#artificial intelligence
May 2026
EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents
EVA-Bench is presented, an end-to-end evaluation framework that addresses realistic conversation simulation and comprehensive voice-specific evaluation and introduces two composite metrics: EVA-A (Accuracy) and EVA-X (Experience).
Tara Bogavelli, Gabrielle Gauthier Melançon, Katrina Stankiewicz et al.
· arXiv.org · 17 citations
· ⚡2