用大模型统一解决材料合成的原料选与步骤设计问题。
MSP-LLM: A Unified Large Language Model Framework for Complete Material Synthesis Planning
- 将合成规划拆解为原料预测与操作预测，中间用材料类别串联。
- 在合成操作预测中引入分级原料类型作为先验知识，提升准确性。
- 适合材料研发人员快速生成可执行的合成方案。
材料合成规划（MSP）是人工智能驱动材料发现中的关键瓶颈，不仅需识别合适的前驱物，还需设计连贯的合成步骤序列以实现目标材料。尽管已有多种AI方法针对部分子任务，但尚未建立统一解决完整MSP任务的方法。本文提出MSP-LLM，一种基于大语言模型的统一框架，将MSP建模为包含原料预测（PP）与合成操作预测（SOP）两个子任务的结构化过程。该方法引入离散材料类别作为中间决策变量，构建化学一致的决策链。针对SOP，进一步融合层级前驱物类型作为合成相关的归纳偏置，并采用显式条件策略，在自回归解码中保留前驱物信息。大量实验表明，MSP-LLM在PP、SOP及完整MSP任务上均显著优于现有方法，验证了其在材料发现中高效且可扩展的潜力。
原文摘要 · Abstract (English)
Material synthesis planning (MSP) remains a fundamental and underexplored bottleneck in AI-driven materials discovery, as it requires not only identifying suitable precursor materials but also designing coherent sequences of synthesis operations to realize a target material. Although several AI-based approaches have been proposed to address isolated subtasks of MSP, a unified methodology for solving the entire MSP task has yet to be established. We propose MSP-LLM, a unified LLM-based framework that formulates MSP as a structured process composed of two constituent subproblems: precursor prediction (PP) and synthesis operation prediction (SOP). Our approach introduces a discrete material class as an intermediate decision variable that organizes both tasks into a chemically consistent decision chain. For SOP, we further incorporate hierarchical precursor types as synthesis-relevant inductive biases and employ an explicit conditioning strategy that preserves precursor-related information in the autoregressive decoding state. Extensive experiments show that MSP-LLM consistently outperforms existing methods on both PP and SOP, as well as on the complete MSP task, demonstrating an effective and scalable framework for MSP that can accelerate real-world materials discovery.
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。