# Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning

arXiv: https://arxiv.org/abs/2506.23056 · HTML: https://mlsanity.com/paper/2506.23056/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 1 of its 46 references that are in the map.
- First posted on arXiv 29 Jun 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 1 of 1)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)

## Built on by (most cited first, 2 of 2)

- [MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation](https://mlsanity.com/paper/2610.12067/) (2026)
- [How well can off-the-shelf LLMs elucidate molecular structures from mass spectra using chain-of-thought reasoning?](https://mlsanity.com/paper/2601.06289/) (2026)

## Abstract (arXiv)

Molecular structure elucidation involves deducing a molecule's structure from various types of spectral data, which is crucial in chemical experimental analysis. While large language models (LLMs) have shown remarkable proficiency in analyzing and reasoning through complex tasks, they still encounter substantial challenges in molecular structure elucidation. We identify that these challenges largely stem from LLMs' limited grasp of specialized chemical knowledge. In this work, we introduce a Knowledge-enhanced reasoning framework for Molecular Structure Elucidation (K-MSE), leveraging Monte Carlo Tree Search for test-time scaling as a plugin. Specifically, we construct an external molecular substructure knowledge base to extend the LLMs' coverage of the chemical structure space. Furthermore, we design a specialized molecule-spectrum scorer to act as a reward model for the reasoning process, addressing the issue of inaccurate solution evaluation in LLMs. Experimental results show that our approach significantly boosts performance, particularly gaining more than 20% improvement on both GPT-4o-mini and GPT-4o. Our code is available at https://github.com/HICAI-ZJU/K-MSE.