Our EvoSkill research paper has been accepted to Agent Skills '26 at
@CAISconf, a workshop dedicated to the design, evaluation, and optimization of skills for LLM agents.
Led by
@salahalzubi401 and members of the
@virginia_tech research team, EvoSkill is an open-source toolkit that takes a benchmark and a coding agent, and evolves it into a state-of-the-art specialist in minutes.