2026-07-31 04:00 UTCOriginal source2 min readUpdated: 2026-07-31 08:34 UTC

GuideSkill: Evolving Executable LLM Agent Skills for Guideline-Grounded Clinical Reasoning

GuideSkill is an external reasoning layer that compiles clinical practice guideline criteria into executable functions returning ordinal diagnostic-support scores. GuideSkill-Zero is initialized from guidelines, while GuideSkill-Evo refines skills using case-diagnosis pairs. Across four benchmarks and four backbones, GuideSkill-Evo achieves the highest macro-average accuracy for every backbone, improves over direct inference by 18.49% relatively, and increases gold-label skill coverage from 56.5% to 99.5%, without updating the backbone.

SourcearXiv AIAuthor: Lang Cao, Yuhao Shen, Tianyang Luo, Simo Du, Hao Peng, Yue Guo

Article intelligence

EngineersAdvanced

Key points

GuideSkill compiles guideline rules into executable functions, enabling LLMs to execute rather than just retrieve clinical guidance.
GuideSkill-Zero is initialized from guidelines; GuideSkill-Evo refines skills and adds missing diagnoses using case-diagnosis pairs.
Across four benchmarks and four backbones, GuideSkill-Evo achieves the highest macro-average accuracy for every backbone, with a relative 18.49% improvement over direct inference.
On Qwen3.5-9B, GuideSkill-Evo beats the strongest parameter-update baseline by 11.16% without updating the backbone, raising gold-label skill coverage from 56.5% to 99.5%.

Why it matters

This matters because guideSkill compiles guideline rules into executable functions, enabling LLMs to execute rather than just retrieve clinical guidance.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

This panel is AI-generated and reviewed for accuracy.

-->

[Submitted on 28 Jul 2026]

Title:GuideSkill: Evolving Executable LLM Agent Skills for Guideline-Grounded Clinical Reasoning

View a PDF of the paper titled GuideSkill: Evolving Executable LLM Agent Skills for Guideline-Grounded Clinical Reasoning, by Lang Cao and 5 other authors

View PDF HTML (experimental)

Abstract:Clinical practice guidelines (CPGs) encode diagnostic criteria, but LLM systems typically retrieve guideline text or absorb it through training rather than execute its rules. We introduce GuideSkill, an external reasoning layer that compiles disease-specific criteria into executable functions returning ordinal diagnostic-support scores. GuideSkill-Zero is initialized from guidelines, while GuideSkill-Evo uses case--diagnosis pairs to refine covered skills and add missing diagnoses. At inference, an LLM proposes a differential diagnosis, grounds the features required by each matched skill, and fuses its ranking with the executed skill scores. Across four benchmarks and four backbones, GuideSkill-Zero improves macro-average accuracy over guideline RAG by 13.45% on average. GuideSkill-Evo achieves the highest macro-average for every backbone, improves over direct inference by 18.49% relatively, and increases gold-label skill coverage from 56.5% to 99.5%. On Qwen3.5-9B, it also exceeds the strongest parameter-update baseline by 11.16% without updating the backbone. Expert evaluation further indicates that GuideSkill produces clinically sound and broadly acceptable skills, suggesting that its initialized and evolved rules are reliable and practically meaningful. These results support executable skills as a model-agnostic mechanism for combining guideline-derived procedures with case-derived diagnostic patterns.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2607.26160 [cs.AI]

(or arXiv:2607.26160v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.26160

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Lang Cao [view email] [v1] Tue, 28 Jul 2026 18:10:33 UTC (636 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled GuideSkill: Evolving Executable LLM Agent Skills for Guideline-Grounded Clinical Reasoning, by Lang Cao and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-07

Change to browse by:

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)