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

arXiv: https://arxiv.org/abs/2608.18508 · HTML: https://mlsanity.com/paper/2608.18508/

## Key facts

- No citing papers in the map yet (data through 14 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.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 30 of 42)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields](https://mlsanity.com/paper/2206.07697/) (2022)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics](https://mlsanity.com/paper/1707.09571/) (2017)
- [CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark](https://mlsanity.com/paper/2409.11363/) (2024)
- [ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning](https://mlsanity.com/paper/2402.04268/) (2024)
- [El Agente: An Autonomous Agent for Quantum Chemistry](https://mlsanity.com/paper/2505.02484/) (2025)
- [ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback](https://mlsanity.com/paper/2402.10980/) (2024)
- [DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation](https://mlsanity.com/paper/2507.14267/) (2025)
- [MDCrow: Automating Molecular Dynamics Workflows with Large Language Models](https://mlsanity.com/paper/2502.09565/) (2025)
- [ChemGraph: An Agentic Framework for Computational Chemistry Workflows](https://mlsanity.com/paper/2506.06363/) (2025)
- [MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows](https://mlsanity.com/paper/2310.20155/) (2023)
- [Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists](https://mlsanity.com/paper/2506.05616/) (2025)
- [Can Coding Agents Reproduce Findings in Computational Materials Science?](https://mlsanity.com/paper/2605.00803/) (2026)
- [El Agente Quntur: A research collaborator agent for quantum chemistry](https://mlsanity.com/paper/2602.04850/) (2026)
- [DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulations](https://mlsanity.com/paper/2512.10034/) (2025)
- [QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities](https://mlsanity.com/paper/2602.00185/) (2026)
- [PolyJarvis: An LLM-Orchestrated Agent for Automated All-Atom Molecular Dynamics of Amorphous Homopolymers](https://mlsanity.com/paper/2604.02537/) (2026)
- [Harnessing AtomisticSkills for Agentic Atomistic Research](https://mlsanity.com/paper/2605.24002/) (2026)
- [Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentials](https://mlsanity.com/paper/2509.21647/) (2025)
- [El Agente Estructural: An Artificially Intelligent Molecular Editor](https://mlsanity.com/paper/2602.04849/) (2026)
- [TritonDFT: Automating DFT with a Multi-Agent Framework](https://mlsanity.com/paper/2603.03372/) (2026)
- [SimMOF: AI agent for Automated MOF Simulations](https://mlsanity.com/paper/2603.29152/) (2026)
- [GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols](https://mlsanity.com/paper/2512.06404/) (2025)
- [El Agente Gr'afico: A Semantic Execution Runtime for Scientific Agents](https://mlsanity.com/paper/2602.17902/) (2026)
- [MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials Exploration](https://mlsanity.com/paper/2604.02688/) (2026)
- [MLIPilot: LLM-Driven Auto-Research for Machine-Learned Interatomic Potentials](https://mlsanity.com/paper/2605.30889/) (2026)
- [ToPolyAgent: AI Agents for Coarse-Grained Topological Polymer Simulations](https://mlsanity.com/paper/2510.12091/) (2025)
- [AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org](https://mlsanity.com/paper/2512.11935/) (2025)
- [Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows](https://mlsanity.com/paper/2605.14527/) (2026)

## 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.