Connecting 0 K density functional theory (DFT) energies to finite-temperature, finite-pressure synthesis conditions is a well-established thermodynamic formalism, yet quantified guidance on when and how to accurately calibrate these results to experimental chemical potentials in practice remains sparse. In this work, we systematically benchmark a complete workflow-the virtual furnace-that constructs effective oxygen chemical potentials (mu O2) for common synthesis atmospheres (air, Ar, H2, CO) as functions of temperature and partial pressure and propagates quantified errors from formation enthalpies through reaction energies to critical chemical potentials. Applying this workflow to 11 binary oxides, we find that "gas-only" thermal corrections are sufficient at low temperatures and for Group II oxides across all temperatures, while solid-phase vibrational contributions become critical at elevated temperatures for transition metal oxides. We quantify this threshold through the ratio |Delta S solid/Delta S total| as a practical guide for when phonon calculations are warranted. Predicted critical reduction temperatures and oxygen chemical potentials show strong agreement with industrial practice and experimental data, with typical errors of 150-250 degrees C for most oxides. This benchmarked workflow provides practitioners with explicit, quantified guidance for predictive modeling of phase stability and synthesis condition design.

Disordered rock-salt with Li-excess (DRX) cathode phases within the Li-Mn-Ti-O (LMTO) composition space have recently been extensively studied, as they promise to deliver exceptional energy density at low cost in Li-ion batteries. The continued development of LMTO DRX with improved power density and cycling stability requires optimization of the composition and particle size/morphology, which are determined by synthesis conditions such as annealing temperatures and hold times. These challenges motivate our investigation of the phase diagram of the LMTO rock-salt phase space, with a focus on understanding the stability of DRX by quantifying the order-disorder transition temperature (T_disord) as a function of composition. We harness first-principles calculations and X-ray diffraction experiments to establish the LMTO phase diagram, which lies within the LiMnO_2 – Li_2MnO_3 – Li_2TiO_3 pseudo-ternary. Our calculations predict that the LMTO phase diagram at elevated temperature (700 - 1300 C) is composed of three phases: DRX, orthorhombic LiMnO_2, and layered Li_2Mn_1-yTi_yO_3 (0 < y < 1). T_disord decreases significantly as off-stoichiometry is introduced to the end-point compositions, resulting in a eutectoid phase diagram. Importantly, a significant range of LMTO compositions containing small to moderate fractions of Li-excess and Ti doping (relative to LiMnO_2) have T_disord spanning 700 - 900 C. These temperatures are substantially lower than conventional DRX synthesis temperatures (≥ 1000 C), suggesting the promise of decreasing synthesis temperatures for specific DRX compositions. The compositions containing moderate to high fractions of Mn^4+ instead have much greater T_disord and phase separation to layered Li_2MnO_3 becomes highly favored.

Amorphous oxyhalides have attracted significant attention due to their relatively high ionic conductivity (1 mS ), excellent chemical stability, mechanical softness, and facile synthesis routes via standard solid-state reactions. These materials exhibit an ionic conductivity that is almost independent of the underlying chemistry, in stark contrast to what occurs in crystalline conductors. In this work, we employ machine learning interatomic potentials to construct large-scale molecular dynamics trajectories encompassing hundreds of nanoseconds to obtain statistically converged transport properties. We find that the amorphous state consists of chain fragments of metal-anion tetrahedra of various lengths. By analyzing the residence time of alkali cations migrating around tetrahedrally-coordinated metals, we find that oxygen anions limit alkali diffusion. By computing the full Einstein expression of the ionic conductivity, we demonstrate that the alkali transference number of these materials is strongly influenced by distinct-particles correlations, while alkali transport is dictated by uncorrelated self-diffusion. By extending this analysis to chemical compositions , spanning different alkaline ( = Li, Na, K), metallic ( = Al, Ga, In), and halogen ( = Cl, Br, I) species, we clarify why the diffusion properties of these materials remain largely insensitive to variations in atomic isovalent chemistry.

Sodium-ion solid electrolytes offer a sustainable route toward next-generation batteries, but few match the performance of their lithium counterparts. Halide-based NaMOCl4 (M = Nb, Ta) has recently emerged as a promising analogue to LiMOCl4, yet its structure-transport relationships remain unclear due to poor crystallinity in experiments. Here, we combine density functional theory and machine-learned molecular dynamics to reveal that crystalline NaMOCl4 exhibits negligible room-temperature conductivity with high activation barriers arising from vacancy-mediated diffusion below an order-disorder transition. Above this transition, rotational and translational motion of the [MO2/2Cl4 -]∞ chains create new Na sites and enhances transport. In contrast, the amorphous phase inherently supports facile, three-dimensional Na diffusion through dynamic framework flexibility. These results show that ordered crystalline phases hinder ionic transport, while disorder - either thermally induced or structural - facilitates it, revising prior assumptions from the Li system and providing design principles for high-conductivity Na halide electrolytes.

Solid-state batteries require lithium-ion conductors that combine high ionic conductivity with stability under harsh electrochemical and chemical conditions. Here, we investigate the chemical factors governing the stability of NASICON-type and garnet-type Li-ion conductors in highly alkaline environments. This is particularly relevant to solid-state Li-air cells operated under humidified air, where alkaline conditions arise due to the formation of LiOH discharge products. We implement a hierarchical high-throughput screening workflow that consists of a pre-screening step using a universal machine-learning interatomic potential and a more accurate density functional theory (DFT)-based screening. This approach enables rapid evaluation of over 320,000 compositions, from which 209 alkaline-stable candidates are identified. We identify specific cation substitutions that improve alkaline stability in NASICON and garnet compounds and reveal the underlying mechanism. More importantly, we highlight design trade-offs that require careful composition optimization to simultaneously enhance synthesizability, operational stability, and Li-ion/electronic conductivities for practical humid Li-air battery applications.

Materials discovery is fundamental to advance next-generation technologies as well as for sustainable and circular economy. Beyond computational screening, generative models are efficient at finding materials with desired properties, via multi-modal learning using multiscale data. This perspective examines the landscape of generative design for inorganic materials and discusses the integration of multi-modal learning with high-throughput experimental validation. We contextualize these challenges through the lens of a generative design framework as a unified approach to address the data-driven inverse design of functional materials. The central idea of the framework is constructed around a foundation AI model for inorganic materials interlinked deeply with various property databases and high-throughput experiments via a machine learning driven closed loop, which enables the framework to solve key challenges in functional materials. We argue that domain-specific implementations of such integrated workflows represent a promising pathway toward the unresolved challenge of data-driven inverse design for atom-engineered inorganic functional materials.

Solid-state reactions remain the dominant route to inorganic materials, yet no large, machine-readable dataset reports their experimental protocols and outcomes with consistent provenance; this gap obstructs first-principles, data-driven, and machine-learning approaches to synthesis science. Here, we present the Precursor Genome, a dataset of 1,035 pairwise solid-state reactions generated autonomously by the A-Lab self-driving laboratory, spanning 46 precursors and 39 elements. Every reaction is reported together with its full experimental metadata, including measured thermal profiles, precursor and recovered masses, and instrument configuration. Every product mixture is identified from raw X-ray diffraction (1,351 scans) through automated Rietveld refinement with the Dara framework, yielding 1,950 refinement cases that are independently validated by human experts on a three-tier quality scale. Raw pattern files, serialized refinement objects, and reviewer annotations are distributed through a Pydantic-validated JSON ledger, preserving full traceability from each precursor pair to its final phase assignment. The Precursor Genome establishes a FAIR, reusable benchmark for training and evaluating predictive models of solid-state reactivity.

Compositional characterization is essential for understanding and optimizing material performance. For powder-based materials underpinning many modern technologies, however, accurately and rapidly resolving the composition of individual constituent phases remains an unsolved challenge, slowing materials research and limiting autonomous laboratory platforms. Scanning electron microscopy with energy-dispersive X-ray spectroscopy (SEM-EDS) offers a time- and cost-effective route, but artifacts generated by irregular particle morphologies fundamentally limit its reliability for quantitative compositional analysis. Here, we introduce a scalable particle-based SEM-EDS quantification scheme that overcomes these artifacts requiring only one experimental standard per element, including light elements conventionally difficult to quantify. To deploy this capability at scale, we then integrate this core quantification scheme with automated measurements and unsupervised machine-learning analysis in an end-to-end automated Python-based framework, AutoEMX, to enable identification and extraction of phase-level compositions within multiphase samples. AutoEMX consistently quantifies atomic fractions across diverse chemistries with relative errors below 10% and typically below 5%, resolving primary phases and intermixed impurities that evade conventional particle-averaged analysis. This work removes a long-standing barrier to rapid powder compositional characterization, enabling seamless integration in autonomous laboratories for accelerated discovery. Researchers introduce AutoEMX, an automated SEM-EDS framework that overcomes particle-shape quantification artifacts to resolve the individual compositions in multi-phase powders with 5-10% error, integrating into self-driving labs for accelerated material discovery

Understanding structure-property relationships in materials is fundamental in condensed matter physics and materials science. Over the past few years, machine learning (ML) has emerged as a powerful tool for advancing this understanding and accelerating materials discovery. Early ML approaches primarily focused on constructing and screening large material spaces to identify promising candidates for various applications. More recently, research efforts have increasingly shifted toward generating crystal structures using end-to-end generative models. This review analyzes the current state of generative modeling for crystal structure prediction and de novo generation. It examines crystal representations, outlines the generative models used to design crystal structures, and evaluates their respective strengths and limitations. Furthermore, the review highlights experimental considerations for evaluating generated structures and provides recommendations for suitable existing software tools. Emerging topics, such as modeling disorder and defects, integration in advanced characterization, incorporating synthetic feasibility constraints, and model explainability are explored. Ultimately, this work aims to inform both experimental scientists looking to adapt suitable ML models to their specific circumstances and ML specialists seeking to understand the unique challenges related to inverse materials design and discovery.

Scientific reasoning in materials science requires integrating multimodal experimental evidence with underlying physical theory. Existing benchmarks make it difficult to assess whether incorporating visual experimental data during post-training improves mechanism-grounded explanation reasoning beyond text-only supervision. We introduce MATRIX, a multimodal benchmark for materials science reasoning that evaluates foundational theory, research-level reasoning, and the interpretation of real experimental artifacts across multiple characterization modalities. Using MATRIX as a controlled diagnostic, we isolate the effect of visual grounding by comparing post-training on structured materials science text alone with post-training that incorporates paired experimental images. Despite using relatively small amounts of multimodal data, visual supervision improves experimental interpretation by 10-25

Autonomous laboratories increasingly enable materials synthesis at scale, but traditional high-throughput characterization workflows remain limited by the need for expert chemical intuition to distinguish plausible interpretations from formally good but chemically incorrect fits. We present an automated interpretation framework that combines probabilistic inference with automated chemical reasoning for phase identification from powder x-ray diffraction (PXRD). The framework evaluates multiple candidate interpretations using diffraction pattern-based metrics. It then refines these likelihoods using chemically-informed priors derived from composition balance and a large language model (LLM)-based plausibility estimate with human-readable justification and also produces a trustworthiness score. In a blinded multi-project benchmark, the framework's top-ranked interpretation was selected over the lowest- R wp baseline in 93% of cases where evaluators expressed a clear preference (95% CI: [78%, 98%], n = 30 ). Trust decisions made by the framework aligned with expert judgment in approximately 75%-80% of cases. In a second evaluation, the framework systematically identified cases where lowest- R wp interpretations were chemically implausible and surfaced credible alternatives to historically ambiguous samples. By reframing phase identification as a problem of probabilistic reasoning and trust-aware decision making, this work demonstrates how chemical intuition can be automated and scaled.

Establishing viable solid-state synthesis pathways for novel inorganic materials remains a major challenge in materials science. Previous pathway design methods using pairwise reaction approaches have navigated the thermodynamic landscape with first-principles data but lack kinetic information, limiting their effectiveness. This gap leads to suboptimal precursor selection and predictions, especially for reactions forming competing phases with similar formation energies, where ion diffusion is a critical influence. Here we demonstrate an inorganic synthesis framework by incorporating machine learning-derived transport properties through 'liquid-like' product layers into a thermodynamic cellular reaction model. In the Ba-Ti-O system, known for its competitive polymorphism, we obtain accurate predictions of phase formation with varying BaO:TiO2 ratios as a function of time and temperature. We find that diffusion-thermodynamics interplay governs phase compositions, with cross-ion transport coefficients critical for predicting diffusion-limited selectivity. This work bridges length scales and timescales by integrating solid-state reaction kinetics with first-principles thermodynamics and spatial reactivity.

Electrochemically redox-active halide (eREAL) materials are an emerging class of materials that combine high Li-ion conductivity with transition-metal redox activity, making them promising candidates for cathode or catholyte applications. As a redox-active catholyte, they could significantly increase the energy density of solid-state batteries. In this work, we perform first-principles calculations on Li-M-Cl (M = 3d transition metals) ternaries to establish such a theoretical foundation for their stability and electrochemical activity. We map the phase stability of eREAL structures with varying metal-to-Cl ratio, transition-metal species, oxidation states, and anion frameworks, and compute cation and anion redox potentials. We find that the high ionicity of metal-Cl bonds elevates cation redox potentials above those of conventional oxide cathodes, but also will promote Cl oxidation and Cl-Cl dimerization at high voltages, which may limit the stability of these materials. Anion substitution effectively tunes both cation and anion redox potentials, with F substitution standing out as a viable route to extend the reversible voltage window. Beyond the anion redox issue, eREAL compounds generally exhibit flat voltage profiles, which potentially poses an electrochemical compatibility challenge when paired with active materials that operate at different voltage values or over wider voltage ranges. Collectively, our study provides a comprehensive analysis for redox behavior of eREAL materials, paving the way for their rational design and optimization in next-generation battery applications.

Large-scale atomistic simulations are essential to bridge computational materials and chemistry to realistic materials and drug discovery applications. In the past few years, rapid developments of machine learning interatomic potentials (MLIPs) have offered a solution to scale up quantum mechanical calculations. Parallelizing these interatomic potentials across multiple devices poses a challenging, but promising approach to further extending simulation scales to real-world applications. In this work, we present \textbf{DistMLIP}, an efficient distributed inference platform for MLIPs based on zero-redundancy, graph-level parallelization. In contrast to conventional space-partitioning parallelization, DistMLIP enables efficient MLIP parallelization through graph partitioning, allowing multi-device inference on flexible MLIP model architectures like multi-layer graph neural networks. DistMLIP presents an easy-to-use, flexible, plug-in interface that enables distributed inference of pre-existing MLIPs. We demonstrate DistMLIP on four widely used and state-of-the-art MLIPs: CHGNet, MACE, TensorNet, and eSEN. We show that existing foundation potentials can perform near-million-atom calculations at the scale of a few seconds on 8 GPUs with DistMLIP.

Understanding the moisture stability of oxide Li-ion conductors is important for their practical applications in solid-state batteries. Unlike sulfide or halide conductors, oxide conductors generally better resist degradation when in contact with water, but can still undergo topotactic Li+/H+ exchange (LHX). Here, we combine density functional theory (DFT) calculations with a machine-learning interatomic potential model to investigate the thermodynamic driving force of the LHX reaction for two representative oxide Li-ion conductor families: garnets and NASICONs. Li-stuffed garnets exhibit a strong driving force for proton exchange due to their high Li chemical potential. In contrast, NASICONs demonstrate a higher resistance against proton exchange due to the lower Li chemical potential and the lower O-H bond covalency for polyanion-bonded oxygens. Our findings reveal a critical trade-off: Li stuffing enhances conductivity but increases moisture susceptibility. This study underscores the importance of designing Li-ion conductors that possess both high conductivity and high stability in practical environments.

Self-driving laboratories promise to accelerate materials discovery. Yet current automated solid-state synthesis platforms are limited to ambient conditions, thereby precluding their use for air-sensitive materials. Here, we present A-Lab for Glovebox Powder Solid-state Synthesis (A-Lab GPSS), a robotic platform capable of synthesizing and characterizing air-sensitive inorganic materials under strict air-free conditions. By integrating an agentic AI framework into the A-Lab GPSS platform, we structure autonomous experimental design through abductive and inductive reasoning. We deploy this platform to explore the vast compositional space of lithium halide spinel solid-state ionic conductors. Across a synthesis campaign comprising 352 samples with diverse compositions, the system explores a broad chemical space, experimentally realizing 72

X-ray absorption spectroscopy (XAS) is central to understanding the local electronic and atomic structure of materials, yet most published spectra remain inaccessible to data-driven analysis because they are embedded in figures and described through fragmented textual context in the literature. Here, we use multimodal (image and text) literature mining to transform this dispersed knowledge into an AI-ready experimental data resource. We developed a scalable spectroscopy data digitization pipeline that identifies XAS figures in full-text articles, digitizes spectral curves, and links each spectrum to accompanying metadata on the measured edge and material. Applying this pipeline to the battery literature produced an open dataset of 13,740 XAS spectra, spanning 66 absorbing elements and diverse battery chemistries, with expert validation confirming accurate extraction of spectral and metadata information. By converting literature-embedded spectra into structured numerical data, this dataset provides a foundation for large-scale XAS analysis, cross-laboratory comparison, high-throughput characterization, and autonomous discovery of advanced materials.

ABSTRACT With the increasing demand for Li‐ion batteries, the reliance on nickel (Ni) and cobalt (Co) has become a critical concern given the high cost and scarcity of these resources. The recently discovered Mn‐rich disordered rocksalt (DRX) oxides have demonstrated high energy density and capacity retention, positioning them as promising candidates for low‐cost sustainable energy storage materials. These Mn‐rich DRX materials undergo structural transformation into a partial spinel‐like ordering phase (δ) during electrochemical cycling, thereby enhancing the rate capability and capacity retention. In this work, δ is formed by delithiation and heating, which bypasses the need for long cycling to form δ. In addition, we identify the correlation between the degree of transformation and the delithiation level and heating time.

Disordered rocksalt (DRX) cathodes could enable high-capacity, cobalt- and nickel-free lithium-ion batteries, but their poor electronic conductivity has required high carbon contents and intensive mechanical processing, sacrificing electrode-level energy density. Here we report a solution-based electrostatic self-assembly approach that uniformly decorates polyethylenimine-modified Li1.05Mn0.85Ti0.10O2 particles with multiwalled carbon nanotubes (CNTs). The high-aspect-ratio CNT network provides electrode-level electronic percolation at < 3 wt% total carbon. Electrodes with < 3 wt% CNT match conventional electrodes containing 20 wt% carbon black while increasing the active-material mass fraction up to > 95%. This low-inactive-content architecture delivers ~500 Wh kg−1 electrode-level specific energy, compared with ~370 Wh kg−1 for carbon-rich electrodes, and remains effective at active-material loadings up to ~56 mg cm−2 and areal capacities of ~8.5 mAh cm−2. The high active-material electrode architecture also delivers a high electrode-level energy density of ~2098.8 Wh L-1, which is comparable to the conventional layered oxides. These results establish conductive-network engineering as a practical route to high-loading DRX cathodes.