用智能代理强化学习自动解析核磁共振谱，直接从原始数据生成分子结构。
SpecXMaster Technical Report
- 基于智能体强化学习，从原始自由感应衰减数据端到端解析谱图
- 在多个公开基准上表现优异，可自动提取1H和13C谱的多重性信息
- 经化学家迭代优化，适合有机化学研究与自动化药物发现场景
智能光谱分析是人工智能驱动闭环科学发现的关键环节，连接物质结构与人工智能。然而，传统依赖专家的谱图解析存在人为偏见、错误风险高、专业人才稀缺及解释者间差异大等挑战。为此，我们提出SpecXMaster，一种基于智能体强化学习（Agentic RL）的核磁共振（NMR）分子谱图解析框架。该框架可直接从原始自由感应衰减（FID）数据中自动化提取1H和13C谱的多重性信息，实现从谱图到化学结构的全链条自动解析。在多个公开的NMR解析基准上表现卓越，并经过专业化学光谱学家的多轮迭代评估优化。我们认为，SpecXMaster作为谱图解析的新范式，将对有机化学领域产生深远影响。
原文摘要 · Abstract (English)
Intelligent spectroscopy serves as a pivotal element in AI-driven closed-loop scientific discovery, functioning as the critical bridge between matter structure and artificial intelligence. However, conventional expert-dependent spectral interpretation encounters substantial hurdles, including susceptibility to human bias and error, dependence on limited specialized expertise, and variability across interpreters. To address these challenges, we propose SpecXMaster, an intelligent framework leveraging Agentic Reinforcement Learning (RL) for NMR molecular spectral interpretation. SpecXMaster enables automated extraction of multiplicity information from both 1H and 13C spectra directly from raw FID (free induction decay) data. This end-to-end pipeline enables fully automated interpretation of NMR spectra into chemical structures. It demonstrates superior performance across multiple public NMR interpretation benchmarks and has been refined through iterative evaluations by professional chemical spectroscopists. We believe that SpecXMaster, as a novel methodological paradigm for spectral interpretation, will have a profound impact on the organic chemistry community.
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。