## ProUtt: Proactive Prediction in Human-Machine Dialogue Proactively predicting a user's next utterance in human-machine dialogue can streamline interaction and improve user experience. Existing commercial API-based solutions raise privacy concerns, while deploying general-purpose large language models (LLMs) locally remains computationally expensive. A new study introduces ProUtt, an LLM-driven method for preference data synthesis, aimed at proactive next utterance prediction. ProUtt converts dialogue history into an intent tree and explicitly models intent reasoning trajectories by predicting the next plausible path from both exploitation and exploration perspectives. ## Methodology and Results The proposed method constructs preference and non-preference reasoning processes by perturbing or revising intent tree paths at different future turns. Extensive evaluations, using LLM-as-a-judge and human judgments, demonstrate that ProUtt consistently outperforms existing data synthesis methods, user simulators, and commercial LLM APIs across four benchmark datasets. The code and synthesized datasets have been released to facilitate future research in this field.