Metraipolis › archive › dc_756c24229bec
Co-Skill: A Collaborative Communication Framework for Skill Evolution — arXiv:2609.16008
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16008
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T19:29:33.604Z
- SHA-256 of the archived text
f9d7fba6f67214ffe6d05d4405e0c2eeae3a3cfc4d2dfd588b4c67f0712972c2- Stable URL of this page
https://metraipolis.com/documento/dc_756c24229bec
How to cite
Co-Skill: A Collaborative Communication Framework for Skill Evolution — arXiv:2609.16008 — arXiv (en), https://arxiv.org/abs/2609.16008 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_756c24229bec (Metraipolis archive dc_756c24229bec, sha256 f9d7fba6f67214ffe6d05d4405e0c2eeae3a3cfc4d2dfd588b4c67f0712972c2)
BibTeX
@misc{dc756c24229bec,
title = {Co-Skill: A Collaborative Communication Framework for Skill Evolution — arXiv:2609.16008},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16008},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_756c24229bec; sha256 f9d7fba6f67214ffe6d05d4405e0c2eeae3a3cfc4d2dfd588b4c67f0712972c2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16008. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agent evolution through skills becomes critical for LLM-based agents to iteratively improve task success rate. Hybrid evolution is a cost-efficient paradigm where a cloud LLM analyzes and generates skills while an edge SLM executes and internalizes them. However, existing hybrid methods, such as SkillRL, still suffer from low success rate and high token usage. We find this stems from blind communication: the cloud cannot perceive the edge's execution capability, while the edge does not understand the cloud's analysis needs. We thus propose the Collaborative Communication Framework (CCF) to achieve effective edge-cloud evolution. CCF is realized via three techniques: (1) a cloud-aware prefix-merged trajectory trie where the edge compresses trajectories by merging shared prefixes and pinpointing divergence points for efficient cloud analysis, (2) an edge-aware progressive skill tree where the cloud progressively builds a hierarchical skill tree to match edge SLM execution capability, and (3) a collaborative skill evolution scheme upon these two trees that evolves cloud LLM and edge SLM in a separated way to jointly improve task success rate. Experiments across ALFWorld and WebShop show that CCF reduces LLM+SLM tokens by 15.6%--41.9% over state-of-the-art hybrid methods while consistently improving 25.8%--76.4% task success rate. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-16 in cs.DC). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2609.16008 — 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 2026-10-15T18:35:05.413Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).