Metraipolis › archive › dc_aefd3fe240e8

Omni-IO Skills: Harnessing Your Agent Omni-Native — arXiv:2609.31847

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31847
License (as archived)
CC0-1.0
Archived
2026-10-07T21:49:54.419Z
SHA-256 of the archived text
c51571a679088f85e115ab216d149267ae4191dac36a80f0770586d9c28aa3aa
Stable URL of this page
https://metraipolis.com/documento/dc_aefd3fe240e8

How to cite

Omni-IO Skills: Harnessing Your Agent Omni-Native — arXiv:2609.31847 — arXiv (en), https://arxiv.org/abs/2609.31847 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aefd3fe240e8 (Metraipolis archive dc_aefd3fe240e8, sha256 c51571a679088f85e115ab216d149267ae4191dac36a80f0770586d9c28aa3aa)
BibTeX
@misc{dcaefd3fe240e8,
  title = {Omni-IO Skills: Harnessing Your Agent Omni-Native — arXiv:2609.31847},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31847},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aefd3fe240e8; sha256 c51571a679088f85e115ab216d149267ae4191dac36a80f0770586d9c28aa3aa},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31847. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

General-purpose agents can plan, reason, and act over long horizons, yet their production capabilities remain fragmented across text, images, audio, video, documents, 3D assets, and code. Extending a foundation model to additional modalities ties capability growth to costly model updates, while assembling specialist models and tools leaves unresolved how procedures, dependencies, intermediate assets, and cross-turn revisions should be coordinated. We present Omni-IO Skills, a plug-and-play Agent Harness that makes existing agents omni-native through hierarchical Skills, a standardized multimodal execution interface, dependency-aware orchestration, and a persistent Asset Registry. Multi-asset workflows are represented as Declare Execution Graphs, which schedule independent operations concurrently and register successful outputs for downstream and cross-turn reuse across replaceable execution backends. Its 27 Skills cover 38 representative tasks spanning seven artifact modalities and four capability families: understanding, generation, reasoning, and retrieval. On UniM-90, the harness raises the input-support rates of GPT-5.6 Sol and Claude Sonnet 5 from 40.00% and 38.89% to 100%, while increasing relative Semantic--Quality Coupled Score from 26.99 to 74.94 and from 27.82 to 77.78, respectively; Strict Structure Score reaches 100.00 and 99.78. These results establish harness-level capability composition as a practical route to broad, evolvable Omni systems without changing the host agent's reasoning core.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.31847 — 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 2026-10-07T21:27:08.371Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).