Turning clinical guidelines into executable skill functions, refined with labeled cases, improves LLM diagnostic accuracy across four benchmarks and four backbones.
JMIR Formative Research , volume=
1 Pith paper cite this work, alongside 5 external citations. Polarity classification is still indexing.
1
Pith paper citing it
5
external citations · OpenAlex
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GuideSkill: Evolving Executable LLM Agent Skills for Guideline-Grounded Clinical Reasoning
Turning clinical guidelines into executable skill functions, refined with labeled cases, improves LLM diagnostic accuracy across four benchmarks and four backbones.