Omni-IO Skills: Harnessing Your Agent Omni-Native

Yanlin Li; Mingyang Hao; Shengqiong Wu; Hao Fei; Mong-Li Lee; Wynne Hsu

cs.CLSep 25, 2026

Omni-IO Skills: Harnessing Your Agent Omni-Native

Authors: Yanlin Li, Mingyang Hao, Shengqiong Wu, Hao Fei, Mong-Li Lee, Wynne Hsu

Organizations: National University of Singapore · University of Oxford

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.

Figures & tables

Figure 1: Overview of Omni-IO Skills. Hierarchical Skills orchestrate multimodal understanding and generation, while generated assets are registered for downstream and cross-turn reuse.

Figure 3: Architecture overview of Omni-IO Skills, which presents the four-layer architecture.

Figure 4: Hierarchical organization of Omni-IO Skills. Higher-level Skills organize and invoke lower-level Skills. Scenario Skills coordinate application-level objectives, Expert Skills encapsulate reusable production workflows, and Atomic Skills provide executable capability primitives.

Panel of Table 1 — Table 1: Implemented Omni-IO Skills and their hierarchical composition.

Figure 5: Runtime workflow of Omni-IO Skills, illustrated with a product promotion request. The selected S5 Event Material Scenario Skill expands through Expert Skills into five Atomic Skills, whose dependencies form a validated Declare Execution Graph (DEG) and determine successive execution Waves. Each ready node follows the same execution loop of tool routing, provider resolution, asset injection, and execution, while successful outputs are registered for downstream use and cross-turn reuse.

Stage	Node(s)	Dependency and output
Wave 0	Analyze product reference images	Extracts product appearance and visual constraints.
Wave 1	Generate poster assets	Generates poster-ready visuals from the product analysis.
	Generate video and sound effects	Generates video and sound-effect assets in parallel.
Wave 2	Generate promotional video and poster	Combines assets into the promotional video and poster.
Wave 3	Generate landing web page	Assembles a landing page from the promotional outputs.

Table 2: Illustrative four-Wave DEG execution for the product-promotion case in Figure 5 .

Base Agent	$\bm{\tau}$	Absolute				Relative
Base Agent	$\bm{\tau}$	SQCS	ICS	StS	LeS	SQCS	ICS	StS	LeS
GPT-5.6 Sol	40%	67.49	86.53	47.84	72.22	26.99	34.61	19.14	28.89
+ Omni-IO Skills	100%	74.94	93.98	100.00	100.00	74.94	93.98	100.00	100.00
Claude Sonnet 5	38.89%	71.53	82.29	52.21	68.57	27.82	32.00	20.30	26.67
+ Omni-IO Skills	100%	77.78	83.28	99.78	100.00	77.78	83.28	99.78	100.00

Table 3: Main results on UniM-90. We report the input-support rate

\tau

together with the absolute and relative variants of Semantic–Quality Coupled Score (SQCS), Interleaved Coherence Score (ICS), Strict Structure Score (StS), and Lenient Structure Score (LeS). Higher is better for all metrics.

Figure 6: Qualitative case studies of Omni-IO Skills with GPT-5.6 Sol and Claude Sonnet 5.

LLM Agent Harnesses

LLM agent harnesses are the software and runtime systems that organize an agent’s tools, context, state, execution, and safeguards.

See all 389 papers

OmniGAIA: Towards Native Omni-Modal AI Agents
Feb 26, 2026Xiaoxi Li, Wenxiang Jiao, Jiarui Jin +10Multimodal Reasoning AI Agent Benchmarks
1Renmin University of China · 2Xiaohongshu Inc. · 3Peking University +2
Orchestra-o1: Omnimodal Agent Orchestration
Jun 10, 2026Fan Zhang, Vireo Zhang, Shengju Qian +8LLM Agent Orchestration Group Relative Policy Optimization
CUHK · LIGHTSPEED · PKU +2
Qwen3.8-Omni: Towards Native Omni-Modal Agents
Sep 22, 2026Qwen TeamMultimodal Pretraining Multimodal Large Language Models
Qwen Team

Feb 26, 2026J/K move · Enter open · S save

OmniGAIA: Towards Native Omni-Modal AI Agents

Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Haoxuan Li+9

1Renmin University of China · 2Xiaohongshu Inc. · 3Peking University+2

Multimodal Reasoning AI Agent Benchmarks Multimodal Agents Multimodal Understanding Multimodal Tool Use

Open paper AskPDF arXiv

Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However, current multi-modal LLMs are primarily confined to bi-modal interactions (e.g., vision-language), lacking the unified cognitive capabilities required for general AI assistants. To bridge this gap, we introduce OmniGAIA, a comprehensive benchmark designed to evaluate omni-modal agents on tasks necessitating deep reasoning and multi-turn tool execution across video, audio, and image modalities. Constructed via a novel omni-modal event graph approach, OmniGAIA synthesizes complex, multi-hop queries derived from real-world data that require cross-modal reasoning and external tool integration. Furthermore, we propose OmniAtlas, a native omni-modal foundation agent under tool-integrated reasoning paradigm with active omni-modal perception. Trained on trajectories synthesized via a hindsight-guided tree exploration strategy and OmniDPO for fine-grained error correction, OmniAtlas effectively enhances the tool-use capabilities of existing open-source models. This work marks a step towards next-generation native omni-modal AI assistants for real-world scenarios.

Abstract

LLM Agent Harnesses

Explore similar work

OmniGAIA: Towards Native Omni-Modal AI Agents

Orchestra-o1: Omnimodal Agent Orchestration

Qwen3.8-Omni: Towards Native Omni-Modal Agents