dorsal/arxiv
View SchemaEnhancing Spatial Reasoning in Large Language Models for Metal-Organic Frameworks Structure Prediction
| Authors | Mianzhi Pan, JianFei Li, Peishuo Liu, Botian Wang, Yawen Ouyang, Yiming Rong, Hao Zhou, Jianbing Zhang |
|---|---|
| Categories | |
| ArXiv ID | 2601.09285vv1 |
| URL | https://arxiv.org/abs/2601.09285 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
Metal-organic frameworks (MOFs) are porous crystalline materials with broad applications such as carbon capture and drug delivery, yet accurately predicting their 3D structures remains a significant challenge. While Large Language Models (LLMs) have shown promise in generating crystals, their application to MOFs is hindered by MOFs' high atomic complexity. Inspired by the success of block-wise paradigms in deep generative models, we pioneer the use of LLMs in this domain by introducing MOF-LLM, the first LLM framework specifically adapted for block-level MOF structure prediction. To effectively harness LLMs for this modular assembly task, our training paradigm integrates spatial-aware continual pre-training (CPT), structural supervised fine-tuning (SFT), and matching-driven reinforcement learning (RL). By incorporating explicit spatial priors and optimizing structural stability via Soft Adaptive Policy Optimization (SAPO), our approach substantially enhances the spatial reasoning capability of a Qwen-3 8B model for accurate MOF structure prediction. Comprehensive experiments demonstrate that MOF-LLM outperforms state-of-the-art denoising-based and LLM-based methods while exhibiting superior sampling efficiency.
{
"annotation_id": "72761ad6-0699-460a-8205-e57548c0f426",
"date_created": "2026-02-17T05:53:20.458000Z",
"date_modified": "2026-02-17T05:53:20.458000Z",
"file_hash": "74b363149bed2bb30e3350950777297de3ed41711faddf59aa5bba4f24e48dc5",
"private": false,
"record": {
"abstract": "Metal-organic frameworks (MOFs) are porous crystalline materials with broad applications such as carbon capture and drug delivery, yet accurately predicting their 3D structures remains a significant challenge. While Large Language Models (LLMs) have shown promise in generating crystals, their application to MOFs is hindered by MOFs\u0027 high atomic complexity. Inspired by the success of block-wise paradigms in deep generative models, we pioneer the use of LLMs in this domain by introducing MOF-LLM, the first LLM framework specifically adapted for block-level MOF structure prediction. To effectively harness LLMs for this modular assembly task, our training paradigm integrates spatial-aware continual pre-training (CPT), structural supervised fine-tuning (SFT), and matching-driven reinforcement learning (RL). By incorporating explicit spatial priors and optimizing structural stability via Soft Adaptive Policy Optimization (SAPO), our approach substantially enhances the spatial reasoning capability of a Qwen-3 8B model for accurate MOF structure prediction. Comprehensive experiments demonstrate that MOF-LLM outperforms state-of-the-art denoising-based and LLM-based methods while exhibiting superior sampling efficiency.",
"arxiv_id": "2601.09285",
"authors": [
"Mianzhi Pan",
"JianFei Li",
"Peishuo Liu",
"Botian Wang",
"Yawen Ouyang",
"Yiming Rong",
"Hao Zhou",
"Jianbing Zhang"
],
"categories": [
"cs.LG",
"cond-mat.mtrl-sci"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "Enhancing Spatial Reasoning in Large Language Models for Metal-Organic Frameworks Structure Prediction",
"url": "https://arxiv.org/abs/2601.09285",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "6c19601e-3d40-4794-a649-2c129b0909ca",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}