PATS treats agent skills as disposable training scaffolding, gaining 18.6% while cutting 32.1% of prompt tokens

arXiv·medium signal

Policy-Aware Training Scaffolding, submitted July 23, converts rollout groups from the latest policy into evidence cards and adjusts agent context per task, removing guidance as the agent improves while preserving beneficial trajectory variation. Critically, the scaffold is discarded at deployment — the skills exist to shape training, not to ship. Reported gains reach 18.6% over strong baselines on ALFWorld and WebShop, with competitive results on search-augmented QA at 32.1% fewer prompt tokens. This inverts the prevailing skills-marketplace assumption that curated skill files should live in the production prompt.