PeroMAS: A Multi-agent System of Perovskite Material Discovery
🤖 AI Summary
This work addresses the limitations of existing AI approaches in perovskite materials discovery, which predominantly rely on discrete models that fail to propagate physical constraints across the closed-loop pipeline of literature retrieval, data integration, and experimental design, thereby hindering end-to-end optimization. The study introduces, for the first time, a multi-agent architecture for perovskite discovery, leveraging a Model Context Protocol (MCP) to encapsulate domain-specific tools and enable seamless collaboration across the entire workflow—from literature mining and data extraction to performance prediction and mechanistic analysis—while supporting multi-objective constrained material design. By integrating large language model–based planning and tool invocation, the system demonstrates superior efficacy over both standalone LLMs and conventional search strategies, as validated by successful synthesis of top candidates in real-world experiments, and establishes an expert-evaluated benchmark to quantitatively assess system performance.
Application Category
📝 Abstract
As a pioneer of the third-generation photovoltaic revolution, Perovskite Solar Cells (PSCs) are renowned for their superior optoelectronic performance and cost potential. The development process of PSCs is precise and complex, involving a series of closed-loop workflows such as literature retrieval, data integration, experimental design, and synthesis. However, existing AI perovskite approaches focus predominantly on discrete models, including material design, process optimization,and property prediction. These models fail to propagate physical constraints across the workflow, hindering end-to-end optimization. In this paper, we propose a multi-agent system for perovskite material discovery, named PeroMAS. We first encapsulated a series of perovskite-specific tools into Model Context Protocols (MCPs). By planning and invoking these tools, PeroMAS can design perovskite materials under multi-objective constraints, covering the entire process from literature retrieval and data extraction to property prediction and mechanism analysis. Furthermore, we construct an evaluation benchmark by perovskite human experts to assess this multi-agent system. Results demonstrate that, compared to single Large Language Model (LLM) or traditional search strategies, our system significantly enhances discovery efficiency. It successfully identified candidate materials satisfying multi-objective constraints. Notably, we verify PeroMAS's effectiveness in the physical world through real synthesis experiments.
Problem
Research questions and friction points this paper is trying to address.
perovskite material discovery
multi-agent system
end-to-end optimization
physical constraints propagation
multi-objective constraints
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-agent system
perovskite material discovery
Model Context Protocol
end-to-end optimization
AI-driven synthesis
🔎 Similar Papers
No similar papers found.
