Metraipolis › archive › dc_062ef93e60ee
SkillDuet: Co-Evolving Models and Skills through Response Feedback — arXiv:2611.12109
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12109
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:43.786Z
- SHA-256 of the archived text
e3b1b825cbcb3a74815460df593aa844a187c12dffd8b185397ed289484e5960- Stable URL of this page
https://metraipolis.com/documento/dc_062ef93e60ee
How to cite
SkillDuet: Co-Evolving Models and Skills through Response Feedback — arXiv:2611.12109 — arXiv (en), https://arxiv.org/abs/2611.12109 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_062ef93e60ee (Metraipolis archive dc_062ef93e60ee, sha256 e3b1b825cbcb3a74815460df593aa844a187c12dffd8b185397ed289484e5960)
BibTeX
@misc{dc062ef93e60ee,
title = {SkillDuet: Co-Evolving Models and Skills through Response Feedback — arXiv:2611.12109},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12109},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_062ef93e60ee; sha256 e3b1b825cbcb3a74815460df593aa844a187c12dffd8b185397ed289484e5960},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12109. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
During reinforcement learning, experience can be both internalized in LLM parameters and retained externally as reusable textual skills. Parameter updates alter the model's behavior and the interaction experience from which new skills are extracted. These skills, in turn, guide the model's subsequent interactions and parameter updates. As the model's capabilities evolve, previously beneficial skills may become redundant or detrimental. We present SkillDuet, a framework that coordinates parameter updates and skill evolution through model response feedback. Skills extracted from on-policy trajectories guide parameter updates through OPD at every step. A response-based score, Strength, ranks candidate skills by the magnitude of the shift they induce in the current model's responses, and the highest-scoring skills are periodically consolidated into a persistent global skill set (Global). The updated model and Global jointly guide subsequent interactions, generating experience for further parameter and skill updates. With Qwen3-4B, SkillDuet achieves success rates of 98.57% on ALFWorld and 92.97% on WebShop, exceeding the matched SEED-API baseline by 2.86 and 5.47 percentage points, respectively. Ablations show that response-based skill selection and Global consolidation improve task performance. Further experiments show that the benefits of retained skills depend on both their content and their compatibility with the model. SkillDuet provides a concrete mechanism for model-skill co-evolution and skill-level recursive self-improvement. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.12109 — 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 2026-11-10T18:37:37.535Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).