Automated molecular structure elucidation remains challenging, as existing approaches often depend on pre-compiled databases or restrict themselves to single spectroscopic modalities. Here we introduce \textbf{SpectraLLM}, a large language model that performs end-to-end structure prediction by reasoning over one or multiple spectra. Unlike conventional spectrum-to-structure pipelines, SpectraLLM represents both continuous (IR, Raman, UV-Vis, NMR) and discrete (MS) modalities in a shared language space, enabling it to capture substructural patterns that are complementary across different spectral types. We pretrain and fine-tune the model on small-molecule domains and evaluate it on four public benchmark datasets. SpectraLLM achieves state-of-the-art performance, substantially surpassing single-modality baselines. Moreover, it demonstrates strong robustness in unimodal settings and further improves prediction accuracy when jointly reasoning over diverse spectra, establishing a scalable paradigm for language-based spectroscopic analysis. Code is available at https://github.com/OPilgrim/SpectraLLM.

翻译：自动化分子结构解析仍具挑战性，现有方法往往依赖预编译数据库或局限于单一光谱模态。本文提出**SpectraLLM**——一种能够通过推理单个或多个光谱执行端到端结构预测的大型语言模型。与传统谱图-结构串联流程不同，SpectraLLM将连续模态（红外、拉曼、紫外-可见、核磁共振）和离散模态（质谱）统一表示为共享语言空间，从而捕捉不同光谱类型中互补的子结构模式。我们在小分子领域对模型进行预训练和微调，并在四个公开基准数据集上评估其性能。SpectraLLM实现了最先进的性能，显著超越了单模态基线模型。此外，它在单模态设置中表现出强鲁棒性，并在联合推理多光谱时进一步提升预测精度，为基于语言的光谱分析建立了可扩展范式。代码已开源：https://github.com/OPilgrim/SpectraLLM