StagePilot: A Deep Reinforcement Learning Agent for Stage-Controlled Cybergrooming Simulation
This addresses cybergrooming prevention for youth, but it is incremental as it applies existing RL methods to a specific domain.
The paper tackled the problem of simulating cybergrooming for youth prevention training by developing StagePilot, an offline RL-based dialogue agent that generates realistic conversations, with results showing it reaches the final stage up to 43% more frequently than baselines while maintaining over 70% sentiment alignment.
Cybergrooming is an evolving threat to youth, necessitating proactive educational interventions. We propose StagePilot, an offline RL-based dialogue agent that simulates the stage-wise progression of grooming behaviors for prevention training. StagePilot selects conversational stages using a composite reward that balances user sentiment and goal proximity, with transitions constrained to adjacent stages for realism and interpretability. We evaluate StagePilot through LLM-based simulations, measuring stage completion, dialogue efficiency, and emotional engagement. Results show that StagePilot generates realistic and coherent conversations aligned with grooming dynamics. Among tested methods, the IQL+AWAC agent achieves the best balance between strategic planning and emotional coherence, reaching the final stage up to 43% more frequently than baselines while maintaining over 70% sentiment alignment.