{"slug": "storymi-steerable-multi-agent-therapeutic-dialogue-generation", "title": "StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation", "summary": "Researchers have developed StoryMI, a multi-agent framework using large language models to generate controlled motivational interviewing dialogues for psychotherapy. The system uses questionnaire-based client profiles expanded into situational stories, with therapist and client agents guided by an interaction agent that dynamically controls therapeutic strategies. A benchmark of 6,000 simulated dialogues across 12 MI codes and 13 symptom domains showed that situational grounding and macro-level strategy control improved clinical adherence and plausibility in generated therapy conversations.", "body_md": "arXiv:2605.27393v1 Announce Type: new\nAbstract: Large language models (LLMs) can generate fluent dialogue, but prior works lack situational grounding, dynamic strategy control, and evaluation aligned with clinical standards in motivational interviewing (MI). We introduce StoryMI, a multi-LLM agent framework for controllable MI dialogue generation, where questionnaire-based client profiles are expanded into situational stories that provide narrative context for the dialogue. Therapist and client agents generate MI-coded utterances guided by MI codes selected by the interaction agent, while an interaction agent dynamically coordinates exchanges to control MI strategies during a multi-turn conversation. We propose a two-level evaluation protocol: lexical metrics and MI-specific measures of macro-level counseling strategies, alongside LLM-as-judge and human expert assessments. We construct a dataset of 6K simulated MI dialogues grounded in 1K questionnaire-story pairs, covering 12 MI codes and 13 symptom domains, and benchmark six open- and closed-source LLMs. Our results show that situational grounding and macro-level control can improve MI adherence and clinical plausibility, demonstrating the effectiveness of a structured multi-agent workflow for psychotherapy dialogue generation. We provide code and data for reproducibility.", "url": "https://wpnews.pro/news/storymi-steerable-multi-agent-therapeutic-dialogue-generation", "canonical_source": "https://arxiv.org/abs/2605.27393", "published_at": "2026-05-28 04:00:00+00:00", "updated_at": "2026-05-28 04:34:53.729375+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "generative-ai", "ai-agents", "artificial-intelligence"], "entities": ["StoryMI", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/storymi-steerable-multi-agent-therapeutic-dialogue-generation", "markdown": "https://wpnews.pro/news/storymi-steerable-multi-agent-therapeutic-dialogue-generation.md", "text": "https://wpnews.pro/news/storymi-steerable-multi-agent-therapeutic-dialogue-generation.txt", "jsonld": "https://wpnews.pro/news/storymi-steerable-multi-agent-therapeutic-dialogue-generation.jsonld"}}