English(EN) Jarvis: A Proactive Speech Agent for Multi-Party Conversations

Jarvis：主动语音代理加入多人对话

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-07 04:00

研究人员开发了Jarvis，一种旨在主动参与多人对话的新型语音代理。与传统的被动代理不同，Jarvis仅在小组错过或误述事实且未能自我纠正时才会介入。该系统以共享文档为基础，确保所有声明都有源句子支持。在CHI-180-proactive数据集上的测试中，Jarvis正确处理了大多数事实错误，而在小组自行解决问题时，它有97%的时间保持沉默。一项对23名参与者的现场研究验证了这些发现，证明了Jarvis在实时干预方面的有效性。 AI

影响这项研究可能带来更自然、更有帮助的协作环境中的AI助手。

排序理由该项目是一篇研究论文，详细介绍了一种新的AI代理及其在特定数据集上的性能。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇研究论文，详细介绍了一种新的AI代理及其在特定数据集上的性能。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Seunghyun Oh, Hirotaka Hiraki, Shuyue Stella Li, Yulia Tsvetkov, Shyamnath Gollakota · 2026-10-07 04:00

Jarvis：一个用于多方对话的主动语音代理

arXiv:2610.07506v1 Announce Type: cross Abstract: Speech agents are reactive and dyadic: they speak when spoken to, and to one person at a time. We ask what it takes for a speech agent to instead take part in a conversation among several people and speak up only when it can help.…

本文如何被排名

报道来源 [1]

Jarvis：一个用于多方对话的主动语音代理

相关实体

相关话题