Grammar-Aware Literate Generative Mathematical Programming with Compiler-in-the-Loop
This work addresses the challenge of automating mathematical programming model creation for users of algebraic modeling languages, representing an incremental improvement over existing methods.
The authors tackled the problem of generating mathematical programming models from natural language descriptions by developing SyntAGM, an end-to-end system that uses a generate-compile-assess-revise loop with compiler feedback. The system achieved competitive accuracy with superior token, cost, and latency profiles compared to established prompting baselines.
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.