NMR Elucidation as an Agentic Search Problem, Not a Modeling Problem

• URL: http://arxiv.org/abs/2607.19406v1
• Date: Tue, 07 Jul 2026 22:05:25 GMT
• Title: NMR Elucidation as an Agentic Search Problem, Not a Modeling Problem
• Abstract summary: Structural elucidation from Nuclear Magnetic Resonance data remains a fundamental bottleneck across chemistry, materials science, and biology.<n>We demonstrate that an agentic AI system can perform this task at a level comparable to graduate-level chemistry students.<n>Our agent elucidates structures with a top-1 accuracy of 71%, comparable to the performance of graduate students at 66% top-1 accuracy.
• Score: 3.8929079574413508
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities [103.60384544335072]
  Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence.<n>Our framework aligns problem-solving agentic behaviors with a structured taxonomy of reusable mathematical atomic capabilities.<n> Experiments reveal that models with similar end-to-end accuracy can exhibit markedly different agentic capability profiles.
  arXiv  Detail & Related papers  (2026-08-27T10:52:06Z)
• DASyR-LLM: Domain-Aware Symbolic Regression with LLMs for Kinetic Model Discovery [0.0]
  Large language models (LLMs) offer a promising avenue for injecting domain expertise into kinetic model discovery.<n>Our framework is evaluated on four in silico case studies of increasing complexity, spanning heterogeneous and bioprocess systems.<n>Results show the LLM-guided framework reduces iterations to identify the ground-truth model by $41.7-79.3%$ versus a state-of-the-art SR framework.
  arXiv  Detail & Related papers  (2026-08-05T17:48:45Z)
• An Agentic Framework for Autonomous Materials Computation [70.24472585135929]
  Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery.<n>Recent advances integrate LLMs into agentic frameworks, enabling retrieval, reasoning, and tool use for complex scientific experiments.<n>Here, we present a domain-specialized agent designed for reliable automation of first-principles materials computations.
  arXiv  Detail & Related papers  (2025-12-22T15:03:57Z)
• ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions [52.79349601462865]
  ChemOrch is a framework that synthesizes chemically grounded instruction-response pairs.<n>ChemOrch enables controllable diversity and levels of difficulty for the generated tasks.
  arXiv  Detail & Related papers  (2025-09-20T05:43:58Z)
• A Multi-Agent System Enables Versatile Information Extraction from the Chemical Literature [8.306442315850878]
  We develop a multimodal large language model (MLLM)-based multi-agent system for robust and automated chemical information extraction.<n>Our system achieved an F1 score of 80.8% on a benchmark dataset of sophisticated multimodal chemical reaction graphics from the literature.
  arXiv  Detail & Related papers  (2025-07-27T11:16:57Z)
• ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data [53.78763789036172]
  We present ChemActor, a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences.<n>This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input.<n>Experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor achieves state-of-the-art performance, outperforming the baseline model by 10%.
  arXiv  Detail & Related papers  (2025-06-30T05:11:19Z)
• CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning [12.745398618084474]
  Large language models (LLMs) have recently demonstrated promising capabilities in chemistry tasks.<n>We propose an LLM-based agent that integrates 137 external chemical tools created ranging from basic information retrieval to complex reaction predictions.
  arXiv  Detail & Related papers  (2025-06-09T08:41:39Z)
• DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery [54.79763887844838]
  Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution.<n>We introduce DrugPilot, a LLM-based agent system with a parameterized reasoning architecture designed for end-to-end scientific in drug discovery.<n>DrugPilot significantly outperforms state-of-the-art agents such as ReAct and LoT, achieving task completion rates of 98.0%, 93.5%, and 64.0% for simple, multi-tool, and multi-turn scenarios, respectively.
  arXiv  Detail & Related papers  (2025-05-20T05:18:15Z)
• Artificial Intelligence in Spectroscopy: Advancing Chemistry from Prediction to Generation and Beyond [38.32974480709081]
  The rapid advent of machine learning (ML) and artificial intelligence (AI) has catalyzed major transformations in chemistry.<n>The application of these methods to spectroscopic and spectrometric data, referred to as Spectroscopy Machine Learning (SpectraML), remains relatively underexplored.<n>We provide a unified review of SpectraML, systematically examining state-of-the-art approaches for both forward tasks and inverse tasks.
  arXiv  Detail & Related papers  (2025-02-14T04:07:25Z)
• How Well Can Modern LLMs Act as Agent Cores in Radiology Environments? [54.36730060680139]
  RadA-BenchPlat is an evaluation platform that benchmarks the performance of large language models (LLMs) in radiology environments.<n>The platform also defines ten categories of tools for agent-driven task solving and evaluates seven leading LLMs.
  arXiv  Detail & Related papers  (2024-12-12T18:20:16Z)
• Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning [71.2981957820888]
  We propose a novel Star-Agents framework, which automates the enhancement of data quality across datasets. The framework initially generates diverse instruction data with multiple LLM agents through a bespoke sampling method. The generated data undergo a rigorous evaluation using a dual-model method that assesses both difficulty and quality.
  arXiv  Detail & Related papers  (2024-11-21T02:30:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.