# Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systems Source: [Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systems]() Collection index: [llms.txt]() Data updated: 2026-01-31T05:00:04.715Z Authors: Haoyuan Yu, Yuxuan Chen, Minjie Cai Published: 2026-01-28T04:00:37.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Full-duplex dialogue on HumDial 1.5 (dev)](): Full-duplex dialogue; HumDial 1.5 (dev); First Response Delay: 1.528. - [Full-duplex dialogue on HumDial 1.5 (test)](): Full-duplex dialogue; HumDial 1.5 (test); Interruption Score: 89.7. ## Original sources and implementation [Original paper]() [PDF]()