StagePilot: A Deep Reinforcement Learning Agent for Stage-Controlled Cybergrooming Simulation

TL;DR

StagePilot is an offline reinforcement learning dialogue agent that simulates grooming behaviors for youth prevention training, balancing realism, emotional engagement, and strategic planning.

Contribution

It introduces a novel RL-based simulation framework for modeling grooming stages with constrained transitions and composite rewards.

Findings

IQL+AWAC achieves 43% higher stage completion than baselines.

Over 70% sentiment alignment in generated dialogues.

Realistic and coherent grooming simulations validated through LLM-based evaluation.

Abstract

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.