MedSkill: Skill Learning for BioMedical Tool-Use Agents

Large language models are increasingly used as agents in healthcare related tasks. The heterogeneity of such biomedical tasks usually requires adapting a separate policy to each task. However, there is often similarity between procedures used across tasks, motivating mechanisms that can learn repeatable useful skills. We propose MedSkill a training-free skill-learning framework that learns a shared bank of natural-language procedures together and composes them to solve new tasks. Skills are optimized for reuse across a distribution of tasks, while the controller learns task- and state-dependent composition, enabling specialization without training a separate end-to-end model per task. We instantiate the framework on Athena-style healthcare evaluations, including biomedical knowledge, and clinical decision tasks, and compare skill-composed policies with direct deployment of the underlying language models.