mlsanityData to 7 Oct 2026

Science Done on a Machine by a Machine: AI Agents in Computational Chemistry

arXiv 2608.18508 ↗First posted 19 Aug 2026physics.chem-ph cs.AI physics.comp-phcited by 0

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

We are witnessing an explosion of agentic systems for computational chemistry: from four in 2024 to seventeen in 2025 and over sixty now, surveyed here. What is delegated to these systems is shifting from single calculations to whole in silico experiments and even manuscript writing. The ultimate destination is a fully autonomous AI scientist, where the entirety of computational chemistry is performed on a machine by a machine, without human supervision. Our survey shows that these systems are turning into vetted chemistry skills on general-purpose coding agents, and that they must be evaluated not only on their final answers but also on whether their calculations actually support these answers. The role of the human computational chemist is shifting from performing calculations to directing and supervising them, and the field should invest in the judgement that makes the supervision reliable: we propose a reporting standard, an evaluation reproducing published studies, a controlled comparison with general-purpose coding agents, and how to teach.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 42 of its 90 references that are in the map. First posted on arXiv 19 Aug 2026.

Builds on

42 of 90 references.

Closest ancestors · 22

Same direction, newest first

  1. 2026Agent-MD: Selective LLM Intervention with Event-Driven Escalation for Stateful GCMC--MD Campaigns7 Aug
  2. 2026CAi Copilot: Reducing Operational Workload in Molecular Design through Intent-Driven Agentic Workflows7 Aug
  3. 2026MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback11 Jun
  4. 2026MLIPilot: LLM-Driven Auto-Research for Machine-Learned Interatomic Potentials29 May
  5. 2026AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations25 May
  6. 2026Harnessing AtomisticSkills for Agentic Atomistic Research18 May
  7. 2026Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows14 May
  8. 2026Can Coding Agents Reproduce Findings in Computational Materials Science?1 May
  9. 2026ChemGraph-XANES: An Agentic Framework for XANES Simulation and Curation17 Apr
  10. 2026MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials Exploration3 Apr
  11. 2026SimMOF: AI agent for Automated MOF Simulations31 Mar
  12. 2026TritonDFT: Automating DFT with a Multi-Agent Framework2 Mar
10 more
  1. 2026El Agente Gr'afico: A Semantic Execution Runtime for Scientific Agents19 Feb
  2. 2026El Agente Quntur: A research collaborator agent for quantum chemistry4 Feb
  3. 2026QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities30 Jan
  4. 2025AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org12 Dec
  5. 2025GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols6 Dec
  6. 2025DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation18 Jul
  7. 2025Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists5 Jun
  8. 2025ChemGraph: An Agentic Framework for Computational Chemistry Workflows3 Jun
  9. 2025El Agente: An Autonomous Agent for Quantum Chemistry5 May
  10. 2024ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning27 Jan

Other references · 20

  1. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  2. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  3. 2025Accelerating scientific discovery with Co-Scientistcited by 353
  4. 2017Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanicscited by 213
  5. 2024CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmarkcited by 115
  6. 2024ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedbackcited by 32
  7. 2025MDCrow: Automating Molecular Dynamics Workflows with Large Language Modelscited by 22
  8. 2023MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflowscited by 10
  9. 2025DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulationscited by 6
  10. 2026PolyJarvis: An LLM-Orchestrated Agent for Automated All-Atom Molecular Dynamics of Amorphous Homopolymerscited by 6
  11. 2025Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentialscited by 5
  12. 2026El Agente Estructural: An Artificially Intelligent Molecular Editorcited by 5
8 more
  1. 2025ToPolyAgent: AI Agents for Coarse-Grained Topological Polymer Simulationscited by 2
  2. 2026Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twincited by 2
  3. 2026Catalyst-Agent: Autonomous heterogeneous catalyst screening with an LLM Agentcited by 1
  4. 2026Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Researchcited by 1
  5. 2026AdsMind: A Physics-Grounded Multi-Agent System for Self-Correcting Discovery of Adsorption Configurations on Heterogeneous Catalyst Surfacescited by 1
  6. 2026LLM-Guided Test-Time Discovery of Quantum-Chemical Approximation Algorithmscited by 1
  7. 2026An Agentic Orchestration of Atomistic Simulationscited by 1
  8. 2026A Multi-Agent Framework for Automated Coarse-Grained Molecular Dynamics of Polymerscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
  2. 2026From Prompts to Protocols: An AI Agent for Laboratory Automation
  3. 2025Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions
  4. 2025AI Agents in Drug Discovery
  5. 2024A Review of Large Language Models and Autonomous Agents in Chemistry
  6. 2026A Cloud-based Multi-Agentic Workflow for Science
  7. 2023Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis
  8. 2026Autonomous computational catalysis through an agentic research system