While large language models (LLMs) excel at open-ended dialogue, effective psychotherapy requires structured progression and adherence to clinical protocols, making the design of psychotherapist chatbots challenging. We investigate how different LLM-based designs shape perceived therapeutic dialogue in a chatbot grounded in the Self-Attachment Technique (SAT), a novel self-administered psychotherapy rooted in attachment theory. We compare three architectural variants: (1) a multi-agent system utilizing finite state machine aligned with therapeutic stages and a shared long-term memory, (2) a single-agent using identical knowledge-base and the same prompts, and (3) an unguided LLM. In an eight-day randomized controlled trial (RCT) with N=66 Farsi-speaking participants, balanced across the three chatbots, the multi-agent system is perceived as significantly more natural and human-like than the other variants and achieves higher ratings across most other metrics. These findings demonstrate that for therapeutic AI, architectural orchestration is as critical as prompt engineering in fostering natural, engaging dialogue.

翻译：尽管大型语言模型（LLM）在开放式对话方面表现出色，但有效的心理治疗需要结构化的进程和临床协议的遵循，这使得心理治疗师聊天机器人的设计具有挑战性。本研究基于依恋理论衍生的新型自助心理疗法——自我依恋技术（SAT），探讨了不同基于LLM的设计如何影响聊天机器人中感知到的治疗性对话。我们比较了三种架构变体：（1）采用有限状态机与治疗阶段对齐并共享长期记忆的多智能体系统，（2）使用相同知识库和提示词的单智能体，以及（3）无引导的LLM。在一项为期八天、包含N=66名波斯语参与者的随机对照试验（RCT）中（参与者均衡分配至三种聊天机器人），多智能体系统被认为显著比其他变体更自然、更拟人，并在大多数其他指标上获得更高评分。这些发现表明，对于治疗性人工智能而言，架构编排与提示工程在促进自然、引人入胜的对话方面同等关键。