A Literature‐Grounded Scientific Reasoning Framework for Defect‐Engineered TiO ₂ Photocatalysts

Defect‐engineered TiO ₂ photocatalysts are extensively investigated for photocatalytic hydrogen evolution; however, the highly heterogeneous nature of the literature, including inconsistent descriptors, diverse synthesis protocols, nonuniform activity metrics, and incomplete mechanistic reporting, limits the applicability of conventional machine‐learning approaches based solely on statistical regression. Here, we present a literature‐grounded large language model (LLM)‐assisted scientific reasoning framework for defect‐engineered TiO ₂ photocatalysts integrating curated literature data, mechanistic rule extraction, and retrieval‐augmented reasoning. A harmonized database was constructed from experimentally relevant publications specifically selected for hydrogen‐evolution‐related defect engineering in TiO ₂ , covering polymorph‐dependent behavior, hydrogenation conditions, Ti ³⁺ defect states, oxygen vacancies, illumination conditions, and photocatalytic activity descriptors. In parallel, mechanistic evidence sentences and literature‐derived, expert‐defined mechanistic rules were encoded into a structured reasoning layer enabling explainable inference beyond black‐box prediction. The resulting framework combines structured experimental descriptors, semantic literature retrieval, and mechanistic interpretation to generate confidence‐aware recommendations for optimal defect‐engineering conditions. For example, the AI agent identified a literature‐supported anatase hydrogenation activity window centered near ~500 °C under H ₂ ‐containing atmospheres for approximately 1 h, supported by mechanistic evidence linking balanced Ti ³⁺ /oxygen‐vacancy populations with enhanced photocatalytic hydrogen evolution.