# Natural-Language to SysMLv2 Translation via Conformance-Driven Iterative Refinement

arXiv: https://arxiv.org/abs/2607.14162 · HTML: https://mlsanity.com/paper/2607.14162/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 59 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [Compilable Neural Code Generation with Compiler Feedback](https://mlsanity.com/paper/2203.05132/) (2022)
- [VeCoGen: Automating Generation of Formally Verified C Code with Large Language Models](https://mlsanity.com/paper/2411.19275/) (2024)
- [Compiler generated feedback for Large Language Models](https://mlsanity.com/paper/2403.14714/) (2024)
- [Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization](https://mlsanity.com/paper/2502.07786/) (2024)
- [LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops](https://mlsanity.com/paper/2603.23613/) (2026)
- [Trust at Your Own Peril: A Mixed Methods Exploration of the Ability of Large Language Models to Generate Expert-Like Systems Engineering Artifacts and a Characterization of Failure Modes](https://mlsanity.com/paper/2502.09690/) (2025)
- [Average Convergence Rate of Evolutionary Algorithms](https://mlsanity.com/paper/1504.08117/) (2015)
- [A System Model Generation Benchmark from Natural Language Requirements](https://mlsanity.com/paper/2508.03215/) (2025)
- [LLM-Assisted Semantic Alignment and Integration in Collaborative Model-Based Systems Engineering Using SysML v2](https://mlsanity.com/paper/2508.16181/) (2025)
- [Text to model via SysML: Automated generation of dynamical system computational models from unstructured natural language text via enhanced System Modeling Language diagrams](https://mlsanity.com/paper/2507.06803/) (2025)
- [Natural Language Processing for Systems Engineering: Automatic Generation of Systems Modelling Language Diagrams](https://mlsanity.com/paper/2208.05008/) (2022)
- [SysTemp: A Multi-Agent System for Template-Based Generation of SysML v2](https://mlsanity.com/paper/2506.21608/) (2025)
- [Intelligent requirements engineering from natural language and their chaining toward CAD models](https://mlsanity.com/paper/2007.07825/) (2020)

## Abstract (arXiv)

Model-Based Systems Engineering (MBSE) relies on formal system models as primary technical artifacts for representing requirements, structure, and behavior across the system lifecycle. With the standardization of SysMLv2 as a textual language, interest is increasing in translating natural-language descriptions directly into executable models. For practical deployment, generated models must be accepted by industrial modeling environments, not merely satisfy grammar constraints. We present a conformance-checker-driven framework for reliable natural-language-to-SysMLv2 translation that enforces production-level acceptance as the termination condition. The system embeds a SysMLv2 conformance checker within a generate-check-repair loop. Each model is evaluated using the checker, and deterministic diagnostics are incorporated into revisions until zero conformance errors are achieved. Using the production checker as the oracle ensures the framework targets deployability rather than grammar plausibility. We evaluate the approach on the full SysMBench prompt set of 151 prompts across four large language model backends, yielding 604 prompt-model cases. Single-shot generation achieves 51.16% production-conformance acceptance, while our approach achieves 100.00% conformance. By elevating production conformance from a post-processing check to a control mechanism within generation, the framework converts probabilistic outputs into production-accepted SysMLv2 artifacts suitable for loading, visualization, and engineering use.