SOURCE-LINKED INTELLIGENCE

MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Voice provides a natural and immediate interface for AI agents. Many settings in which voice agents could be useful, including meetings, households, and collaborative work, are inherently multi-speaker. Supporting these settings introduces challenges that are largely absent from one-on-one interaction. We introduce the Multi-Speaker Interaction Benchmark (MSI-Bench) for evaluating multi-speaker voice interaction. Each test case is a short multi-party multi-turn audio scene with participant context, expected tool calls, and atomic rubrics. The benchmark targets three capability families: multi-

Read original source ↗ Open in workspace

recordType

paper

region

Global