PriM: Principle-Inspired Material Discovery through Multi-Agent Collaboration
Submission Track: Full Paper
Submission Category: AI-Guided Design + Automated Synthesis
Keywords: physicochemical principles, multi-agent systems, material discovery
TL;DR: Automated, language-based AI guided by physicochemical principles for efficient and transparent materials discovery, shown in nanohelix optimization. Code on GitHub.
Abstract: 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 \texttt{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}.
Submission Number: 72
Loading