SOURCE-LINKED INTELLIGENCE

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Reusable skills give agents transferable procedural knowledge, making scalable acquisition essential for extending agents beyond prior experience. Existing methods face two limitations: trajectory-based synthesis requires interactions with specific environments, while document-derived skills may lack executable evidence and verification. Source code offers a complementary path: it requires no prior agent experience yet provides executable evidence for grounding abstractions. We present Code2Skill, a fully automated pipeline that transforms selected code units into implementation-anchored recor

Read original source ↗ Open in workspace

recordType

paper

region

Global