analiza aiqbench
S3C-LLM introduces a novel agentic framework that shifts spectrum-to-structure elucidation from direct generation to a workflow modeled on human analytical reasoning, integrating diagnostic skills and code execution. By combining supervised fine-tuning with step-level reinforcement learning, the model achieves superior performance on diverse benchmarks while requiring significantly less training data than existing spectrum-specific models. This approach represents a meaningful advancement in applying agentic LLMs to specialized scientific domains where explicit reasoning steps are critical for accuracy.
S3C-LLM: Skill-Code Guided Agentic Language Models for Spectrum-to-Structure Elucidation
arXiv:2608.30910v1 Announce Type: cross Abstract: 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.
Abstract: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.
Machine Learning (cs.LG); Computation and Language (cs.CL)
arXiv:2608.30910 [cs.LG]
(or arXiv:2608.30910v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.30910 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 261 cuvinte
Subiecte conexe
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · 12 iun. 2026
Mastering Agentic Techniques: AI Agent Customization
NVIDIA · 20 mai 2026
The Local AI Stack for Productive SLMs
KDnuggets · 28 aug. 2026