# A practical guide to machine learning interatomic potentials -- Status and future

arXiv: https://arxiv.org/abs/2503.09814 · HTML: https://mlsanity.com/paper/2503.09814/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 173 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Builds on (most cited first, 30 of 38)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials](https://mlsanity.com/paper/2101.03164/) (2021)
- [MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields](https://mlsanity.com/paper/2206.07697/) (2022)
- [Crystal Diffusion Variational Autoencoder for Periodic Material Generation](https://mlsanity.com/paper/2110.06197/) (2021)
- [Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics](https://mlsanity.com/paper/2204.05249/) (2022)
- [Machine Learning Force Fields](https://mlsanity.com/paper/2010.07067/) (2020)
- [EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations](https://mlsanity.com/paper/2306.12059/) (2023)
- [e3nn: Euclidean Neural Networks](https://mlsanity.com/paper/2207.09453/) (2022)
- [Deep neural network solution of the electronic Schr"odinger equation](https://mlsanity.com/paper/1909.08423/) (2019)
- [Machine learning for molecular simulation](https://mlsanity.com/paper/1911.02792/) (2019)
- [The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials](https://mlsanity.com/paper/2205.06643/) (2022)
- [MatterGen: a generative model for inorganic materials design](https://mlsanity.com/paper/2312.03687/) (2023)
- [Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations](https://mlsanity.com/paper/2210.07237/) (2022)
- [Fine-Tuned Language Models Generate Stable Inorganic Materials as Text](https://mlsanity.com/paper/2402.04379/) (2024)
- [Less is more: sampling chemical space with active learning](https://mlsanity.com/paper/1801.09319/) (2018)
- [DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics](https://mlsanity.com/paper/1712.03641/) (2017)
- [Orb: A Fast, Scalable Neural Network Potential](https://mlsanity.com/paper/2410.22570/) (2024)
- [DScribe: Library of Descriptors for Machine Learning in Materials Science](https://mlsanity.com/paper/1904.08875/) (2019)
- [Scalable Diffusion for Materials Generation](https://mlsanity.com/paper/2311.09235/) (2023)
- [From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction](https://mlsanity.com/paper/2310.16802/) (2023)
- [Matbench Discovery -- A framework to evaluate machine learning crystal stability predictions](https://mlsanity.com/paper/2308.14920/) (2023)
- [Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size](https://mlsanity.com/paper/2304.10061/) (2023)
- [Machine learning for electronically excited states of molecules](https://mlsanity.com/paper/2007.05320/) (2020)
- [Hyperactive Learning (HAL) for Data-Driven Interatomic Potentials](https://mlsanity.com/paper/2210.04225/) (2022)
- [TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations](https://mlsanity.com/paper/1912.01398/) (2019)
- [86 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracy](https://mlsanity.com/paper/2004.11658/) (2020)
- [Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics](https://mlsanity.com/paper/2002.07264/) (2020)
- [Tensor-reduced atomic density representations](https://mlsanity.com/paper/2210.01705/) (2022)
- [WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials](https://mlsanity.com/paper/1712.05861/) (2017)
- [Spin-Dependent Graph Neural Network Potential for Magnetic Materials](https://mlsanity.com/paper/2203.02853/) (2022)

## Built on by (most cited first, 26 of 26)

- [FlashMD: long-stride, universal prediction of molecular dynamics](https://mlsanity.com/paper/2505.19350/) (2025)
- [Scalable Boltzmann Generators for equilibrium sampling of large-scale materials](https://mlsanity.com/paper/2509.25486/) (2025)
- [MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interatomic Potentials](https://mlsanity.com/paper/2603.02002/) (2026)
- [Harnessing AtomisticSkills for Agentic Atomistic Research](https://mlsanity.com/paper/2605.24002/) (2026)
- [Molecular Machine Learning in Chemical Process Design](https://mlsanity.com/paper/2508.20527/) (2025)
- [Learning Inter-Atomic Potentials without Explicit Equivariance](https://mlsanity.com/paper/2510.00027/) (2025)
- [Generative Models for Crystalline Materials](https://mlsanity.com/paper/2511.22652/) (2025)
- [Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs](https://mlsanity.com/paper/2605.03964/) (2026)
- [Smooth Dynamic Cutoffs for Machine Learning Interatomic Potentials](https://mlsanity.com/paper/2601.21147/) (2026)
- [Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs](https://mlsanity.com/paper/2605.13788/) (2026)
- [ADAPT: Lightweight, Long-Range Machine Learning Force Fields Without Graphs](https://mlsanity.com/paper/2509.24115/) (2025)
- [Proof-Carrying Materials: Falsifiable Safety Certificates for Machine-Learned Interatomic Potentials](https://mlsanity.com/paper/2603.12183/) (2026)
- [Accurate, transferable, and verifiable machine-learned interatomic potentials for layered materials](https://mlsanity.com/paper/2503.15432/) (2025)
- [Knowledge Distillation Framework for Accelerating High-Accuracy Neural Network-Based Molecular Dynamics Simulations](https://mlsanity.com/paper/2506.15337/) (2025)
- [Model Accuracy and Data Heterogeneity Shape Uncertainty Quantification in Machine Learning Interatomic Potentials](https://mlsanity.com/paper/2508.03405/) (2025)
- [Motional representation; the ability to predict odor characters using molecular vibrations](https://mlsanity.com/paper/2509.16245/) (2025)
- [Why Physics Still Matters: Improving Machine Learning Prediction of Material Properties with Phonon-Informed Datasets](https://mlsanity.com/paper/2511.15222/) (2025)
- [On The Finetuning of MLIPs Through the Lens of Iterated Maps With BPTT](https://mlsanity.com/paper/2512.01067/) (2025)
- [From Regression to Classification: Exploring the Benefits of Categorical Representations of Energy in MLIPs](https://mlsanity.com/paper/2512.01160/) (2025)
- [Comparing the latent features of universal machine-learning interatomic potentials](https://mlsanity.com/paper/2512.05717/) (2025)
- [Autotuning T-PaiNN: Enabling Data-Efficient GNN Interatomic Potential Development via Classical-to-Quantum Transfer Learning](https://mlsanity.com/paper/2603.24752/) (2026)
- [Making Room for AI: Multi-GPU Molecular Dynamics with Deep Potentials in GROMACS](https://mlsanity.com/paper/2604.07276/) (2026)
- [GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond](https://mlsanity.com/paper/2606.03232/) (2026)
- [Scaling Density Functional Theory with Gaussian Splatting](https://mlsanity.com/paper/2609.31483/) (2026)
- [MOF-VERIFY: A Failure-Aware Agentic Harness for MOF Hypothesis Verification](https://mlsanity.com/paper/2610.03056/) (2026)
- [Automatically Building and Updating a Knowledge Graph of MLIP Models](https://mlsanity.com/paper/2610.09644/) (2026)

## Abstract (arXiv)

The rapid development and large body of literature on machine learning interatomic potentials (MLIPs) can make it difficult to know how to proceed for researchers who are not experts but wish to use these tools. The spirit of this review is to help such researchers by serving as a practical, accessible guide to the state-of-the-art in MLIPs. This review paper covers a broad range of topics related to MLIPs, including (i) central aspects of how and why MLIPs are enablers of many exciting advancements in molecular modeling, (ii) the main underpinnings of different types of MLIPs, including their basic structure and formalism, (iii) the potentially transformative impact of universal MLIPs for both organic and inorganic systems, including an overview of the most recent advances, capabilities, downsides, and potential applications of this nascent class of MLIPs, (iv) a practical guide for estimating and understanding the execution speed of MLIPs, including guidance for users based on hardware availability, type of MLIP used, and prospective simulation size and time, (v) a manual for what MLIP a user should choose for a given application by considering hardware resources, speed requirements, energy and force accuracy requirements, as well as guidance for choosing pre-trained potentials or fitting a new potential from scratch, (vi) discussion around MLIP infrastructure, including sources of training data, pre-trained potentials, and hardware resources for training, (vii) summary of some key limitations of present MLIPs and current approaches to mitigate such limitations, including methods of including long-range interactions, handling magnetic systems, and treatment of excited states, and finally (viii) we finish with some more speculative thoughts on what the future holds for the development and application of MLIPs over the next 3-10+ years.