摘要：基于核磁共振（Nuclear Magnetic Resonance，NMR）数据进行结构解析，仍然是化学、材料科学和生物学领域的一个根本性瓶颈。我们证明，一个智能体式 AI 系统能够以可与研究生阶段化学学生相比的水平完成这一任务。我们并非训练模型将谱图直接映射为结构，而是构建了一个由冻结 LLM 支持的单一自主 Agent；该 Agent 可与经过策展的环境交互，并可访问领域专用处理工具、验证检查、表格化学位移数据，以及概述化学家分步思考过程的指令。在 Alberts 数据集上，我们的 Agent 实现了 71% 的 top-1 准确率，与研究生学生 66% 的 top-1 准确率相当。在 van Bramer 和 AstraZeneca 数据集上，我们的 Agent 分别取得了 80% 和 20% 的 top-1 准确率，优于在大规模模拟谱图数据集上训练的零样本端到端深度学习模型。这些结果表明，将 NMR 结构解析重新定义为由 LLM 引导的约束搜索，而非建模任务，可带来显著提升；同时也为构建多步骤编排框架提供了路径，这类框架能够整合各类工具、模型和领域知识，以协助实现光谱分析自动化。

Abstract: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.