# S3C-LLM: Skill-Code Guided Agentic Language Models for Spectrum-to-Structure Elucidation

arXiv: https://arxiv.org/abs/2608.30910 · HTML: https://mlsanity.com/paper/2608.30910/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 50 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 20 of 20)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification](https://mlsanity.com/paper/2604.01687/) (2026)
- [SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources](https://mlsanity.com/paper/2604.03964/) (2026)
- [MassSpecGym: A benchmark for the discovery and identification of molecules](https://mlsanity.com/paper/2410.23326/) (2024)
- [DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra](https://mlsanity.com/paper/2502.09571/) (2025)
- [Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry](https://mlsanity.com/paper/2407.17492/) (2024)
- [Rapid Prediction of Electron-Ionization Mass Spectrometry using Neural Networks](https://mlsanity.com/paper/1811.08545/) (2018)
- [Accurate and efficient structure elucidation from routine one-dimensional NMR spectra using multitask machine learning](https://mlsanity.com/paper/2408.08284/) (2024)
- [Competitive Fragmentation Modeling of ESI-MS/MS spectra for putative metabolite identification](https://mlsanity.com/paper/1312.0264/) (2013)
- [TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks](https://mlsanity.com/paper/2511.06283/) (2025)
- [IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra](https://mlsanity.com/paper/2508.16112/) (2025)
- [SpectraLLM: Uncovering the Ability of LLMs for Molecular Structure Elucidation from Multi-Spectral Data](https://mlsanity.com/paper/2508.08441/) (2025)
- [ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding](https://mlsanity.com/paper/2604.06685/) (2026)
- [LUMIR: an LLM-Driven Unified Agent Framework for Multi-task Infrared Spectroscopy Reasoning](https://mlsanity.com/paper/2507.21471/) (2025)
- [SpecMol: A Spectroscopy-Grounded Foundation Model for Multi-Task Molecular Learning](https://mlsanity.com/paper/2509.21861/) (2025)
- [NMRTrans: Structure Elucidation from Experimental NMR Spectra via Set Transformers](https://mlsanity.com/paper/2602.10158/) (2026)

## Abstract (arXiv)

Spectroscopic structure elucidation is central to molecular analysis, but recent Large Language Model (LLM)-based methods mostly formulate it as direct spectrum-to-SMILES generation. Although this paradigm can leverage paired spectral data, it does not explicitly model the analytical workflow used by spectroscopists, such as diagnostic peak interpretation, fragment reasoning, formula constraints, and chemical consistency checking. In this paper, we introduce S3C-LLM, a skill-guided and code-grounded agentic LLM for spectrum-to-structure elucidation. Rather than directly predicting a molecule, S3C-LLM retrieves modality-specific spectroscopy skills, executes analysis code to instantiate these skills on the input spectra, and integrates the resulting peak-level evidence and formula constraints before generating SMILES. Specifically, we contribute a self-evolving spectroscopy skill library, a thinking-augmented skill-code trajectory construction pipeline, and a two-stage training strategy that teaches Qwen3-4B through supervised fine-tuning (SFT) followed by our proposed step-level reinforcement learning (RL). Experiments on diverse benchmarks show that S3C-LLM consistently outperforms current general LLMs and spectrum-specific models across spectra, while using less than 1/10th of SpectraLLM's training corpus.