Automating alloy design and discovery with physics-aware multimodal multiagent AI

Proceedings of the National Academy of Sciences, Journal Year: 2025, Volume and Issue: 122(4)

Published: Jan. 24, 2025

The design of new alloys is a multiscale problem that requires holistic approach involves retrieving relevant knowledge, applying advanced computational methods, conducting experimental validations, and analyzing the results, process typically slow reserved for human experts. Machine learning can help accelerate this process, instance, through use deep surrogate models connect structural chemical features to material properties, or vice versa. However, existing data-driven often target specific objectives, offering limited flexibility integrate out-of-domain knowledge cannot adapt new, unforeseen challenges. Here, we overcome these limitations by leveraging distinct capabilities multiple AI agents collaborate autonomously within dynamic environment solve complex materials tasks. proposed physics-aware generative platform, AtomAgents, synergizes intelligence large language (LLMs) collaboration among with expertise in various domains, including retrieval, multimodal data integration, physics-based simulations, comprehensive results analysis across modalities. concerted effort multiagent system allows addressing problems, as demonstrated examples include designing metallic enhanced properties compared their pure counterparts. Our enable accurate prediction key characteristics highlight crucial role solid solution alloying steer development alloys. framework enhances efficiency multiobjective tasks opens avenues fields such biomedical engineering, renewable energy, environmental sustainability.

Language: Английский

Molecular analysis and design using multimodal generative artificial intelligence via multi-agent modeling

Published: April 16, 2024

We report the use of a multimodal generative artificial intelligence framework, X-LoRA-Gemma large language model (LLM), to analyze, design and test molecular design. The model, inspired by biological principles featuring ~7 billion parameters, dynamically reconfigures its structure through dual-pass inference strategy enhance problem-solving abilities across diverse scientific domains. is used first identify engineering targets systematic human-AI AI-AI self-driving multi-agent approach elucidate key for optimization improve interactions between molecules. Next, process that includes rational steps, reasoning autonomous knowledge extraction. Target properties molecule are identified either using Principal Component Analysis (PCA) or sampling from distribution known properties. then generate set candidate molecules, which analyzed via their structure, charge distribution, other features. validate as predicted, increased dipole moment polarizability indeed achieved in designed anticipate an increasing integration these techniques into workflow, ultimately enabling development innovative solutions address wide range societal challenges. conclude with critical discussion challenges opportunities AI engineering, analysis

Language: Английский