Fine-Tuning Unifies Foundational Machine-Learned Interatomic Potential Architectures at <i>ab initio</i> Accuracy

This work demonstrates that fine-tuning transforms foundational machine-learned interatomic potentials (MLIPs) to achieve consistent, near-<i>ab initio</i> accuracy across diverse architectures. Benchmarking five leading MLIP frameworks (MACE, GRACE, SevenNet, MatterSim, and ORB) across seven chemically diverse compounds reveals that fine-tuning universally enhances force predictions by factors of 5-15 and improves energy accuracy by 2-4 orders of magnitude. The investigated models span both equivariant and invariant, as well as conservative and non-conservative, architectures. While general-purpose foundation models are robust, they exhibit architecture-dependent deviations from <i>ab initio</i> reference data; specialized system-specific training (fine-tuning) eliminates these discrepancies, enabling quantitatively accurate predictions of atomistic and structural properties. Using datasets constructed from 2000 equidistantly sampled frames of short <i>ab initio</i> molecular dynamics trajectories, fine-tuning reduces force errors by an order of magnitude and harmonizes performance across all architectures. These findings establish fine-tuning as a universal route to achieving system-specific predictive accuracy while preserving the computational efficiency of MLIPs. To promote widespread adoption, we introduce the <i>aMACEing Toolkit</i>, which provides a unified and reproducible interface for fine-tuning workflows across multiple MLIP frameworks.