Metraipolis › archive › dc_d5e97b5dfbf1

SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams — arXiv:2609.02217

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02217
License (as archived)
CC0-1.0
Archived
2026-10-17T03:26:12.000Z
SHA-256 of the archived text
9c906e6b4c52979595579388608ed26e3297293ed3138f87255f408d66eecbe5
Stable URL of this page
https://metraipolis.com/documento/dc_d5e97b5dfbf1

How to cite

SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams — arXiv:2609.02217 — arXiv (en), https://arxiv.org/abs/2609.02217 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d5e97b5dfbf1 (Metraipolis archive dc_d5e97b5dfbf1, sha256 9c906e6b4c52979595579388608ed26e3297293ed3138f87255f408d66eecbe5)
BibTeX
@misc{dcd5e97b5dfbf1,
  title = {SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams — arXiv:2609.02217},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02217},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d5e97b5dfbf1; sha256 9c906e6b4c52979595579388608ed26e3297293ed3138f87255f408d66eecbe5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02217. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents increasingly self-improve by writing and reusing textual skills, kept either as one global document or as a flat pool of per-task entries, though most of the evidence comes from domains with structurally similar tasks. On long-horizon workloads where each task demands a different solution, the two forms fail in opposite ways: the document collapses into generic discipline, while the pool inflates and its entries stay bound to the instance that wrote them. We argue the missing unit of reuse is the solving procedure shared by a cluster of related tasks, and build SkillGLoW (Global-Local Weave) around it: the local skills a task writes from its own execution are aggregated into procedural families and compressed into de-instantiated global priors, while the instance detail they hold is regenerated per task rather than stored; a commit gate admits a prior only when real execution shows it does not degrade the deployed library. Across four benchmarks (mathematical reasoning, terminal automation, software repair, and embodied control) and three models, the priors gain 17.2 points (hard) over the no-skill baseline on average, with positive gains in all 12 continual-improvement runs, and 18.0 with local regeneration, while the library holds one prior per procedural family, 3.6x more compact than the per-task pool. Under the same protocol GLoW leads a published single-document optimizer on 15 of 21 cells. Unmodified, the library lifts success on unseen ALFWorld tasks from 73.9% to 83.9%, evidence that what transfers is procedure rather than task memory.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.02217 — 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 2026-10-17T03:13:12.430Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).