NMR Elucidation as an Agentic Search Problem, Not a Modeling Problem
For chemists and materials scientists, this work demonstrates that agentic AI can automate NMR analysis at a level comparable to human experts, offering a practical alternative to training large models on simulated data.
The paper reframes NMR structural elucidation as an LLM-guided search problem rather than a modeling task, achieving top-1 accuracies of 71% (Alberts), 80% (van Bramer), and 20% (AstraZeneca), outperforming graduate students (66%) and zero-shot deep learning models.
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.