paperSeptember 2026Unreviewed

SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale

Dawei Fu, Cheng Jiang, Sitian Qian, Huainan Wang, Zhongkai Hao

Abstract

Modern LLM agents increasingly rely on reusable skills, yet as skill libraries scale to thousands of entries, effective retrieval becomes a bottleneck. Graph-of-Skills (GoS) addresses this challenge by exploiting dependency-aware graph structure for scalable skill retrieval, while SkillDAG further demonstrates that skill graphs can accumulate execution-backed structure online. However, these approaches leave open whether historical execution traces can be systematically distilled into a better r

Cite

@misc{fu2026segos,
  title = {{SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale}},
  author = {Dawei Fu and Cheng Jiang and Sitian Qian and Huainan Wang and Zhongkai Hao},
  year = {2026},
  month = sep,
  eprint = {2609.08228},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.08228}
}