SOURCE-LINKED INTELLIGENCE

MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Conversational voice agents have advanced significantly, offering increasingly natural human-machine interactions through both cascaded and end-to-end architectures. However, while recent benchmarks extensively evaluate dyadic interactions and passive audio comprehension, they largely overlook a prevalent real-world scenario: multi-party conversations. Evaluating agents in these settings is fundamentally more challenging than in dyadic interactions due to the exponentially greater conversational complexity. For voice agents to integrate seamlessly into human group dynamics, they must not only

Read original source ↗ Open in workspace

recordType

paper

region

Global