# Agentic Scientific Simulation: Execution-Grounded Model Construction and Reconstruction

arXiv: https://arxiv.org/abs/2603.00214 · HTML: https://mlsanity.com/paper/2603.00214/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 13 of 13)

- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [SciCode: A Research Coding Benchmark Curated by Scientists](https://mlsanity.com/paper/2407.13168/) (2024)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge](https://mlsanity.com/paper/2311.08166/) (2023)
- [Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI](https://mlsanity.com/paper/2505.19443/) (2025)
- [MetaOpenFOAM: an LLM-based multi-agent framework for CFD](https://mlsanity.com/paper/2407.21320/) (2024)
- [CodePDE: An Inference Framework for LLM-driven PDE Solver Generation](https://mlsanity.com/paper/2505.08783/) (2025)
- [Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations](https://mlsanity.com/paper/2504.09602/) (2025)
- [MooseAgent: A LLM Based Multi-agent Framework for Automating Moose Simulation](https://mlsanity.com/paper/2504.08621/) (2025)
- [MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processing](https://mlsanity.com/paper/2502.00498/) (2025)
- [LLM Agent for Fire Dynamics Simulations](https://mlsanity.com/paper/2412.17146/) (2024)
- [FeaGPT: an End-to-End agentic-AI for Finite Element Analysis](https://mlsanity.com/paper/2510.21993/) (2025)
- [SwarmFoam: An OpenFOAM Multi-Agent System Based on Multiple Types of Large Language Models](https://mlsanity.com/paper/2601.07252/) (2026)

## Built on by (most cited first, 4 of 4)

- [Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters](https://mlsanity.com/paper/2606.09774/) (2026)
- [Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards](https://mlsanity.com/paper/2607.10474/) (2026)
- [Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks](https://mlsanity.com/paper/2606.01975/) (2026)
- [WorldAgent: Verification-Guided Agentic Physical World Construction](https://mlsanity.com/paper/2609.33208/) (2026)

## Abstract (arXiv)

LLM agents are increasingly used for code generation, but physics-based simulation poses a deeper challenge: natural-language descriptions of simulation models are inherently underspecified, and different admissible resolutions of implicit choices produce physically valid but scientifically distinct configurations. Without explicit detection and resolution of these ambiguities, neither the correctness of the result nor its reproducibility from the original description can be assured. This paper investigates agentic scientific simulation, where model construction is organized as an execution-grounded interpret-act-validate loop and the simulator serves as the authoritative arbiter of physical validity rather than merely a runtime. We present JutulGPT, a reference implementation built on the fully differentiable Julia-based reservoir simulator JutulDarcy. The agent combines structured retrieval of documentation and examples with code synthesis, static analysis, execution, and systematic interpretation of solver diagnostics. Underspecified modelling choices are detected explicitly and resolved either autonomously (with logged assumptions) or through targeted user queries. The results demonstrate that agent-mediated model construction can be grounded in simulator validation, while also revealing a structural limitation: choices resolved tacitly through simulator defaults are invisible to the assumption log and to any downstream representation. A secondary experiment with autonomous reconstruction of a reference model from progressively abstract textual descriptions shows that reconstruction variability exposes latent degrees of freedom in simulation descriptions and provides a practical methodology for auditing reproducibility. All code, prompts, and agent logs are publicly available.