# PolyJarvis: An LLM-Orchestrated Agent for Automated All-Atom Molecular Dynamics of Amorphous Homopolymers

arXiv: https://arxiv.org/abs/2604.02537 · HTML: https://mlsanity.com/paper/2604.02537/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 64 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Automating MD simulations for Proteins using Large language Models: NAMD-Agent](https://mlsanity.com/paper/2507.07887/) (2025)
- [Toward Automated Simulation Research Workflow through LLM Prompt Engineering Design](https://mlsanity.com/paper/2408.15512/) (2024)
- [Adsorb-Agent: Autonomous Identification of Stable Adsorption Configurations via Large Language Model Agent](https://mlsanity.com/paper/2410.16658/) (2024)
- [DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulations](https://mlsanity.com/paper/2512.10034/) (2025)
- [AlloyBERT: Alloy Property Prediction with Large Language Models](https://mlsanity.com/paper/2403.19783/) (2024)
- [Polymer-Agent: Large Language Model Agent for Polymer Design](https://mlsanity.com/paper/2601.16376/) (2026)
- [From Natural Language to Materials Discovery:The Materials Knowledge Navigation Agent](https://mlsanity.com/paper/2602.11123/) (2026)

## Built on by (most cited first, 6 of 6)

- [MDGYM: Benchmarking AI Agents on Molecular Simulations](https://mlsanity.com/paper/2605.08941/) (2026)
- [Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows](https://mlsanity.com/paper/2605.14527/) (2026)
- [MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback](https://mlsanity.com/paper/2606.12916/) (2026)
- [MDArena: Evaluating Coding Agents on Realistic Molecular Dynamics Workflows](https://mlsanity.com/paper/2608.02642/) (2026)
- [Material Database Agent: A Multimodal Agentic Framework for Scientific Literature Mining](https://mlsanity.com/paper/2605.04278/) (2026)
- [Science Done on a Machine by a Machine: AI Agents in Computational Chemistry](https://mlsanity.com/paper/2608.18508/) (2026)

## Abstract (arXiv)

All-atom molecular dynamics (MD) simulations can predict polymer properties from molecular structure, yet their execution requires specialized expertise in force field selection, system construction, equilibration, and property extraction. We present PolyJarvis, a platform in which a planning agent produces a validated run plan that deterministic stage scripts execute through established simulation toolkits, Enhanced Monte Carlo (EMC) for system construction and LAMMPS for molecular dynamics, exposed as Model Context Protocol (MCP) servers, with a recovery agent consulted only on structured failures and within a fixed decision budget. Given a repeat-unit SMILES string and target properties, PolyJarvis constructs the amorphous cell, equilibrates it under a mechanized convergence gate, and computes target properties. Validation is conducted on seven amorphous homopolymers, each run as three replicates that share a protocol frozen per system and use independent random seeds, namely polyethylene (PE), atactic polystyrene (aPS), syndiotactic poly(vinyl chloride) (sPVC), poly(L-lactic acid) (PLLA), poly(ethylene glycol) (PEG), poly(ether ether ketone) (PEEK), and polysulfone (PSU). Against experimental references, 13 of 19 graded comparisons meet the acceptance criteria (density 5 of 7, glass transition 4 of 7, bulk modulus 4 of 5). The failures are concentrated in the PCFF systems: under-density of aPS and PEG, overestimated glass transitions of the stiff PLLA and PEEK backbones, and an overstiff PEG bulk modulus.