Phenomenon-first problem formulation with language models in metal-organic frameworks
Abstract
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 H2 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.
Related
- Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agents
- Chiroptical Nonlinearity Found in Covalent Organic Frameworks
- Ultrasound-Assisted Facile Nanoconfinement of Luminescent Guests in Zirconium Metal-Organic Frameworks
- Molecular Curvature Enables Tubular π-Stacked Pathways in Three-Dimensional Conductive Metal-Organic Frameworks
- Designing Geared Molecular Rotors in Flexible Metal-Organic Frameworks
BibTeX
@misc{kim2026phenomenonfirst,
title = {{Phenomenon-first problem formulation with language models in metal-organic frameworks}},
author = {Jihan Kim},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.04866},
eprint = {2610.04866},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.04866},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Phenomenon-first problem formulation with language models in metal-organic frameworks
AU - Jihan Kim
PY - 2026
DA - 2026/10/04
PB - arXiv
DO - 10.48550/arxiv.2610.04866
UR - https://arxiv.org/abs/2610.04866
AB - 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.
ER -