paperarXivTrust 82 · PrimaryPublished 4d agoLive · 3d ago
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).
Has model
Implements
Related to
Covers
Implements (incoming)
Covers (incoming)
Related across the graph
repoactiveloopai/hivemindarticleA field guide to AI agents in 2026modelAgentCore-8BnewsHow Preply combines AI and human tutors to personalize learningnewsLearning Structured Reasoning via Tractable Trajectory Control - Apple Machine Learning Researchreporoxblnfk/skillsnewsNew benchmark exposes reasoning gaps in top modelsrepoagent-tools
