Metraipolis › archive › dc_d500b82fc4fa

HiThink Turn: An Intent-Aware Turn-Taking Control Module for Full-Duplex Dialogue — arXiv:2609.34096

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34096
License (as archived): CC0-1.0
Archived: 2026-10-07T22:35:33.209Z
SHA-256 of the archived text: 545a700c128cfcd17c6ad17753ce87bdfd2af4ab0deb1f22175c6f71a8d15f78
Stable URL of this page: https://metraipolis.com/documento/dc_d500b82fc4fa

How to cite

HiThink Turn: An Intent-Aware Turn-Taking Control Module for Full-Duplex Dialogue — arXiv:2609.34096 — arXiv (en), https://arxiv.org/abs/2609.34096 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d500b82fc4fa (Metraipolis archive dc_d500b82fc4fa, sha256 545a700c128cfcd17c6ad17753ce87bdfd2af4ab0deb1f22175c6f71a8d15f78)

BibTeX

@misc{dcd500b82fc4fa,
  title = {HiThink Turn: An Intent-Aware Turn-Taking Control Module for Full-Duplex Dialogue — arXiv:2609.34096},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34096},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d500b82fc4fa; sha256 545a700c128cfcd17c6ad17753ce87bdfd2af4ab0deb1f22175c6f71a8d15f78},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34096. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Full-duplex dialogue requires timely yet selective interruption handling, which end-of-turn prediction alone cannot achieve: complete utterances may need no response, while unfinished requests may warrant interruption. To address this challenge, we propose HiThink Turn, an intent-aware streaming turn-state predictor that separates response intent from semantic completeness and conditions decisions on system playback state. A key contribution is minimal intent-sufficient prefix supervision, constructed through LLM judgments and speech alignment, while training on audio truncated at chunk boundaries improves robustness to partial speech. These components support streaming inference with 240-ms audio chunks, enabling low-latency, accurate full-duplex turn control. Experiments show that HiThink Turn leads the compared methods in Easy Turn macro accuracy, Full-Duplex-Bench average interaction rate score (0.933), and non-target-speech average playback resume rate (0.735). Additionally, intent-prefix triggering raises interruption success from 89\% to 98\% and reduces mean stop latency by 60.9\%.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.HC).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.34096 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:13:52.240Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).