# On Integrating Resilience and Human Oversight into LLM-Assisted Modeling Workflows for Digital Twins

arXiv: https://arxiv.org/abs/2603.25898 · HTML: https://mlsanity.com/paper/2603.25898/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 41 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Large Language Models Hallucination: A Comprehensive Survey](https://mlsanity.com/paper/2510.06265/) (2025)
- [Towards Understanding the Characteristics of Code Generation Errors Made by Large Language Models](https://mlsanity.com/paper/2406.08731/) (2024)
- [Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chat](https://mlsanity.com/paper/2401.17163/) (2024)
- [Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems](https://mlsanity.com/paper/2506.13905/) (2025)
- [GPT-Based Models Meet Simulation: How to Efficiently Use Large-Scale Pre-Trained Language Models Across Simulation Tasks](https://mlsanity.com/paper/2306.13679/) (2023)
- [Context, Composition, Automation, and Communication -- The C2AC Roadmap for Modeling and Simulation](https://mlsanity.com/paper/2310.05649/) (2023)
- [Performance of LLMs on Stochastic Modeling Operations Research Problems: From Theory to Practice](https://mlsanity.com/paper/2506.23924/) (2025)
- [Using (Not-so) Large Language Models to Generate Simulation Models in a Formal DSL: A Study on Reaction Networks](https://mlsanity.com/paper/2503.01675/) (2025)

## Built on by (most cited first, 1 of 1)

- [AgenticTwin: An Agentic LLM Framework Integrated with Digital Twin for Anomaly Detection](https://mlsanity.com/paper/2608.11679/) (2026)

## Abstract (arXiv)

LLM-assisted modeling holds the potential to rapidly build executable Digital Twins of complex systems from only coarse descriptions and sensor data. However, resilience to LLM hallucination, human oversight, and real-time model adaptability remain challenging and often mutually conflicting requirements. We present three critical design principles for integrating resilience and oversight into such workflows, derived from insights gained through our work on FactoryFlow - an open-source LLM-assisted framework for building simulation-based Digital Twins of manufacturing systems. First, orthogonalize structural modeling and parameter fitting. Structural descriptions (components, interconnections) are LLM-translated from coarse natural language to an intermediate representation (IR) with human visualization and validation, which is algorithmically converted to the final model. Parameter inference, in contrast, operates continuously on sensor data streams with expert-tunable controls. Second, restrict the model IR to interconnections of parameterized, pre-validated library components rather than monolithic simulation code, enabling interpretability and error-resilience. Third, and most important, is to use a density-preserving IR. When IR descriptions expand dramatically from compact inputs hallucination errors accumulate proportionally. We present the case for Python as a density-preserving IR : loops express regularity compactly, classes capture hierarchy and composition, and the result remains highly readable while exploiting LLMs strong code generation capabilities. A key contribution is detailed characterization of LLM-induced errors across model descriptions of varying detail and complexity, revealing how IR choice critically impacts error rates. These insights provide actionable guidance for building resilient and transparent LLM-assisted simulation automation workflows.