MIT researchers’ approach captures subtle atomic patterns, improving predictions of material properties.
arXiv:2610.08165v1 Announce Type: new Abstract: The mechanical properties of a metallic alloy are set by its microstructure and texture: the size and shape of its grains and the orientation of their...
arXiv:2610.28629v1 Announce Type: cross Abstract: Agentic artificial intelligence (AI) systems hold immense potential for automating complex workflows in materials discovery and design, but extending...
AtomWorld-Mirror introduces a time‑aware macro‑step world model that condenses short micro‑event segments into physically reachable transitions between key atomic states. By predicting sparse structural edits and accumulated physical time through latent macro‑step dynamics, it replaces explicit micro‑event replay with efficient macro‑step inference. Experiments on five atomic systems—including Cu‑rich RPV steel, Cu‑Zr metallic glass, and Li₃N‑based solid electrolytes—show speedups of 10³ to 10⁴ times over traditional event‑by‑event simulation while maintaining structural validity and time semantics.
AtomWorld-Mirror is a time‑aware macro‑step world model that compresses short micro‑event segments into physically reachable transitions between key atomic states, predicting sparse structural edits and accumulated physical time through latent macro‑step dynamics. By enforcing local reachability, inventory conservation, and continuous‑time consistency, the model replaces explicit micro‑event replay with macro‑step inference, enabling substantially faster long‑term materials evolution simulations. Across five atomic systems—including Cu‑rich RPV steel irradiation aging, Cu‑Zr metallic glass, and Li₃N‑based anti‑perovskite solid electrolyte—the approach achieves speed‑ups of 10³ to 10⁴ times over traditional event‑by‑event simulation.
The article reviews strategies for modeling chemical disorder in materials, addressing the gap between experimental descriptions of disorder and the detailed configurations required for atomistic simulations and AI workflows. It evaluates traditional approaches such as mean-field theories, cluster expansion, and Monte Carlo, alongside emerging AI-powered methods like universal interatomic potentials and generative models. The review also discusses how AI can accelerate computational schemes and enable disorder-native capabilities, providing a roadmap for integrating disorder into realistic AI-accelerated materials discovery.
The study uses large‑scale, quantum‑accurate reactive simulations powered by active learning and deep equivariant neural network potentials to investigate the coupled reactions and diffusion at the interface of a symmetric solid‑state battery cell. Unsupervised clustering of local atomic environments reveals a previously unreported crystalline disordered phase, Li₂S₀.₇₂P₀.₁₄Cl₀.₁₄, in the solid‑electrolyte interphase (SEI), and explains experimental observations of SEI formation and lithium creep mechanisms that drive dendrite initiation. The work demonstrates a parameter‑free digital twin capable of providing atomistic insights into complex heterogeneous processes in solid‑state electrochemistry.
The article reviews methods for assessing large language model (LLM) based AI agents in materials synthesis, focusing on their integration with experimental tools. It outlines evaluation strategies—including knowledge, reasoning, tool‑use, and closed‑loop benchmarks—and applies them to atomic layer deposition (ALD) as a case study. A practical framework for evaluating LLMs in this context is also presented.
New research enables AI models to perceive crystalline materials in three dimensions, allowing them to better understand and analyze the structure of these materials. By providing a clearer, more detailed view of the materials world, the study enhances the AI’s ability to reason about material properties. This advancement could improve the accuracy and usefulness of AI-driven material science investigations.
arXiv:2604. 14562v2 Announce Type: replace Abstract: Accurate temperature field prediction in metal additive manufacturing (AM) is essential for understanding the process-structure-performance relationship.
The article introduces the concept of agentic programs—scientific software that blends deterministic algorithms with bounded large‑language‑model (LLM) judgment, task‑specific verification, episodic maturation, and full delegation in production. It argues that recent LLM‑based agents enable this new form of computational materials science software. The authors illustrate the idea with DeMARS, an agentic program designed to build atomistic models from experimentally measured disordered crystal structures.
arXiv:2508. 05762v2 Announce Type: replace-cross Abstract: Universal machine learning force fields (UMLFFs) promise to revolutionize materials science by enabling rapid atomistic simulations across the periodic table.
The paper investigates whether machine learning models can uncover physical patterns in atomistic data without relying on traditional physics-based inductive biases such as geometric locality or graph structures. By training a general-purpose architecture on molecular simulation data, the authors demonstrate that the model autonomously learns interatomic interaction strengths resembling classical electrostatics and identifies interaction cutoffs aligned with established physical models. The study also reports predictable neural scaling behavior and competitive accuracy on certain metrics compared to physics-informed architectures, suggesting that explicit priors may only be necessary when empirically justified.