---
title: "LLMs Depend on Specialist Tools for Out-of-Distribution Generalization in MS/MS Structural Elucidation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.03308v1"
permalink: "https://feed.astralor.com/items/itm_5cf9428bc30ac025950ee68f"
published: "2026-11-02T15:39:07.000Z"
score: 57
channel: "tech"
tags: ["LLM","AI Agent","LLMs Depend","Specialist Tools","Out-of-Distribution Generalization","Structural Elucidation","NMR","MassSpecGym"]
---

# LLMs Depend on Specialist Tools for Out-of-Distribution Generalization in MS/MS Structural Elucidation

## At a glance

A frontier language model was recently reported to solve 1D NMR structural elucidation without tools. We ask whether this capability transfers to tandem mass spectrometry (MS/MS) in the de novo setting, where the model …

## Key points

- A frontier language model was recently reported to solve 1D NMR structural elucidation without tools.
- We ask whether this capability transfers to tandem mass spectrometry (MS/MS) in the de novo setting, where the model must propose a structure directly from the spectrum without a candidate list or reference library.
- To separate reasoning from recall, we build a 100-analyte benchmark from MassSpecGym, split by each analyte's textual footprint into in-distribution (well documented in literature) and out-of-distribution (essentially u…

## Full text

A frontier language model was recently reported to solve 1D NMR structural elucidation without tools. We ask whether this capability transfers to tandem mass spectrometry (MS/MS) in the de novo setting, where the model must propose a structure directly from the spectrum without a candidate list or reference library. To separate reasoning from recall, we build a 100-analyte benchmark from MassSpecGym, split by each analyte's textual footprint into in-distribution (well documented in literature) and out-of-distribution (essentially undocumented) arms. We hold the model, harness, and output format fixed and vary only the LLM's access to domain-specific tools. Without tools, a frontier LLM reaches 52% Top-1 accuracy in-distribution but only 2% out-of-distribution. Only access to de novo structure generators improves out-of-distribution accuracy, raising it to as much as 38% Top-1, and the resulting agent outperforms the standalone de novo models both in and out of distribution. These results suggest that LLMs are not effective at de novo MS/MS structural elucidation on their own, and that further gains depend on the specialist tools available to the agent rather than on the LLM itself.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_5cf9428bc30ac025950ee68f