fig2

From prediction to realization: large language models and AI agents for inorganic materials discovery

Figure 2. Closed-loop AI agent architecture for inorganic materials synthesis. An AI orchestrator integrating LLMs, ML models, and physics-based tools connects experimental databases and computational resources to an autonomous laboratory cycle comprising candidate design, robotic synthesis, and characterization, with experimental feedback refining each subsequent cycle. Diagram elements were created with Chemix (https://chemix.org); robot arm icon by Ehtisham Abid (Flaticon), adapted with ChatGPT. AI: Artificial intelligence; LLMs: large language models; ML: machine learning; DFT: density functional theory.

Chemical Synthesis
ISSN 2769-5247 (Online)

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/