mlsanityData to 7 Oct 2026

MDCrow: Automating Molecular Dynamics Workflows with Large Language Models

arXiv 2502.09565 ↗First posted 13 Feb 2025cs.AI physics.chem-phcited by 22

Not on the map. Why?

Abstract (arXiv)

Molecular dynamics (MD) simulations are essential for understanding biomolecular systems but remain challenging to automate. Recent advances in large language models (LLM) have demonstrated success in automating complex scientific tasks using LLM-based agents. In this paper, we introduce MDCrow, an agentic LLM assistant capable of automating MD workflows. MDCrow uses chain-of-thought over 40 expert-designed tools for handling and processing files, setting up simulations, analyzing the simulation outputs, and retrieving relevant information from literature and databases. We assess MDCrow's performance across 25 tasks of varying required subtasks and difficulty, and we evaluate the agent's robustness to both difficulty and prompt style. textttgpt-4o is able to complete complex tasks with low variance, followed closely by textttllama3-405b, a compelling open-source model. While prompt style does not influence the best models' performance, it has significant effects on smaller models.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 25 of its 104 references that are in the map. First posted on arXiv 13 Feb 2025.

Builds on

25 of 104 references.

References · 25

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2024GPT-4o System Cardcited by 4,467
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  7. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  8. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  9. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  10. 2022BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Miningcited by 531
  11. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  12. 2024LAB-Bench: Measuring Capabilities of Language Models for Biology Researchcited by 138
13 more
  1. 2024Language agents achieve superhuman synthesis of scientific knowledgecited by 121
  2. 2024Empowering Biomedical Discovery with AI Agentscited by 117
  3. 2023AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learncited by 97
  4. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
  5. 202314 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathoncited by 85
  6. 2024MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learningcited by 66
  7. 2024ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learningcited by 63
  8. 2023BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biologycited by 42
  9. 2024LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillationcited by 32
  10. 2023Opportunities for Retrieval and Tool Augmented Large Language Models in Scientific Facilitiescited by 27
  11. 2024Aviary: training language agents on challenging scientific taskscited by 23
  12. 2015FabSim: facilitating computational research through automation on large-scale and distributed e-infrastructurescited by 1
  13. 2023CACTUS: A Computational Framework for Generating Realistic White Matter Microstructure Substratescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 13.

22 papers.

Sort:

By area:

  1. 2025El Agente: An Autonomous Agent for Quantum Chemistrycited by 43
  2. 2025DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulationcited by 29
  3. 2025ChemGraph: An Agentic Framework for Computational Chemistry Workflowscited by 16
  4. 2025Assessing the Chemical Intelligence of Large Language Modelscited by 14
  5. 2025Towards LLM Agents for Earth Observationcited by 13
  6. 2025AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentationcited by 13
  7. 2025Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulationscited by 8
  8. 2026El Agente Quntur: A research collaborator agent for quantum chemistrycited by 7
  9. 2025DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulationscited by 6
  10. 2026MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamicscited by 6
  11. 2026MDGYM: Benchmarking AI Agents on Molecular Simulationscited by 3
  12. 2026Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflowscited by 2
10 more
  1. 2026MDArena: Evaluating Coding Agents on Realistic Molecular Dynamics Workflowscited by 2
  2. 2026Agent-MD: Selective LLM Intervention with Event-Driven Escalation for Stateful GCMC--MD Campaignscited by 2
  3. 2026From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistrycited by 1
  4. 2026LLM-Guided Test-Time Discovery of Quantum-Chemical Approximation Algorithmscited by 1
  5. 2026A Multi-Agent Framework for Automated Coarse-Grained Molecular Dynamics of Polymerscited by 1
  6. 2025Prospects for Using Artificial Intelligence to Understand Intrinsic Kinetics of Heterogeneous Catalytic Reactionscited by 0
  7. 2026Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branchescited by 0
  8. 2026Science Done on a Machine by a Machine: AI Agents in Computational Chemistrycited by 0
  9. 2026Molecular LLM Agents: From Architectural Design to Scientific Autonomycited by 0
  10. 2026Editorial routing shapes how computational results are qualified in AI-assisted scientific writingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback
  2. 2025Automating MD simulations for Proteins using Large language Models: NAMD-Agent
  3. 2024AgentDrug: Utilizing Large Language Models in An Agentic Workflow for Zero-Shot Molecular Editing
  4. 2026Evaluating LLM-generated code for domain-specific languages: molecular dynamics with LAMMPS
  5. 2025Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design
  6. 2026Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery
  7. 2026EvoMD-LLM: Learning the Language of Species Evolution in Reactive Molecular Dynamics
  8. 2025MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization