Omni-IO Skills: Harnessing Your Agent Omni-Native
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.
Community
Hi everyone! Sharing our new work: Omni-IO Skills: Harnessing Your Agent Omni-Native π
Your agent is only one harness away from being omni-native!
General-purpose agents like Claude and Codex are strong at reasoning and planning, but audio, video, 3D, and coordinated media workflows still depend on external tools. Extending a foundation model to new modalities ties capability growth to costly retraining. Real tasks also never stay within one modality. For example, "watch this video, compose a BGM, and turn it into a slide deck with a cover" chains understanding, generation, and conversion, and reuses intermediate assets across turns.
Research question: Can a plug-and-play harness make an existing general-purpose agent omni-native while preserving its reasoning and planning core?
Our answer: Omni-IO Skills, a multimodal harness that wraps around the agent instead of replacing it:
- 𧩠Hierarchical Skills: 27 Skills covering 38 representative tasks across 7 artifact modalities and 4 capability families (understanding, generation, reasoning, retrieval)
- π Declarative execution graphs: multi-step workflows are planned as dependency graphs, and independent tasks run in parallel
- ποΈ Asset Registry: intermediate outputs persist and are reused across turns
- π Pluggable backends: switching providers only requires a config change
On UniM, with two host agents (GPT-5.6 Sol and Claude Sonnet 5), support rates rise from under 40% to 100%, and the SQCS rises from about 27% to 75β78%.
Code, along with 20 example workflows, is open-sourced. Feel free to read, share, and star! π
π Paper: https://arxiv.org/abs/2609.31847
π» Code: https://github.com/any2any-mllm/Omni-IO-Skill
Get this paper in your agent:
hf papers read 2609.31847 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper