RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
Paper • 2606.29538 • Published • 146
Skill
-
-
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
Paper • 2608.02287 • Published • 32 -
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
Paper • 2608.05139 • Published • 28 -
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
Paper • 2608.11079 • Published • 17 -
Self-Evolving Embodied Agents via Skill-Harness Evolution
Paper • 2608.11350 • Published • 15 -
Demystifying Agent Skills: Why They Work-Until They Don't
Paper • 2608.14036 • Published • 170 -
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Paper • 2608.27454 • Published • 33 -
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Paper • 2609.02749 • Published • 554 -
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
Paper • 2609.11682 • Published • 38