PulseAugur
EN
LIVE 22:58:55

New framework StoryMI generates steerable therapeutic dialogues using multi-LLM agents

Researchers have developed StoryMI, a novel multi-LLM agent framework designed to generate therapeutic dialogues for motivational interviewing (MI). This system expands client profiles into narrative contexts, enabling distinct therapist and client agents to produce MI-coded utterances. An interaction agent dynamically manages MI strategies throughout the conversation, with evaluations conducted using lexical metrics, MI-specific measures, and expert assessments. The framework aims to improve MI adherence and clinical plausibility in simulated psychotherapy dialogues. AI

IMPACT This research could lead to more sophisticated AI agents for mental health support and therapeutic applications.

RANK_REASON The cluster contains an academic paper detailing a new framework for AI-driven dialogue generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New framework StoryMI generates steerable therapeutic dialogues using multi-LLM agents

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Qingyu Meng, Min Chen, Dingming Liu, Yifan Mo, Yue Su, Xin Sun, Koen Hindriks, Jiahuan Pei ·

    StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation

    arXiv:2605.27393v1 Announce Type: cross Abstract: 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 StoryM…