TopoMAS: Large Language Model Driven Topological Materials Multiagent System

2025-07-05

AI Summary

Topological material design across multiple length scales is hindered by inefficient conventional workflows. This work proposes a large language model (LLM)-driven multi-agent system that establishes a human–machine collaborative closed-loop framework—“Requirement–Design–Validation”—integrating first-principles calculations, dynamically self-evolving knowledge graphs, and multi-source data reasoning. The framework enables end-to-end automation of topological material discovery, spanning theoretical derivation, crystal structure generation, and novel phase identification. The paradigm is transferable and scalable, validated across multiple foundation models: lightweight models achieve 94.55% accuracy, exhibit 100× faster response times, and significantly reduce computational resource consumption. Critically, it successfully guided the discovery of a new intrinsic topological insulator, SrSbO₃. This work establishes a generalizable, intelligent paradigm for accelerated topological materials design.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Inefficient discovery workflows in topological materials design
• Lack of seamless human-AI collaboration in materials discovery
• Need for continuous knowledge refinement in materials science

Innovation

• Interactive human-AI framework for materials discovery
• Autonomous knowledge graph for continuous refinement
• Lightweight LLM model with high efficiency