# MIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing Counseling

arXiv: https://arxiv.org/abs/2606.29265 · HTML: https://mlsanity.com/paper/2606.29265/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 28 Jun 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024)
- [A Computational Framework for Behavioral Assessment of LLM Therapists](https://mlsanity.com/paper/2401.00820/) (2024)
- [Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation](https://mlsanity.com/paper/2402.13211/) (2024)
- [Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback](https://mlsanity.com/paper/2501.01377/) (2025)
- [EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models](https://mlsanity.com/paper/2502.04424/) (2025)
- [Helping the Helper: Supporting Peer Counselors via AI-Empowered Practice and Feedback](https://mlsanity.com/paper/2305.08982/) (2023)
- [PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection](https://mlsanity.com/paper/2310.20256/) (2023)
- [Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling](https://mlsanity.com/paper/2505.15715/) (2025)
- [Virtual Agents for Alcohol Use Counseling: Exploring LLM-Powered Motivational Interviewing](https://mlsanity.com/paper/2407.08095/) (2024)
- [Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning](https://mlsanity.com/paper/2403.15737/) (2024)
- [CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Exploration](https://mlsanity.com/paper/2502.02807/) (2025)
- [Rethinking the Alignment of Psychotherapy Dialogue Generation with Motivational Interviewing Strategies](https://mlsanity.com/paper/2408.06527/) (2024)
- [Psy-Copilot: Visual Chain of Thought for Counseling](https://mlsanity.com/paper/2503.03645/) (2025)

## Abstract (arXiv)

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 reverse-engineers 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 state-of-the-art systems with an order of magnitude less computation.