Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914542637809664 |
|---|---|
| author | Zeng, Kun Huo, Yu Zhang, Siyu Ye, Zi Zhuo, Yuecheng Liu, Haoyue Lu, Yuquan Wen, Junhao Tang, Xiaoying |
| author_facet | Zeng, Kun Huo, Yu Zhang, Siyu Ye, Zi Zhuo, Yuecheng Liu, Haoyue Lu, Yuquan Wen, Junhao Tang, Xiaoying |
| contents | Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable context. Existing methods typically return atomic skills or dependency-aware bundles whose internal roles remain implicit, leaving the agent to infer the execution entry point, support skills, visible requirements, and failure-avoidance guidance. We introduce Group of Skills (GoSkills), an inference-time group-structured retrieval method that changes the agent-facing retrieval object from a flat skill list to a compact, role-labeled execution context. GoSkills builds anchor-centered skill groups from a typed skill graph, expands support groups through a group graph, bottlenecks the selected group plan into a bounded set of atomic skill payloads, and renders a fixed execution contract with Start, Support, Check, and Avoid fields, without changing the downstream agent, skill payloads, or execution environment. Experiments on SkillsBench and ALFWorld show that GoSkills preserves visible-requirement coverage under a small skill budget, improves over flat skill-access baselines, and often improves reward and agent-only runtime relative to structural retrieval references. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06978 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries Zeng, Kun Huo, Yu Zhang, Siyu Ye, Zi Zhuo, Yuecheng Liu, Haoyue Lu, Yuquan Wen, Junhao Tang, Xiaoying Computation and Language Artificial Intelligence Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable context. Existing methods typically return atomic skills or dependency-aware bundles whose internal roles remain implicit, leaving the agent to infer the execution entry point, support skills, visible requirements, and failure-avoidance guidance. We introduce Group of Skills (GoSkills), an inference-time group-structured retrieval method that changes the agent-facing retrieval object from a flat skill list to a compact, role-labeled execution context. GoSkills builds anchor-centered skill groups from a typed skill graph, expands support groups through a group graph, bottlenecks the selected group plan into a bounded set of atomic skill payloads, and renders a fixed execution contract with Start, Support, Check, and Avoid fields, without changing the downstream agent, skill payloads, or execution environment. Experiments on SkillsBench and ALFWorld show that GoSkills preserves visible-requirement coverage under a small skill budget, improves over flat skill-access baselines, and often improves reward and agent-only runtime relative to structural retrieval references. |
| title | Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.06978 |