PriM: Principle-Inspired Material Discovery through Multi-Agent Collaboration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lai, Zheyuan, Pu, Yingming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910909550559232
author Lai, Zheyuan
Pu, Yingming
author_facet Lai, Zheyuan
Pu, Yingming
contents Complex chemical space and limited knowledge scope with biases holds immense challenge for human scientists, yet in automated materials discovery. Existing intelligent methods relies more on numerical computation, leading to inefficient exploration and results with hard-interpretability. To bridge this gap, we introduce a principles-guided material discovery system powered by language inferential multi-agent system (MAS), namely PriM. Our framework integrates automated hypothesis generation with experimental validation in a roundtable system of MAS, enabling systematic exploration while maintaining scientific rigor. Based on our framework, the case study of nano helix demonstrates higher materials exploration rate and property value while providing transparent reasoning pathways. This approach develops an automated-and-transparent paradigm for material discovery, with broad implications for rational design of functional materials. Code is publicly available at our \href{https://github.com/amair-lab/PriM}{GitHub}.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08810
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PriM: Principle-Inspired Material Discovery through Multi-Agent Collaboration
Lai, Zheyuan
Pu, Yingming
Machine Learning
Materials Science
Artificial Intelligence
Complex chemical space and limited knowledge scope with biases holds immense challenge for human scientists, yet in automated materials discovery. Existing intelligent methods relies more on numerical computation, leading to inefficient exploration and results with hard-interpretability. To bridge this gap, we introduce a principles-guided material discovery system powered by language inferential multi-agent system (MAS), namely PriM. Our framework integrates automated hypothesis generation with experimental validation in a roundtable system of MAS, enabling systematic exploration while maintaining scientific rigor. Based on our framework, the case study of nano helix demonstrates higher materials exploration rate and property value while providing transparent reasoning pathways. This approach develops an automated-and-transparent paradigm for material discovery, with broad implications for rational design of functional materials. Code is publicly available at our \href{https://github.com/amair-lab/PriM}{GitHub}.
title PriM: Principle-Inspired Material Discovery through Multi-Agent Collaboration
topic Machine Learning
Materials Science
Artificial Intelligence
url https://arxiv.org/abs/2504.08810