{"ID":2898142,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.04053","arxiv_id":"2507.04053","title":"TopoMAS: Large Language Model Driven Topological Materials Multiagent System","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.","short_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...","url_abs":"https://arxiv.org/abs/2507.04053","url_pdf":"https://arxiv.org/pdf/2507.04053v1","authors":"[\"Baohua Zhang\",\"Xin Li\",\"Huangchao Xu\",\"Zhong Jin\",\"Quansheng Wu\",\"Ce Li\"]","published":"2025-07-05T14:23:12Z","proceeding":"cond-mat.mtrl-sci","tasks":"[\"cond-mat.mtrl-sci\",\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false}