PriM: Principle-Inspired Material Discovery through Multi-Agent Collaboration
This work addresses the problem of interpretability and efficiency in materials discovery for scientists, presenting a novel automated paradigm with potential broad impact.
The authors tackled the challenge of inefficient and opaque automated materials discovery by introducing PriM, a principles-guided multi-agent system that integrates hypothesis generation with experimental validation, achieving higher exploration rates and property values in a nano helix case study.
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}.