StagePilot: 网络诱骗中长程对话模拟的阶段级规划
StagePilot: Stage-Level Planning for Long-Horizon Dialogue Simulation in Cybergrooming
AI总结：
提出StagePilot框架，通过分离阶段级规划与响应生成，结合强化学习学习阶段策略，实现网络诱骗对话的结构化、连贯模拟，相比基线减少对话停滞，IQL+AWAC变体最终阶段到达率提升43%。
摘要：
网络诱骗是对青少年的一种不断演变的威胁，需要主动的教育干预。我们通过将对话进展建模为阶段式交互上的结构化规划问题来解决这一问题。我们提出StagePilot，一个将阶段级规划与响应生成分离的对话框架，其中模型在受约束的转换下选择下一阶段，并基于该阶段生成响应，从而实现连贯且逼真的进展。使用强化学习从离线数据中学习阶段级策略，优化情感对齐和目标一致进展。我们的实证实验表明，与基线相比，StagePilot生成更结构化、更连贯的对话轨迹，并减少对话停滞；值得注意的是，IQL+AWAC变体更频繁地到达最终阶段，同时保持超过70%的正面或中性响应，实现了43%的相对改进。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
