Parametric Skills
Since intelligence fundamentally relies on efficient skill acquisition (Chollet, 2019), the ability to leverage skills is critical. For LLMs, skills, manually authored or extracted from task trajectories, are textual recipes encoding mature problem-solving experience and are critical to agentic capabilities. Despite widespread deployment, their utility is limited by the model's ability to comprehend and follow skill instructions, especially under complex and long-context scenarios, where key instructions are difficult to locate and adhere to. To address this limitation, we propose ParametricSk
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownAgentCore-8B →
- LinkedLinked via unknownagent-tools →
- LinkedLinked via unknownA field guide to AI agents in 2026 →
- LinkedLinked via unknownNew benchmark exposes reasoning gaps in top models →
- LinkedLinked via unknownHow Preply combines AI and human tutors to personalize learning →
- PossiblePossibly related (embedding) · 53%activeloopai/hivemind →
- PossiblePossibly related (embedding) · 52%Learning Structured Reasoning via Tractable Trajectory Control - Apple Machine Learning Research →
- PossiblePossibly related (embedding) · 47%roxblnfk/skills →
