Preprint
Aug 2026
ESCRAG-R1: Retrieval-Augmented Reinforcement Learning for Emotional Support Conversation
ESCRAG-R1 is proposed, a unified framework that integrates retrieval-based psychological guidance into Group Relative Policy Optimization (GRPO) and transforms external knowledge into a robust learning signal that stimulates explicit internal reasoning prior to generation and fundamentally reshapes the model's internal...
Wei-Chuan Liu, Yuxuan Hu, Yi-Rong Sun et al.
· 1 citation