Machine learning force fields (MLFFs) have revolutionized molecular simulations by providing quantum mechanical accuracy at the speed of molecular mechanical computations. However, a fundamental reliance of these models on fixed-cutoff architectures limits their applicability to macromolecular systems where long-range interactions dominate. We demonstrate that this locality constraint causes force prediction errors to scale monotonically with system size, revealing a critical architectural bottleneck. To overcome this, we establish the systematically designed MolLR25 ({Mol}ecules with {L}ong-{R}ange effect) benchmark up to 1200 atoms, generated using high-fidelity DFT, and introduce E2Former-LSR, an equivariant transformer that explicitly integrates long-range attention blocks. E2Former-LSR exhibits stable error scaling, achieves superior fidelity in capturing non-covalent decay, and maintains precision on complex protein conformations. Crucially, its efficient design provides up to 30% speedup compared to purely local models. This work validates the necessity of non-local architectures for generalizable MLFFs, enabling high-fidelity molecular dynamics for large-scale chemical and biological systems.

翻译：机器学习力场（MLFFs）通过以分子力学计算的速度提供量子力学精度，彻底改变了分子模拟领域。然而，这些模型对固定截断架构的根本依赖限制了其在长程相互作用占主导的大分子系统中的适用性。我们证明，这种局部性约束导致力预测误差随系统尺寸单调增长，揭示了一个关键的结构瓶颈。为克服此限制，我们建立了系统设计的MolLR25（具有长程效应的分子）基准数据集（原子数高达1200个，基于高精度密度泛函理论生成），并引入了E2Former-LSR——一种显式集成长程注意力模块的等变Transformer模型。E2Former-LSR展现出稳定的误差缩放特性，在捕获非共价衰减方面具有卓越的保真度，并在复杂蛋白质构象上保持精度。至关重要的是，其高效设计相比纯局部模型可实现高达30%的加速。这项工作验证了非局部架构对于通用化MLFFs的必要性，从而为大规模化学与生物系统的高保真分子动力学模拟提供了可能。