---
id: 20260930-T0-08
title: "Omni-IO Skills：让智能体原生打通文本图像音频视频与3D"
title_en: "Omni-IO Skills Lets Agents Natively Handle Text, Image, Audio, Video and 3D"
url: https://ai.daily.yangsir.net/daily/20260930-T0-08
issue_date: 2026-09-30
publish_date: 2026-09-29T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2609.31847
---

# Omni-IO Skills：让智能体原生打通文本图像音频视频与3D

通用智能体已经能进行长程规划、推理与执行，但其产出能力仍分散在文本、图像、音频、视频、文档、3D资产和代码等模态中。Omni-IO Skills 提出一套方案，让智能体无需为每种模态单独扩展基础模型，即可原生调用多种输入输出能力。论文探讨了如何统一调度这些分散能力，减少为新增模态而重复训练基础模型的成本。对开发者而言，这意味着构建多模态智能体时不必维护多套模型管线，可以一套技能体系覆盖文字、图像、音视频和3D内容生成。

## English Version

**Omni-IO Skills Lets Agents Natively Handle Text, Image, Audio, Video and 3D**

General-purpose agents can plan, reason, and act over long horizons, yet their output capabilities remain fragmented across text, images, audio, video, documents, 3D assets, and code. Omni-IO Skills proposes a scheme that lets agents natively invoke multiple input and output modalities without extending a foundation model separately for each one. The paper examines how to unify scheduling of these fragmented capabilities and reduce the cost of retraining base models for every new modality. For developers, this means building multimodal agents without maintaining multiple model pipelines, covering text, image, audio, video, and 3D generation under one skill system.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2609.31847)

**详情页**：https://ai.daily.yangsir.net/daily/20260930-T0-08

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*