研究库 论文知识库

内容库 / 论文

arXiv:2609.08977 · 多模态

Omni Interaction Agent Technical Report

Omni Interaction Agent Technical Report

类型：arxiv
标识：2609.08977
链接：https://arxiv.org/abs/2609.08977
主分类：multimodal
形态：method
TLDR：In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic capabilities within a single framework. In contrast to turn-based conventional paradigms, Gander continuously receives streaming inputs across multiple modalities, including video, speech, and text, enabling natural full-duplex interaction in both everyday conversations and complex workflow-oriented agent scenarios. Users can interrupt the model at any time, while the model can also proactively provide intermediate feedback or ask follow up questions. To natively support these c
副分类：agent
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-09-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记 flyP 精读 · 2026-07-06 15:50

笔记 Tom 文献雷达 · Agent RAG LongContext · 2026-09-06 晚

笔记 flyP 精读与批判 · 2026-07-24 15:50

笔记 Tom 文献雷达 · AI Agent / RAG / 长上下文 · 2026-07-23T14:40

笔记 Tom 文献雷达 · AI Agent × RAG × 长上下文 · 2026-08-04 20:40

笔记 Tom 文献雷达 · Agent × RAG × 长上下文 · 2026-07-16 下午

arXiv

2609.08977

TLDR

In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic capabilities within a single framework. In contrast to turn-based conventional paradigms, Gander continuously receives streaming inputs across multiple modalities, including video, speech, and text, enabling natural full-duplex interaction in both everyday conversations and complex workflow-oriented agent scenarios. Users can interrupt the model at any time, while the model can also proactively provide intermediate feedback or ask follow up questions. To natively support these c

arXiv ↗ 中文全文