用多智能体大模型自主推理，减少90%模拟次数发现新材料
Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Functional Materials Discovery
- 构建多层级智能体系统，自动生成并优化密度泛函理论流程
- 在两种催化剂研究中，模拟次数减少最高达90%
- 适合需要高效材料探索的科研人员和自动化研发团队
人工智能正在重塑科学探索，但多数方法仅能自动化流程任务，缺乏科学推理能力，限制了发现的自主性。我们提出Materials Agents for Simulation and Theory in Electronic-structure Reasoning（MASTER），一个主动学习框架，使大语言模型能够自主设计、执行并解释原子级模拟。在MASTER中，多模态系统将自然语言转化为密度泛函理论工作流，高层推理智能体通过分层策略引导发现，包括单智能体基线及三种多智能体方法：同行评审、优先排序与分类筛选。在铜表面过渡金属吸附以及金属-氮-碳催化剂两个化学应用中，基于推理的探索相比随机选择，最多可减少90%的原子级模拟需求。推理路径揭示了具有化学依据的决策过程，无法由随机采样或语义偏差解释。总体而言，多智能体协作显著加速材料发现，标志着自主科学探索的新范式。
原文摘要 · Abstract (English)
Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We introduce Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), an active learning framework where large language models autonomously design, execute, and interpret atomistic simulations. In MASTER, a multimodal system translates natural language into density functional theory workflows, while higher-level reasoning agents guide discovery through a hierarchy of strategies, including a single agent baseline and three multi-agent approaches: peer review, triage-ranking, and triage-forms. Across two chemical applications, CO adsorption on Cu-surface transition metal (M) adatoms and on M-N-C catalysts, reasoning-driven exploration reduces required atomistic simulations by up to 90% relative to trial-and-error selection. Reasoning trajectories reveal chemically grounded decisions that cannot be explained by stochastic sampling or semantic bias. Altogether, multi-agent collaboration accelerates materials discovery and marks a new paradigm for autonomous scientific exploration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。