arXiv cs.AI
· Papers
GuideSkill: Evolving Executable LLM Agent Skills for Guideline-Grounded Clinical Reasoning
arXiv:2607.26160v1 Announce Type: new 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