用智能体搜索取代模型建模，实现媲美研究生的核磁解析
NMR Elucidation as an Agentic Search Problem, Not a Modeling Problem
- 构建基于大模型的自主智能体，通过逐步推理与工具调用解析核磁数据
- 在Alberts数据集上准确率达71%，接近研究生水平（66%）
- 适合化学、材料、生物领域科研人员，推动自动化谱学分析
从核磁共振（NMR）数据进行结构解析仍是化学、材料科学和生物学中的核心瓶颈。我们证明，一个自主的智能体系统可达到与研究生相当的解析水平。不同于直接训练模型将谱图映射到结构，我们构建了一个由冻结的大语言模型驱动的单一智能体，它在包含领域专用处理工具、化学位移表、验证检查和分步思维指令的受控环境中运行。在Alberts数据集上，该智能体的结构解析顶1准确率为71%，接近研究生水平（66%）。在van Bramer和AstraZeneca数据集上分别达到80%和20%的顶1准确率，优于零样本端到端深度学习模型。结果表明，将NMR解析重新定义为大模型引导的约束搜索，而非建模任务，能带来显著提升，并为集成多种工具、模型和领域知识的多步协同框架提供路径。
原文摘要 · Abstract (English)
Structural elucidation from Nuclear Magnetic Resonance (NMR) data remains a fundamental bottleneck across chemistry, materials science, and biology. We demonstrate that an agentic AI system can perform this task at a level comparable to graduate-level chemistry students. Instead of training a model to directly map spectra to structures, we build a single autonomous agent, backed by a frozen LLM, that interacts with a curated environment with access to domain-specific processing tools, validation checks, tabulated chemical shifts, and instructions that outline the stepwise nature of a chemist's thinking process. On the Alberts dataset, our agent elucidates structures with a top-1 accuracy of 71%, comparable to the performance of graduate students at 66% top-1 accuracy. On the van Bramer and AstraZeneca datasets, our agent achieved 80% and 20% top-1 accuracy respectively, outperforming zero-shot end-to-end deep learning models which were trained on large datasets of simulated spectra. These results show that reframing NMR elucidation as an LLM-guided constrained search, rather than a modeling task, yields substantial gains and suggests a path toward multi-step orchestration frameworks that integrate a variety of tools, models, and domain knowledge to assist in automating spectroscopic analysis.
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。