Metraipolis › archive › dc_41018fe788be

SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback — arXiv:2608.13120

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13120
License (as archived)
CC0-1.0
Archived
2026-10-19T04:17:33.261Z
SHA-256 of the archived text
c53e2a542f4b27f982eac8cc0a5bee1e631393cf6459e610e33b2e7ebea4d691
Stable URL of this page
https://metraipolis.com/documento/dc_41018fe788be

How to cite

SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback — arXiv:2608.13120 — arXiv (en), https://arxiv.org/abs/2608.13120 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_41018fe788be (Metraipolis archive dc_41018fe788be, sha256 c53e2a542f4b27f982eac8cc0a5bee1e631393cf6459e610e33b2e7ebea4d691)
BibTeX
@misc{dc41018fe788be,
  title = {SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback — arXiv:2608.13120},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13120},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_41018fe788be; sha256 c53e2a542f4b27f982eac8cc0a5bee1e631393cf6459e610e33b2e7ebea4d691},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13120. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no closed loop through which they might improve from the interaction failures they actually cause. Recent work does close this loop, but derives its feedback from single-turn question-answering evaluation. The consequence is a sharp asymmetry: once the first round has patched the gaps that a single exchange can reveal, the evolution gradient decays, the defects that surface only across multiple turns remain invisible, and evolution stalls. Governance in these systems is likewise driven by an end-to-end verification score, a scalar gate that can reject a degraded candidate but can neither localize nor repair its structural cause. We argue that the binding constraint on sustained skill evolution is neither editing capability nor the number of iterations, but whether the evaluation feedback keeps supplying trustworthy evolution gradients. We introduce SkillEvo, in which trustworthy feedback generates the gradient and controllable governance constrains its direction. The first component recasts multi-turn user simulation from an evaluation endpoint into a feedback generator: follow-up questions expose defects layer by layer, so that every round of revision both consumes feedback and produces new feedback. The second replaces the passive rejection of a scalar gate with an independent governance layer that actively repairs factual degradation and structural bloat, preventing the gradient from drifting as degradation accumulates. Across six categories of cloud services, 9 production Skills, and 98 skill-reference files, SkillEvo surpasses self-reflection-based evolution by 23.0 points and single- turn-QA-driven evolution by 15.4 points.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.13120 — 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 2026-10-19T04:13:06.584Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).