18 August 2026

Research shows AI agents improve mainly through procedural anchoring

• Researchers measured how AI agents gain capability. Procedural anchoring, which grounds agents in specific step-by-step processes, accounted for 65.7% of improvements versus 4.5% from adding factual knowledge.
• A new dataset called GitSkills extracted 3.8 million skill definitions from open-source repositories, enabling researchers to study how agents learn practical tasks at scale.
• The findings suggest agent development should focus on teaching systematic procedures rather than just feeding agents more facts.

How it was covered

Latent Spaceswyx & Alessio

Research quantifies that agent skills help primarily through procedural anchoring (65.7%) rather than factual knowledge injection (4.5%), with emerging ecosystems around discoverability via GitSkills dataset mining 3.8M SKILL.md files showing maturing skill library management.