Jarvis：面向多人对话的主动式语音智能体

View PDF HTML (experimental)

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. We introduce Jarvis, a real-time proactive speech agent that audibly participates in multi-party human conversations. Grounded in a document shared beforehand, Jarvis follows the discussion and intervenes when the group misses or misstates a fact and does not correct itself within a few turns. We make three contributions: a problem setting based on epistemic breakdowns that makes proactive intervention measurable, realized as CHI-180-proactive, a synthetic multi-party dataset seeded with known gaps, errors, and self-corrections; a proactive backbone that harnesses a small, open-weight model with deterministic checks and grounds every claim in a source sentence; and interaction techniques for taking the floor in live speech and showing the cited evidence on screen. On CHI-180-proactive, Jarvis is correct on most events it addresses and stays silent 97% of the time when the group resolves an issue itself. A live study with 23 participants confirms these trends with real-time interventions.

Comments:	45 pages, 6 figures, 20 tables
Subjects:	Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.07506 [cs.HC]
	(or arXiv:2610.07506v2 [cs.HC] for this version)
	https://doi.org/10.48550/arXiv.2610.07506 arXiv-issued DOI via DataCite

Submission history

From: Seunghyun Oh [view email]
[v1] Mon, 5 Oct 2026 23:18:04 UTC (3,388 KB)
[v2] Sun, 25 Oct 2026 20:42:28 UTC (3,388 KB)