MIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing Counseling
Year: 2026
Type: conference-paper
Abstract: Reasoning large language models (LLMs) have recently made much progress in complex problem-solving, leveraging internal reasoning (or thought) to guide their solution generation.However, existing LLM-based counseling agents, including those using Motivational Interviewing (MI), generate responses without explicitly aligning thoughts with counseling techniques, limiting their effectiveness.We propose MIThinker, a lightweight thinking model that generates therapeutic thoughts to guide MI counseling agents in strategy selection and response generation.To overcome the lack of annotated thought data, we introduce AugR1-MI, an automated pipeline that reverseengineers counselor's thoughts from observed responses.Through two-stage training combining supervised fine-tuning and reinforcement learning, MIThinker demonstrates improved theory-of-mind assessment and strategy alignment.Comprehensive evaluations show that MindfulMI, our agent leveraging MIThinker, achieves MI competency comparable to stateof-the-art systems with an order of magnitude less computation.
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166805101