cs.SDApr 17, 2026

VoxMind: An End-to-End Agentic Spoken Dialogue System

Authors: Tianle LiangYifu ChenShengpeng JiYijun ChenZhiyang JiaJingyu LuFan ZhuoXueyi Pu+2 more

Organizations: Zhejiang University · China University of Petroleum-Beijing at Karamay · Xiamen University

Abstract

Recent end-to-end spoken dialogue models enable natural interaction. However, as user demands become increasingly complex, models that rely solely on conversational abilities often struggle to cope. Incorporating agentic capabilities is therefore essential: by enabling tool use, these models can extend their knowledge boundaries and better solve real-world tasks. Yet, existing research has largely concentrated on core perception and generation, with comparatively limited exploration of such tool-augmented extensions. To bridge this gap, we present VoxMind, an integrated framework designed to equip end-to-end spoken dialogue models with comprehensive agentic abilities. Leveraging our curated 470-hour AgentChat dataset, we incorporate a "Think-before-Speak" mechanism, enabling the model to internalize structured reasoning as a critical prerequisite for planning and response generation. Furthermore, to mitigate latency bottlenecks caused by large-scale tool integration, we propose a Multi-Agent Dynamic Tool Management architecture. By asynchronously delegating retrieval tasks to an auxiliary agent aligned with the main model's reasoning trajectory, this system effectively decouples inference latency from toolset size. Experimental results confirm that VoxMind achieves significant improvements in agent performance: compared with strong baselines, the task completion rate increases from 34.88% to 74.57%, outperforming Gemini-2.5-Pro on spoken agent tasks while preserving general conversational quality. The source code and associated data are publicly available at https://github.com/MM-Speech/VoxMind.

Explore similar work

CardsList
  1. SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue

    Mar 17, 2026Jonggeun Lee, Junseong Pyo, Jeongmin Park +1Voice AgentsDialogue

  2. Endpoint Anticipation for Low-Latency Spoken Dialogue

    Jun 11, 2026Sathvik Udupa, Shinji Watanabe, Petr Schwarz +1Turn-TakingLow-Latency Systems