Nov 2025· Nature Machine Intelligence· Vol 8, pp. 1087 - 1099· 27 citations· ⚡ 3 influential· 63 references
Computer SciencePhysics
TL;DR
A reinforcement learning framework that guides latent denoising diffusion models in finding diverse and novel, yet thermodynamically viable, crystalline compounds and demonstrates enhanced property-guided design that preserves chemical validity while targeting desired functional properties.
Abstract
Discovering functional crystalline materials entails navigating an immense combinatorial design space. Although recent advances in generative artificial intelligence have enabled the sampling of chemically plausible compositions and structures, a fundamental challenge remains: the objective misalignment between the likelihood-based sampling in generative modelling and the targeted focus on underexplored regions where novel compounds reside. Here we introduce a reinforcement learning framework that guides latent denoising diffusion models in finding diverse and novel, yet thermodynamically viable, crystalline compounds. Our approach integrates group-relative policy optimization with verifiable, multi-objective rewards that jointly balance creativity, stability and diversity. Beyond de novo generation, we demonstrate enhanced property-guided design that preserves chemical validity while targeting desired functional properties. This approach establishes a modular foundation for controllable AI-driven inverse design that addresses the novelty–validity trade-off across the scientific discovery applications of generative models. Park and Walsh introduce a reinforcement learning framework that could accelerate the discovery of new, thermodynamically stable and diverse crystalline materials with desired properties.
A review of physically constrained, multimodal and closed‐loop workflows as the clearest route from generative crystal models to experimentally actionable candidates and defines the inverse‐design problem and main generation tasks.
Tao Li, Xiaolin Liu, Fei Wang et al.· ENERGY & ENVIRONMENTAL M...· 0 citations
Generative artificial intelligence is rapidly transforming materials design by enabling de novo exploration of immense chemical spaces. Yet a large proportion of AI-generated compositions remain implausible, violating established chemical principles, which limits the reliability and interpretability of generative materials design. Here, we introduce a chemical validity operator that recasts heuristic chemical rules as a configurable algorithmic prior for evaluating and guiding generative materials discovery. Built on the open-source SMACT package, a data-informed oxidation-state model exposes tunable thresholds, allowing users to interpolate continuously between permissive and conservative chemical constraints, while supporting both exploratory and conservative materials-design workflows. Benchmarking six state-of-the-art generative models for inorganic crystals shows that most reproduce stoichiometry but under-represent realistic oxidation-state combinations, and that filtering removes compositions reliant on rarely observed oxidation states while preserving low-energy compounds near the convex hull. Beyond screening, the same operator can also serve as a reinforcement-learning reward, steering a latent diffusion model towards chemically grounded compositions. By encoding chemical heuristics and observations, this work establishes a foundation for oxidation-state-aware generative models.
Kinga O. Mastej, Panyalak Detrattanawichai, Hyunsoo Park et al.· 0 citations
Artificial intelligence (AI) is fundamentally transforming materials discovery, shifting the paradigm from labor-intensive trial-and-error approaches to data-driven, automated workflows. This review examines emerging AI methodologies for accelerated materials discovery, with particular emphasis on how computational design, data infrastructure, synthesis planning, and autonomous experimentation can be connected into experimentally grounded workflows. We begin by surveying generative models for inverse materials design, tracing the evolution from early variational autoencoders and generative adversarial networks to recent diffusion models, Bayesian flow networks, flow-based architectures, transformer-based methods, and large language model-driven approaches for the de novo generation of crystalline materials with targeted properties. We then discuss physics-informed and data-efficient AI strategies that incorporate domain knowledge to enhance the model generalizability and robustness in low-data regimes. The emergence of multimodal foundation models, which integrate heterogeneous data modalities including crystal structures, text, and spectroscopic information into unified representations, is examined as a key enabler for cross task generalization. We further review AI-driven synthesis planning algorithms and autonomous self-driving laboratories that bridge the persistent gap between the computational design and experimental realization. Critical infrastructure challenges, including database limitations, FAIR data principles, and knowledge-graph construction, are also addressed. By highlighting both demonstrated capabilities and persistent limitations, this review aims to guide the reliable application of AI toward materials discovery workflows that connect candidate generation, synthesis feasibility, experimental feedback, and data provenance.
Jaehwan Choi, Seongmin Kim, Junkil Park et al.· Chemical Reviews· 0 citations
Closed-loop materials discovery iterates between proposing candidate structures and evaluating their properties, and property evaluation dominates the cost. In the generative variant, a learned prior proposes candidate crystals and a property oracle scores them; we ask whether a cheap probabilistic surrogate can triage the generator's output, and what such a surrogate must do well. Across three architecturally distinct pretrained diffusion priors (MatterGen, CrystalFlow, ADiT) and two targets (room-temperature heat capacity and bulk modulus), we insert a Gaussian process acquisition gate between structure generation and the oracle in an RL-steered generative workflow. The gate matches or exceeds ungated fine-tuning of the generative model while capping oracle calls at a fixed per-cycle budget. Budget-matched ablations isolate the mechanism. At an identical four-call budget, ranking-based selection outperforms arbitrary selection, confirming that the gain comes from the surrogate's choice; the gate comes within $\sim$9\% of exhaustive oracle spending at roughly one-fifth of the calls. A density-functional-theory check of the bulk-modulus discoveries confirms the learned oracle to within 2.5\% on average and the surrogate's ranking of the generated structures at Spearman $\rho = 0.94$. A cross-factorial benchmark of surrogate performance spanning mechanical, electronic, and vibrational properties identifies pretrained ORB embeddings with a Gaussian process as the most reliable combination, which we adopt as the building blocks of the proposed workflow. The complete pipeline is released as open-source software.
Sk Md Ahnaf Akif Alvi, Jan Janssen, Danny Perez et al.· arXiv.org· 0 citations
The Simulation-Calibrated Active Learning Estimator (SCALE), a closed-loop framework uniting high-throughput molecular dynamics, machine learning, and robotic synthesis to bridge the gap between simulation and experiment, is introduced.
Felix Arendt, T. Waurischk, Stefan Reinsch et al.· npj Computational Materials· 0 citations
Artificial intelligence (AI) is accelerating materials prediction and design by enabling efficient exploration of chemical and structural spaces, with particular promise for novel materials discovery. However, novelty in materials discovery encompasses chemical plausibility, structural distinctiveness, property relevance and experimental realisability, making AI-driven novelty claims difficult to substantiate. We introduce a materials property hierarchy, from intrinsic, composition-determined properties to extrinsic, processing-dependent performance, to clarify deployment constraints and distinguish structural, physical and deployment novelty. This framework motivates an evidence-based view of multimodal materials data spanning chemical composition, microstructure, processing, and testing and characterisation, showing that current evidence remains concentrated in composition and idealised structure while heterogeneous, under-represented and weakly integrated modalities limit support for physical and deployment novelty. It also highlights the limitations of benchmarks based mainly on computational labels and proxy novelty criteria. Community-wide standards for data collection, modality alignment and evidence synthesis are needed to support multimodal data construction, process-aware multimodal modelling, feasibility-first generative modelling and deployment-aware benchmarking, so that generative and multimodal AI can design experimentally realisable materials with defensible scientific and practical novelty.
Xianyuan Liu, Charles Anjah, Benjamin E. Jolly et al.· Journal of Physics Materials· 0 citations