Rehearsed Multi-Agent Live Product Demonstrations with Real-Time Voice Question Answering
排练式多智能体实时语音问答产品演示
机构 * PayPal AI
专题命中 音频语音多模态 :cross-modal(abstract);分类 cs.AI
AI总结 提出多智能体系统Rhetor,通过跨模态特征表示、接地脚本、排练循环和运行时同步,实现带语音问答的实时产品演示自动化。
Comments Preprint. 4 figures, 1 algorithm, 5 tables. Systems paper with a preliminary six-session case study on four deployed applications; full benchmark protocol proposed, corpus run to appear in a later revision