AI RESEARCH
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
arXiv CS.AI
•
ArXi:2603.25158v1 Announce Type: new Equipping Large Language Model (LLM) agents with domain-specific skills is critical for tackling complex tasks. Yet, manual authoring creates a severe scalability bottleneck. Conversely, automated skill generation often yields fragile or fragmented results because it either relies on shallow parametric knowledge or sequentially overfits to non-generalizable trajectory-local lessons. To overcome this, we