| title | Omni-IO Skills: Harnessing Your Agent Omni-Native |
|---|---|
| authors | Yanlin Li, Mingyang Hao, Shengqiong Wu, Hao Fei, Mong-Li Lee, Wynne Hsu |
| date | 2026-09-25 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.31847 |
| affiliation | National University of Singapore |
| upvotes | 63 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | 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. |
cite
@misc{li2026omni,
title={Omni-IO Skills: Harnessing Your Agent Omni-Native},
author={Yanlin Li and Mingyang Hao and Shengqiong Wu and Hao Fei and Mong-Li Lee and Wynne Hsu},
year={2026},
eprint={2609.31847},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.31847}
}