Metraipolis › archive › dc_5f5e6689efbc
Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation — arXiv:2609.38024
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38024
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:24:26.260Z
- SHA-256 of the archived text
511cdb659f8f3f97b8c644044e12315f630e5804180e90bc612093c66a4679af- Stable URL of this page
https://metraipolis.com/documento/dc_5f5e6689efbc
How to cite
Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation — arXiv:2609.38024 — arXiv (en), https://arxiv.org/abs/2609.38024 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5f5e6689efbc (Metraipolis archive dc_5f5e6689efbc, sha256 511cdb659f8f3f97b8c644044e12315f630e5804180e90bc612093c66a4679af)
BibTeX
@misc{dc5f5e6689efbc,
title = {Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation — arXiv:2609.38024},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38024},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5f5e6689efbc; sha256 511cdb659f8f3f97b8c644044e12315f630e5804180e90bc612093c66a4679af},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38024. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness. Recent studies have explored the optimization of agent skills, contributing to a growing collection of publicly available skills spanning diverse tasks, domains, and harnesses. Despite millions of publicly shared skills, existing skill optimization methods largely overlook this accumulated knowledge, instead relying solely on expensive agent rollouts to iteratively refine skills for a target task. To address this, we propose \textbf{Retrieval-Augmented Skill Optimization (RASO)}, a framework that leverages an external skill corpus as prior knowledge throughout skill optimization. RASO retrieves relevant knowledge from existing skills and adapts it to the target task and harness via Cross-Harness Adaptation, accounting for mismatches in both domain and harness. RASO comprises two complementary stages: \textbf{Retrieval-Augmented Skill Initialization (RASI)} constructs a knowledge-grounded initial skill without requiring agent rollouts, while \textbf{Retrieval-Augmented Skill Update (RASU)} iteratively refines the skill by retrieving external knowledge guided by execution feedback. Across four agent benchmarks and two models, extensive experiments show that RASO consistently outperforms baselines without retrieval-augmented skill initialization and updating.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38024 — 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 2026-10-07T15:54:53.684Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).