TopoMAS: Large Language Model Driven Topological Materials Multiagent System

TL;DR

TopoMAS is an interactive AI framework that streamlines the discovery of topological materials by integrating large language models, data retrieval, theoretical inference, and validation into a continuous, self-improving pipeline, leading to novel material identification.

Contribution

It introduces a novel multi-agent system that combines human expertise with AI-driven data processing and knowledge graph updates for efficient topological materials discovery.

Findings

Successfully identified a new topological phase SrSbO3.

Achieved 94.55% accuracy with lightweight LLM, outperforming larger models in efficiency.

Demonstrated robustness and speed across multiple benchmarks.

Abstract

Topological materials occupy a frontier in condensed-matter physics thanks to their remarkable electronic and quantum properties, yet their cross-scale design remains bottlenecked by inefficient discovery workflows. Here, we introduce TopoMAS (Topological materials Multi-Agent System), an interactive human-AI framework that seamlessly orchestrates the entire materials-discovery pipeline: from user-defined queries and multi-source data retrieval, through theoretical inference and crystal-structure generation, to first-principles validation. Crucially, TopoMAS closes the loop by autonomously integrating computational outcomes into a dynamic knowledge graph, enabling continuous knowledge refinement. In collaboration with human experts, it has already guided the identification of novel topological phases SrSbO3, confirmed by first-principles calculations. Comprehensive benchmarks demonstrate robust adaptability across base Large Language Model, with the lightweight Qwen2.5-72B model achieving 94.55% accuracy while consuming only 74.3-78.4% of tokens required by Qwen3-235B and 83.0% of DeepSeek-V3's usage--delivering responses twice as fast as Qwen3-235B. This efficiency establishes TopoMAS as an accelerator for computation-driven discovery pipelines. By harmonizing rational agent orchestration with a self-evolving knowledge graph, our framework not only delivers immediate advances in topological materials but also establishes a transferable, extensible paradigm for materials-science domain.