ChatThero: A Language Agent for Recovery Support

ICLR 2026 Conference Submission22038 Authors

Keywords: Healthcare AI, Clinical NLP, Multi-Agent Simulation, Long-Horizon Dialogue Modeling, Behavior Change Support

Abstract: Substance use disorders (SUDs) affect millions of people, and relapses are common, requiring multi-session treatments. Access to care is limited, which contributes to the challenge of recovery support. We present ChatThero, an innovative low-cost, multi-session, stressor-aware, and memory-persistent autonomous language agent designed to facilitate long-term behavior change and therapeutic support in addiction recovery. Unlike existing work that mostly finetuned large language models (LLMs) on patient-therapist conversation data, ChatThero was trained in a multi-agent simulated environment that mirrors real therapy. We created anonymized patient profiles from recovery communities (e.g., Reddit). We classify patients as easy, medium, and difficult, three scales representing their resistance to recovery. We created an external environment by introducing stressors (e.g., social determinants of health) to simulate real-world situations. We dynamically inject clinically-grounded therapeutic strategies (motivational interview and cognitive behavioral therapy). Our evaluation, conducted by both human (blinded clinicians) and LLM-as-Judge, shows that ChatThero is superior in empathy and clinical relevance. We show that stressor simulation improves robustness of ChatThero. Explicit stressors increase relapse-like setbacks, matching real-world patterns. We evaluate ChatThero with behavioral change metrics. On a 1--5 scale, ChatThero raises motivation by +1.71 points (from 2.39 to 4.10) and confidence by +1.67 points (from 1.52 to 3.19), substantially outperforming GPT-5. On difficult patients, ChatThero reaches the success milestone with 26% fewer turns than GPT-5.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 22038