AI RESEARCH
Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions
arXiv CS.CL
•
ArXi:2408.15787v2 Announce Type: replace Creating effective dialogue systems for mental health requires high-quality multi-turn counseling dialogue data, yet collecting real counselor-client conversations presents significant challenges, including privacy concerns, high costs, and limited scalability. We present \textbf{Interactive Agents}, a novel framework that simulates naturalistic counseling dialogues through controlled LLM-to-LLM interactions. The framework