{
  "id": 12526394,
  "title": "Coupled but Late: Turn-Taking Between Full-Duplex Speech Models in Unscripted Dialogue",
  "url": "https://urgent.news/2026/10/06/coupled-but-late-turn-taking-between-full-duplex-speech-models-in",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-06T17:03:54.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.08683v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each other, in self-play data generation, agent societies, and model-based evaluation. In that loop no human absorbs a timing error: each model's turn-taking is the other's input. We ask what timing the loop settles into. Two PersonaPlex-7B instances exchange audio tokens on a shared…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}