SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization 事件

SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization arXiv:2606.06079v1 Announce Type: new Abstract: Agent skills, which consist of reusable strategies that guide agent reasoning and action, have shown strong potential for improving model capability at inference time. However, current skill construction methods treat the problem as one-shot extraction, overlooking a fundamental tension: a skill tailored to the specific task fails to transfer, while the abstracted