From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914592920174592 |
|---|---|
| author | Huang, Zisu Xu, Jingwen Yang, Yifan Gong, Ziyang Yang, Qihao Tian, Muzhao Wang, Xiaohua Lv, Changze Gao, Xuemei Dai, Qi Liu, Bei Qiu, Kai Yang, Xue Chen, Dongdong Zheng, Xiaoqing Luo, Chong |
| author_facet | Huang, Zisu Xu, Jingwen Yang, Yifan Gong, Ziyang Yang, Qihao Tian, Muzhao Wang, Xiaohua Lv, Changze Gao, Xuemei Dai, Qi Liu, Bei Qiu, Kai Yang, Xue Chen, Dongdong Zheng, Xiaoqing Luo, Chong |
| contents | Language agents increasingly improve by reusing \emph{skills} -- structured procedural artifacts distilled from past experience. In particular, \emph{domain-level} and \emph{model-generated} skills are especially promising. They offer fast adaptation within a domain by encoding domain-specific recurring procedures, and they scale beyond labor-intensive hand-crafting. However, while extraction methods continue to proliferate, understanding remains limited, with no comprehensive study spanning the full skill lifecycle -- \textbf{experience generation}, \textbf{skill extraction}, and \textbf{skill consumption} -- to ask whether such skills actually work, when they work, and what makes them succeed or fail. To close this gap, we build a utility-grounded evaluation framework that provides systematic experimental results across extractors and target agents, covering five diverse agentic task domains. We find that model-generated skills are beneficial on average but exhibit non-trivial negative transfer, and that neither extractors nor targets behave uniformly. A model can be a strong extractor yet a weak consumer, or vice versa, with skill utility independent of model scale or baseline task strength. To explain these patterns, we then dissect each lifecycle stage in depth, analyzing how experience composition shapes skill quality, what properties characterize useful skills, and how the same skill transfers across different consumers. Finally, we translate these findings into a concrete \emph{meta-skill} that guides skill extraction toward the features tied to actual utility, which consistently improves skill quality across domains and substantially reduces negative transfer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_23899 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills Huang, Zisu Xu, Jingwen Yang, Yifan Gong, Ziyang Yang, Qihao Tian, Muzhao Wang, Xiaohua Lv, Changze Gao, Xuemei Dai, Qi Liu, Bei Qiu, Kai Yang, Xue Chen, Dongdong Zheng, Xiaoqing Luo, Chong Artificial Intelligence Language agents increasingly improve by reusing \emph{skills} -- structured procedural artifacts distilled from past experience. In particular, \emph{domain-level} and \emph{model-generated} skills are especially promising. They offer fast adaptation within a domain by encoding domain-specific recurring procedures, and they scale beyond labor-intensive hand-crafting. However, while extraction methods continue to proliferate, understanding remains limited, with no comprehensive study spanning the full skill lifecycle -- \textbf{experience generation}, \textbf{skill extraction}, and \textbf{skill consumption} -- to ask whether such skills actually work, when they work, and what makes them succeed or fail. To close this gap, we build a utility-grounded evaluation framework that provides systematic experimental results across extractors and target agents, covering five diverse agentic task domains. We find that model-generated skills are beneficial on average but exhibit non-trivial negative transfer, and that neither extractors nor targets behave uniformly. A model can be a strong extractor yet a weak consumer, or vice versa, with skill utility independent of model scale or baseline task strength. To explain these patterns, we then dissect each lifecycle stage in depth, analyzing how experience composition shapes skill quality, what properties characterize useful skills, and how the same skill transfers across different consumers. Finally, we translate these findings into a concrete \emph{meta-skill} that guides skill extraction toward the features tied to actual utility, which consistently improves skill quality across domains and substantially reduces negative transfer. |
| title | From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.23899 |