AI & ML New Capability

Trace2Skill distills lessons from across a 'parallel fleet' of execution trajectories into a unified, conflict-free skill directory for LLM agents.

March 27, 2026

Original Paper

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

Jingwei Ni, Yihao Liu, Xinpeng Liu, Yutao Sun, Mengyu Zhou, Pengyu Cheng, Dexin Wang, Xiaoxi Jiang, Guanjun Jiang

arXiv · 2603.25158

The Takeaway

Current agent skill learning often overfits to specific trajectories. This framework allows agents to autonomously build and 'deepen' their own library of reusable skills that generalize to out-of-distribution tasks and transfer across model scales.

From the abstract

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 introduce Trace2Skill, a framework that mirrors how human experts author skills: by holistica