# Migration as a Probe: A Generalizable Benchmark Framework for Specialist vs. Generalist Machine-Learned Force Fields

arXiv: https://arxiv.org/abs/2509.00090 · HTML: https://mlsanity.com/paper/2509.00090/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 71 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 7 of 7)

- [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)
- [Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics](https://mlsanity.com/paper/2204.05249/) (2022)
- [Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics](https://mlsanity.com/paper/1707.09571/) (2017)
- [Machine Learning Force Fields](https://mlsanity.com/paper/2010.07067/) (2020)
- [UMA: A Family of Universal Models for Atoms](https://mlsanity.com/paper/2506.23971/) (2025)
- [Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation](https://mlsanity.com/paper/1810.11890/) (2018)

## Abstract (arXiv)

Machine-learned force fields (MLFFs), especially pre-trained foundation models, are transforming computational materials science by enabling ab initio-level accuracy at molecular dynamics scales. Yet their rapid rise raises a key question: should researchers train specialist models from scratch, fine-tune generalist foundation models, or use hybrid approaches? The trade-offs in data efficiency, accuracy, cost, and robustness to out-of-distribution failure remain unclear. We introduce a benchmarking framework using defect migration pathways, evaluated through nudged elastic band trajectories, as diagnostic probes that test both interpolation and extrapolation. Using Cr-doped Sb2Te3 as a representative two-dimensional material, we benchmark multiple training paradigms within the MACE architecture across equilibrium, kinetic (atomic migration), and mechanical (interlayer sliding) tasks. Fine-tuned models substantially outperform from-scratch and zero-shot approaches for kinetic properties but show partial loss of long-range physics. Representational analysis reveals distinct, non-overlapping latent encodings, indicating that different training strategies learn different aspects of system physics. This framework provides practical guidelines for MLFF development and establishes migration-based probes as efficient diagnostics linking performance to learned representations, guiding future uncertainty-aware active learning.