DREAMS：端到端计算材料发现的 LLM 智能体系统

An LLM agent for end-to-end computational materials discovery

AI 导读

研究团队提出基于大语言模型的智能体系统 DREAMS，可执行金属有机框架（MOF）的完整筛选流程。该系统处理大量 MOF 文献、将论文与晶体结构关联并整理为可计算数据库，再用逐步更昂贵的模拟进行筛选。在湿烟气分离条件下识别出的候选材料均来自独立研究，使非专家也能以端到端自动化方式发现高性能材料。

正文 · 原文

View PDF

Abstract:Coordinating multi-scale tasks is an effective strategy for computational materials discovery, yet the diverse algorithms and tools involved make this process highly challenging. Here we present DREAMS, a large language model (LLM)-based agent system capable of executing the entire screening pipeline for metal-organic frameworks (MOFs). DREAMS processes a large body of MOF literature, links publications to their crystal structures, and curates them into a computation-ready database, which is then screened with progressively more expensive simulations. The promising candidates identified for separation under wet flue gas conditions all originate from independent studies. By bridging the heterogeneous stages from literature mining to high-throughput simulation, DREAMS operates across application domains and enables even non-experts to discover high-performance materials in an end-to-end, automated manner.

Subjects:	Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2608.20434 [cond-mat.mtrl-sci]
	(or arXiv:2608.20434v2 [cond-mat.mtrl-sci] for this version)
	https://doi.org/10.48550/arXiv.2608.20434 arXiv-issued DOI via DataCite

Submission history

From: Guobin Zhao [view email]
[v1] Thu, 20 Aug 2026 06:23:09 UTC (4,930 KB)
[v2] Fri, 23 Oct 2026 10:37:02 UTC (11,279 KB)

来源：arXiv cs.AI · arxiv.org