Metraipolis › archive › dc_742412e779f5
Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks — arXiv:2609.09233
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09233
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:24:20.927Z
- SHA-256 of the archived text
c78ea4b1ee0b248eaff1a50e253cfa6125fc619b9bd4ab2fa9b16a09157ff18a- Stable URL of this page
https://metraipolis.com/documento/dc_742412e779f5
How to cite
Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks — arXiv:2609.09233 — arXiv (en), https://arxiv.org/abs/2609.09233 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_742412e779f5 (Metraipolis archive dc_742412e779f5, sha256 c78ea4b1ee0b248eaff1a50e253cfa6125fc619b9bd4ab2fa9b16a09157ff18a)
BibTeX
@misc{dc742412e779f5,
title = {Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks — arXiv:2609.09233},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09233},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_742412e779f5; sha256 c78ea4b1ee0b248eaff1a50e253cfa6125fc619b9bd4ab2fa9b16a09157ff18a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09233. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
How can language model agents effectively leverage libraries of reusable knowledge to solve long-horizon tasks? Recent work has increasingly focused on agent skills: reusable capabilities represented as skill packages, i.e., multi-file bundles containing instructions, scripts, and other resources that help agents perform specific tasks. Agent skills are typically executed by loading their skill instructions into an agent's context and relying on the agent to follow them. As task horizons grow, however, this approach becomes increasingly brittle, because reasoning quality degrades as more information accumulates in the context window. We investigate an alternative approach in which skill packages are instead invoked as subagents. Rather than loading skill instructions into the main context, subagent execution spawns fresh context windows dedicated to solving individual subtasks. We show that subagent execution outperforms agent-skill execution when skill packages expose clear input-output contracts and their instructions encode the procedural knowledge needed to fulfill those contracts. The tradeoff is additional communication overhead, as extra tokens are required to coordinate between the main agent and its subagents. Our results show that the benefit of reusable knowledge depends not only on its content, but also on how it is organized and invoked. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.09233 — 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 2026-10-16T07:00:16.174Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).