Metraipolis › archive › dc_e8fda7e28ac3
MultiEvoSkill: Structure-Aware Multi-Agent Skill Evolution for Generalizable Skill Artifacts — arXiv:2610.34260
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34260
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:57:30.222Z
- SHA-256 of the archived text
e2bb5509842860766ef246c3c6aacb21396de765af1ff736c0cdbb6855eea591- Stable URL of this page
https://metraipolis.com/documento/dc_e8fda7e28ac3
How to cite
MultiEvoSkill: Structure-Aware Multi-Agent Skill Evolution for Generalizable Skill Artifacts — arXiv:2610.34260 — arXiv (en), https://arxiv.org/abs/2610.34260 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e8fda7e28ac3 (Metraipolis archive dc_e8fda7e28ac3, sha256 e2bb5509842860766ef246c3c6aacb21396de765af1ff736c0cdbb6855eea591)
BibTeX
@misc{dce8fda7e28ac3,
title = {MultiEvoSkill: Structure-Aware Multi-Agent Skill Evolution for Generalizable Skill Artifacts — arXiv:2610.34260},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34260},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e8fda7e28ac3; sha256 e2bb5509842860766ef246c3c6aacb21396de765af1ff736c0cdbb6855eea591},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34260. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Skill documents are becoming the default adaptation surface for frozen large language model (LLM) agents, but current skill generators face two key limitations. First, humans and different LLMs differ in how they organize procedural knowledge and approach task solving. Skills authored from a human or single-model perspective may therefore fail to align with the reasoning behaviors of other backbones, limiting cross-model generalization. Second, sequential skill descriptions inadequately represent procedures with parallel branches and explicit dependencies, while existing skill optimizers primarily operate on prose and lack explicit support for graph-structured skill evolution. We introduce MultiEvoSkill, a skill-optimization framework comprising three core components: 1) Skill compiler casts the skill as a typed graph with tailored operators, producing a compact, informative representation with explicit procedural topology; 2) Heterogeneous agent system proposes revision advices using collective intelligence, where minimal and informative issues are identified based on multiple sets of experiences. 3) Structure-aware debate and evolution mechanism organizes candidate edits into a heterogeneous graph, resolves them under dependency and importance constraints, and distills the collective proposal into the artifact. Multi-dimensional gating ensures the information gain and topological correctness of each evolution. Optimal skills are then obtained when the system converges at a consistent state. Various experiments and ablations against SOTA methods validate the effectiveness and generalization of MultiEvoSkill. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.34260 — 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 2026-10-27T07:55:30.684Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).