Consolidating per-task skills into one prior per procedural family beat the no-skill baseline by 17 points and shrank the library 3.6x

arXiv 2609.02217·high signalXBlueskyLinkedInCopy link

SkillGLoW (arXiv 2609.02217, 2026-09-02) attacks the two failure shapes of agent skill storage: a single global document collapses into generic advice, while a flat per-task pool inflates and stays welded to the instance that wrote it. Its unit of reuse is the solving procedure shared by a cluster of related tasks, so local skills get aggregated into procedural families, compressed into de-instantiated global priors, and admitted only when real execution shows they don't degrade the deployed library. Across mathematical reasoning, terminal automation, software repair, and embodied control on three models, priors gained 17.2 points on hard tasks with positive gains in all 12 continual-improvement runs, held one prior per family (3.6x more compact than a per-task pool), and lifted unseen ALFWorld success from 73.9% to 83.9%.