EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents 事件

EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents arXiv:2605.13841v2 Announce Type: replace-cross Abstract: Voice agents, artificial intelligence systems that conduct spoken conversations to complete tasks, are increasingly deployed across enterprise applications. However, no existing benchmark jointly addresses two core evaluation challenges: generating realistic simulated conversations, and measuring quality across the full scope of voice-specific failure modes. We present EVA