arXiv AI June 15, 2026 By Donghang Wu, Haoyang Zhang, Chen Chen, Tianyu Zhang, Fei Tian, Xuerui Yang, Gang Yu, Hexin Liu, Nana Hou, Yuchen Hu, Eng Siong Chng

Chronological Thinking in Full-Duplex Spoken Dialogue Language Models

Read the original on arXiv AI →

arXiv:2510. 05150v3 Announce Type: replace-cross Abstract: Recent advances in spoken dialogue language models (SDLMs) reflect growing interest in shifting from turn-based to full-duplex systems, where the models continuously perceive user speech streams while generating responses.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 7

Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking

arXiv:2607. 03093v1 Announce Type: cross Abstract: Thinking has emerged as a critical capability for Large Language Models (LLMs) tackling complex tasks.

By Ante Wang, Jiaqi Fu, Xuanyi Chen, Ruotian Ma, Zhaopeng Tu, Weizhi Ma, Yang Liu

llms benchmarks

arXiv Computation and Language

Sep 23

Spoken Language Models that Think Aloud

arXiv:2609.26488v1 Announce Type: new Abstract: While Chain-of-Thought (CoT) reasoning has improved the capability of language models, directly applying it to Spoken Language Models (SLMs) may introd...

By Junyi Ao, Kainan Peng, Mingbo Ma, Shun Zhang, Zhenyu Tang, Xutai Ma, Xiang Li, Yinghao Li, Yuancheng Wang, Zhizheng Wu, Haizhou Li, Qing He, Xubo Liu

llms benchmarks

arXiv AI

Jun 9

Liberating LLM Capabilities in Full-Duplex Speech Models

arXiv:2606. 07547v1 Announce Type: cross Abstract: Speech-based large language models are typically constrained to spoken replies, which limits their user-facing outputs to what can be verbalized and suppresses text-native capabilities such as code generation, structured analysis, and multi-step reasoning in realtime interaction, for tasks that require persistent, structured, and inspectable intermediate outputs.

By Luoyuan Zhang, Bokai Xu, Junbo Cui, Weiyue Sun, Yingjing Xu, Hanyu Liu, Yuan Yao

llms data-engineering

arXiv Computation and Language

Aug 25

Agentic-DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech

arXiv:2608.16053v2 Announce Type: replace Abstract: Synthetic conversational speech has become an important resource for developing and evaluating conversational speech systems. However, existing dia...

By Pengcheng Wang, Sheng Li, Jiyi Li, Takahiro Shinozaki

llms agents multimodal

arXiv AI

Sep 16

Never Stop Thinking: Continuous-Time Language Agents

arXiv:2609.17416v1 Announce Type: new Abstract: Voice agents built on LLMs follow a rigid listen-think-speak loop that inserts seconds of dead air before every reply. We show that continuous-time cog...

By Bojie Li, Noah Shi

llms agents reinforcement-learning

arXiv AI

Sep 24

Neither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Models

arXiv:2609.27372v1 Announce Type: cross Abstract: Benchmarks for full-duplex spoken dialogue models score turn-taking with binary fixed-window rules that reward immediate response or silence by compl...

By Kian Shamsaie, Iman Modarressi

benchmarks

One email a morning, machine-written

Related stories

Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking

Spoken Language Models that Think Aloud

Liberating LLM Capabilities in Full-Duplex Speech Models

Agentic-DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech

Never Stop Thinking: Continuous-Time Language Agents

Neither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Models