# MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics

arXiv: https://arxiv.org/abs/2601.02075 · HTML: https://mlsanity.com/paper/2601.02075/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 5 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research](https://mlsanity.com/paper/2402.00159/) (2024)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.13939/) (2025)
- [Machine learning for molecular simulation](https://mlsanity.com/paper/1911.02792/) (2019)
- [MatterGen: a generative model for inorganic materials design](https://mlsanity.com/paper/2312.03687/) (2023)
- [14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon](https://mlsanity.com/paper/2306.06283/) (2023)
- [Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey](https://mlsanity.com/paper/2412.20367/) (2024)
- [Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities](https://mlsanity.com/paper/2409.03444/) (2024)
- [HoneyComb: A Flexible LLM-Based Agent System for Materials Science](https://mlsanity.com/paper/2409.00135/) (2024)
- [QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training](https://mlsanity.com/paper/2506.00711/) (2025)
- [Efficient Continual Pre-training for Building Domain Specific Large Language Models](https://mlsanity.com/paper/2311.08545/) (2023)
- [MDCrow: Automating Molecular Dynamics Workflows with Large Language Models](https://mlsanity.com/paper/2502.09565/) (2025)
- [Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations](https://mlsanity.com/paper/2504.09602/) (2025)
- [DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles](https://mlsanity.com/paper/2207.01079/) (2022)
- [Assessing the Chemical Intelligence of Large Language Models](https://mlsanity.com/paper/2505.07735/) (2025)

## Built on by (most cited first, 7 of 7)

- [QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities](https://mlsanity.com/paper/2602.00185/) (2026)
- [MDGYM: Benchmarking AI Agents on Molecular Simulations](https://mlsanity.com/paper/2605.08941/) (2026)
- [Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters](https://mlsanity.com/paper/2606.09774/) (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)
- [Molecular LLM Agents: From Architectural Design to Scientific Autonomy](https://mlsanity.com/paper/2608.23104/) (2026)
- [NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents](https://mlsanity.com/paper/2610.03631/) (2026)

## Abstract (arXiv)

Molecular dynamics (MD) simulations are essential for understanding atomic-scale behaviors in materials science, yet writing LAMMPS scripts remains highly specialized and time-consuming tasks. Although LLMs show promise in code generation and domain-specific question answering, their performance in MD scenarios is limited by scarce domain data, the high deployment cost of state-of-the-art LLMs, and low code executability. Building upon our prior MDAgent, we present MDAgent2, the first end-to-end framework capable of performing both knowledge Q&A and code generation within the MD domain. We construct a domain-specific data-construction pipeline that yields three high-quality datasets spanning MD knowledge, question answering, and code generation. Based on these datasets, we adopt a three stage post-training strategy--continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL)--to train two domain-adapted models, MD-Instruct and MD-Code. Furthermore, we introduce MD-GRPO, a closed-loop RL method that leverages simulation outcomes as reward signals and recycles low-reward trajectories for continual refinement. We further build MDAgent2-RUNTIME, a deployable multi-agent system that integrates code generation, execution, evaluation, and self-correction. Together with MD-EvalBench proposed in this work, the first benchmark for LAMMPS code generation and question answering, our models and system achieve performance surpassing several strong baselines.This work systematically demonstrates the adaptability and generalization capability of large language models in industrial simulation tasks, laying a methodological foundation for automatic code generation in AI for Science and industrial-scale simulations. URL: https://github.com/FredericVAN/PKU_MDAgent2