@inproceedings{an-etal-2026-stagepilot,
    title = "{S}tage{P}ilot: Stage-Level Planning for Long-Horizon Dialogue Simulation in Cybergrooming",
    author = "An, Heajun  and
      Zhang, Qi  and
      Liu, Minqian  and
      Zhang, Xinyi  and
      Lee, Sang Won  and
      Huang, Lifu  and
      Wisniewski, Pamela  and
      Cho, Jin-Hee",
    editor = "Choi, Jinho D.  and
      Chen, Yun-Nung  and
      Funakoshi, Kotaro  and
      Emami, Ali",
    booktitle = "Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
    month = aug,
    year = "2026",
    address = "Atlanta, Georgia, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-nlpsi/2026.sigdial-1.37/",
    pages = "536--552",
    abstract = "Cybergrooming is an evolving threat to youth, requiring proactive educational interventions. We address this by modeling dialogue progression as a structured planning problem over stage-wise interactions. We propose StagePilot, a dialogue framework that separates stage-level planning from response generation, in which the model selects the next stage under constrained transitions and generates responses conditioned on it, enabling coherent and realistic progression. Reinforcement learning is used to learn stage-level policies from offline data, optimizing for both emotional alignment and goal-consistent progression. Our empirical experiments show that StagePilot generates more structured, coherent dialogue trajectories and reduces conversational stagnation compared to baselines; notably, the IQL+AWAC variant reaches the final stage more often while maintaining over 70{\%} positive or neutral responses, yielding a 43{\%} relative improvement."
}