achieves competitive accuracy with superior token, cost, and latency profiles.

Related papers

• Program Synthesis via Test-Time Transduction [26.30808249424997]
  We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly leverages test inputs during synthesis.<n>We evaluate our approach on four benchmarks: Playgol, MBPP+, 1D-ARC, and programmatic world modeling on MiniGrid.<n>We demonstrate that our method significantly improves program synthesis in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-09-22T06:53:32Z)
• Matchmaker: Self-Improving Large Language Model Programs for Schema Matching [60.23571456538149]
  We propose a compositional language model program for schema matching, comprised of candidate generation, refinement and confidence scoring. Matchmaker self-improves in a zero-shot manner without the need for labeled demonstrations. Empirically, we demonstrate on real-world medical schema matching benchmarks that Matchmaker outperforms previous ML-based approaches.
  arXiv  Detail & Related papers  (2024-10-31T16:34:03Z)
• Training Language Models on Synthetic Edit Sequences Improves Code Synthesis [33.13471417703669]
  Language models (LMs) autorely synthesize programs in a single pass.<n>While high-quality instruction data for code synthesis is scarce, edit data for synthesis is even scarcer.<n>We develop a synthetic data generation algorithm called LintSeq to fill this gap.
  arXiv  Detail & Related papers  (2024-10-03T17:57:22Z)
• Using Grammar Masking to Ensure Syntactic Validity in LLM-based Modeling Tasks [0.996023506058745]
  Grammar masking is used to guide large language models toward producing syntactically correct models for a given context-free grammar. We show that grammar masking can dramatically improve the modeling capabilities of several language models.
  arXiv  Detail & Related papers  (2024-07-08T17:19:59Z)
• HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis [25.260063704712458]
  Large language models (LLMs) often fail to produce fully correct programs in unfamiliar DSLs. Motivated by these limitations, we introduce a hybrid approach, where LLM completions for a given task are used to learn a task-specific, context-free surrogate model. We evaluate this hybrid approach on three domains, and show that it outperforms both unguided search and direct sampling from LLMs, as well as existing program synthesizers.
  arXiv  Detail & Related papers  (2024-05-24T18:45:51Z)
• CodecLM: Aligning Language Models with Tailored Synthetic Data [51.59223474427153]
  We introduce CodecLM, a framework for adaptively generating high-quality synthetic data for instruction-following abilities. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples.
  arXiv  Detail & Related papers  (2024-04-08T21:15:36Z)
• Guiding Enumerative Program Synthesis with Large Language Models [15.500250058226474]
  In this paper, we evaluate the abilities of Large Language Models to solve formal synthesis benchmarks. When one-shot synthesis fails, we propose a novel enumerative synthesis algorithm. We find that GPT-3.5 as a stand-alone tool for formal synthesis is easily outperformed by state-of-the-art formal synthesis algorithms.
  arXiv  Detail & Related papers  (2024-03-06T19:13:53Z)
• Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code? [51.29970742152668]
  We highlight relying on accuracy-based measurements may lead to an overestimation of models' capabilities. To address these issues, we introduce a technique called SyntaxEval in Syntactic Capabilities.
  arXiv  Detail & Related papers  (2024-01-03T02:44:02Z)
• LILO: Learning Interpretable Libraries by Compressing and Documenting Code [71.55208585024198]
  We introduce LILO, a neurosymbolic framework that iteratively synthesizes, compresses, and documents code. LILO combines LLM-guided program synthesis with recent algorithmic advances in automated from Stitch. We find that AutoDoc boosts performance by helping LILO's synthesizer to interpret and deploy learned abstractions.
  arXiv  Detail & Related papers  (2023-10-30T17:55:02Z)
• Adapting Language Models to Compress Contexts [71.98287002918941]
  Transformer-based language models (LMs) are powerful and widely-applicable tools, but their usefulness is constrained by a finite context window. We propose to adapt pre-trained LMs into AutoCompressors, which are capable of compressing long contexts into compact summary vectors. We fine-tune OPT and Llama-2 models on sequences of up to 30,720 tokens and show that AutoCompressors can utilize long contexts to improve perplexity.
  arXiv  Detail & Related papers  (2023-05-24T06:42:44Z)
• ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers [60.6418431624873]
  Large language models (LLMs) excel at implementing code from functionality descriptions but struggle with algorithmic problems. We propose ALGO, a framework that synthesizes Algorithmic programs with LLM-Generated Oracles to guide the generation and verify their correctness. Experiments show that when equipped with ALGO, we achieve an 8x better one-submission pass rate over the Codex model and a 2.6x better one-submission pass rate over CodeT.
  arXiv  Detail & Related papers  (2023-05-24T00:10:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.