arXiv 2609.31847 · cs.CL · 2026-09-25
Omni-IO Skills: Harnessing Your Agent Omni-Native
Yanlin Li, Mingyang Hao, Shengqiong Wu, Hao Fei, Mong-Li Lee, Wynne Hsu
National University of Singapore
在最新榜 #9 2026-W40 第 4 名 本站收录于 2026-10-21
一句话要点
Omni-IO Skills 用分层技能和资产登记表，让现有 Agent 能读写图像、音频、视频、3D 等多种模态。
Omni-IO Skills makes existing agents omni-modal through hierarchical skills, a common execution interface and an asset registry.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲490
- Player-1: Learning to Play from Synthetic Experience ▲348
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use ▲330
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。