MP-Bench: 12 voice agents no better than coin flip at knowing when to speak in group chats
solyarisoftware · x · 2026-10-16
The MP-Bench paper (EMNLP 2026) tackles an overlooked question: voice agents can talk one-on-one, but can they join a group conversation?
- Across 12 voice agents, performance at knowing when to interject was no better than a coin flip — unless the agent was called by name.
- The results show current voice agents lack the turn-taking and social awareness needed for multi-party conversations, a key blocker for group-chat use cases.
More from Research
- ETH Zurich's LFD lets a frozen LLM teach drug-design generators natural-language goals — rohanpaul_ai · 2026-10-16
- Community debates whether Sonnet 3 conversation datasets are fair game for model training — Sauers_ · 2026-10-16
- Request for a Sonnet 3 dataset surfaces community-shared cyborgism and anima sets — arm1st1ce · 2026-10-16
- MLCommons launches MLPerf Endpoints, a benchmark that measures inference endpoints the way buyers actually purchase them — TheKanter · 2026-10-16
- DIY LEGO bench tests AI brick-building, GPT-6 Astra beats Opus — TheLegoless · 2026-10-16
- tszzl's theory: Tornado → Apache license → apaches → Southwest → Colorado — tszzl · 2026-10-16