Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a phenomenon-first framework for materials discovery using LLMs, where separate descriptions of guest physics, host capabilities, and operating context are provided to generate qualitative behaviors with mechanisms, signatures, and falsifiers. Across 80 guest-host combinations in metal-organic frameworks, the LLM proposed 57 unique qualitative behaviors, with nine computationally tractable candidates identified, including reproducible hydration-driven reorientation of retained ethanol and a quantum-corrected reversal of H$_2$ adsorption-region preference. This structured LLM reasoning demonstrates a shift from objective execution to prospective formulation of materials phenomena.
LLMs can prospectively formulate novel materials phenomena, moving beyond executing predefined objectives to independently identifying unique guest-host interactions and their underlying mechanisms.
Here we introduce a phenomenon-first framework for materials discovery in which an LLM receives separate descriptions of guest physics, host capabilities and operating context and proposes an unusual qualitative behavior with its mechanism, distinguishing signature and falsifier. Across 80 guest-host combinations in metal-organic frameworks, the model generated 57 proposals that were frozen before evaluation or materials selection; assessment identified nine computationally tractable candidates. In a repeat and guest-only baseline, structured formulation reproducibly broadened mechanistic exploration: the original and repeat runs each covered 21 broad mechanism families versus eight for guest-only formulation despite fewer proposals. From the original run, MC-010 yielded reproducible hydration-driven reorientation of retained ethanol in experimentally reported MOFs, while MC-015 yielded a quantum-corrected reversal of H$_2$ adsorption-region preference relative to the matched classical description. These results show how structured LLM reasoning can move upstream from executing supplied objectives toward prospectively formulating qualitative materials phenomena.