mlsanityData to 7 Oct 2026

Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systems

arXiv 2601.20230 ↗First posted 28 Jan 2026cs.CL cs.HCcited by 1

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Full-duplex voice interaction is crucial for natural human computer interaction. We present a framework that decomposes complex dialogue into minimal conversational units, enabling the system to process each unit independently and predict when to transit to the next. This framework is instantiated as a semi-cascaded full-duplex dialogue system built around a multimodal large language model, supported by auxiliary modules such as voice activity detection (VAD) and text-to-speech (TTS) synthesis. The resulting system operates in a train-free, plug-and-play manner. Experiments on the HumDial dataset demonstrate the effectiveness of our framework, which ranks second among all teams on the test set of the Human-like Spoken Dialogue Systems Challenge (Track 2: Full-Duplex Interaction). Code is available at the GitHub repository https://github.com/yu-haoyuan/fd-badcat.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 13 of its 13 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

13 of 13 references.

References · 13

  1. 2025Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Modelscited by 53
  2. 2024A Full-duplex Speech Dialogue Scheme Based On Large Language Modelscited by 40
  3. 2025OSUM-EChat: Enhancing End-to-End Empathetic Spoken Chatbot via Understanding-Driven Spoken Dialoguecited by 21
  4. 2025FireRedChat: A Pluggable, Full-Duplex Voice Interaction System with Cascaded and Semi-Cascaded Implementationscited by 17
  5. 2025Game-Time: Evaluating Temporal Dynamics in Spoken Language Modelscited by 13
  6. 2025Chronological Thinking in Full-Duplex Spoken Dialogue Language Modelscited by 13
  7. 2025Easy Turn: Integrating Acoustic and Linguistic Modalities for Robust Turn-Taking in Full-Duplex Spoken Dialogue Systemscited by 11
  8. 2025From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Modelscited by 9
  9. 2025Chain-of-Thought Training for Open E2E Spoken Dialogue Systemscited by 5
  10. 2026The ICASSP 2026 HumDial Challenge: Benchmarking Human-like Spoken Dialogue Systems in the LLM Eracited by 5
  11. 2025Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systemscited by 4
  12. 2025Towards General Auditory Intelligence: Large Multimodal Models for Machine Listening and Speakingcited by 4
1 more
  1. 2025MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labelingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialoguecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026BayLing-Duplex: Native Full-Duplex Speech Dialogue with a Single Autoregressive LLM
  2. 2024Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents
  3. 2026τ-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
  4. 2024Enabling Real-Time Conversations with Minimal Training Costs
  5. 2026SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents
  6. 2026Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models
  7. 2024SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation
  8. 2026Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency