Metraipolis › archive › dc_371cc9dbc628

SkillSandbox: Skill Verification via Dynamic Scenario Synthesis — arXiv:2610.10088

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10088
License (as archived)
CC0-1.0
Archived
2026-10-08T11:09:47.538Z
SHA-256 of the archived text
4ddd11bd4f4e2661cdd1fca6c07aea2520db43a9bd2b7607336ce0cb2006b80a
Stable URL of this page
https://metraipolis.com/documento/dc_371cc9dbc628

How to cite

SkillSandbox: Skill Verification via Dynamic Scenario Synthesis — arXiv:2610.10088 — arXiv (en), https://arxiv.org/abs/2610.10088 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_371cc9dbc628 (Metraipolis archive dc_371cc9dbc628, sha256 4ddd11bd4f4e2661cdd1fca6c07aea2520db43a9bd2b7607336ce0cb2006b80a)
BibTeX
@misc{dc371cc9dbc628,
  title = {SkillSandbox: Skill Verification via Dynamic Scenario Synthesis — arXiv:2610.10088},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10088},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_371cc9dbc628; sha256 4ddd11bd4f4e2661cdd1fca6c07aea2520db43a9bd2b7607336ce0cb2006b80a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10088. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-evolving agents distill task-solving experience into skills for future reuse, but these skills can encode incorrect procedures or non-transferable knowledge. It is therefore critical to verify each skill's reusability: whether its guidance remains useful beyond the experience from which it was distilled. Such verification requires observing how a skill affects execution in new tasks, yet existing tasks may not expose the situations where the target skill can actually be exercised. To construct such situations, we propose SkillSandbox, a framework that dynamically synthesizes a task and its environment for each skill that are skill-relevant yet novel. A Proposer specifies the conditions to preserve and the source-specific details to vary, a Builder constructs an executable scenario, and a Verifier compares executions with and without the skill. The Verifier assesses executability, utility, and efficiency to assign a Keep or Reject verdict, determining whether the skill enters the library. Across ALFWorld and WebShop with three models, SkillSandbox consistently yields the strongest downstream performance and improved execution efficiency. Further analyses examine whether these gains reflect accurate assessment of skill reusability and identify which components of SkillSandbox contribute to them.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.10088 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T10:14:05.974Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).