发表机构
Department of Materials, Imperial College London（帝国理工学院材料系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对AI生成材料成分不合理问题，引入化学有效性算子，基于SMACT包构建氧化态模型，通过可调阈值支持不同工作流程。经基准测试，该算子能过滤不合理成分，还可作强化学习奖励，为氧化态感知生成模型奠定基础。
AI 中文摘要
生成式人工智能正在迅速改变材料设计，通过对巨大化学空间进行从头探索。然而，很大一部分人工智能生成的成分仍然不合理，违反了既定的化学原理，这限制了生成式材料设计的可靠性和可解释性。在此，我们引入了一种化学有效性算子，将启发式化学规则重新塑造为一种可配置的算法先验，用于评估和指导生成式材料发现。基于开源SMACT包构建的一个数据驱动的氧化态模型揭示了可调阈值，允许用户在宽松和保守的化学约束之间连续插值，同时支持探索性和保守性材料设计工作流程。对六种无机晶体的最新生成模型进行基准测试表明，大多数模型能重现化学计量，但实际氧化态组合的代表性不足，过滤可去除依赖罕见氧化态的成分，同时保留凸包附近的低能化合物。除了筛选，同一个算子还可以作为强化学习奖励，引导潜在扩散模型生成基于化学的成分。通过编码化学启发式和观察结果，这项工作为氧化态感知生成模型奠定了基础。
英文摘要
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.
Comments19 pages, 7 figures, 3 tables, including Supplementary Information
