Large language models for porous materials: from text mining to autonomous laboratory

Abstract

Porous materials such as metal–organic frameworks (MOFs), covalent organic frameworks (COFs), zeolites, and porous carbons play central roles in gas storage, separation, catalysis, and environmental technologies. However, their design and discovery remain resource-intensive, relying heavily on expert intuition and fragmented knowledge distributed across the literature. Recent advances in large language models (LLMs) present new opportunities to accelerate these workflows by integrating scientific text mining, domain reasoning, and experimental planning. In this review, we outline the emerging role of LLMs across the porous materials research ecosystem. We first introduce the foundations of LLMs, followed by a discussion of NLP-based text mining for literature analysis. We then examine LLM adaptation including prompt engineering and fine-tuning, and autonomous research systems from human-in-the-loop to self-driving laboratories. For each domain, we summarize how LLM architectures are integrated with research systems, highlighting their applications, advantages, and limitations. Additionally, we discuss the current challenges of applying LLMs to porous materials, trade-offs between prompt engineering and fine-tuning, the influence of generation parameters such as temperature, and safety considerations in autonomous laboratory systems. Finally, we expect LLMs to advance toward multimodal reasoning, tighter integration with structured knowledge bases, and safer autonomous experimental workflows. Together, these developments suggest emerging LLM-driven paradigms that could transform the conceptualization, design, and synthesis of porous materials.