From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health
A survey traces mental-health LLMs from assessment tools to empathetic chat and stateful personalized companions.
This survey argues that LLM use in mental health has progressed through three phases: passive information and pattern-recognition tools, stateless empathetic conversationalists, and stateful personalized companion agents. It reviews supporting technologies, including profile, memory, reasoning, and planning architectures, plus datasets and benchmarks. The authors synthesize the literature and outline a roadmap for responsible, human-centered mental-health AI, with curated resources on GitHub.
- Frames three phases: assessment tools, empathetic chat, then personalized companions.
- Reviews profile, memory, reasoning, and planning in mental-health agents.
- Covers datasets, benchmarks, and a roadmap for responsible support AI.
Full article253 words · extracted from huggingface.co · click to collapse
The rising global prevalence of mental health conditions, together with longstanding barriers in traditional healthcare, such as limited resources, high cost, stigma, and privacy concerns, has created an urgent need for accessible and scalable support. Large Language Models (LLMs) have emerged as a transformative technology with strong potential to democratize mental health support through advanced natural language understanding and generation. However, the rapidly expanding, fragmented body of work in this area lacks a coherent evolutionary narrative, making it difficult to contextualize current progress and identify future directions. This survey addresses this gap by organizing and analyzing the literature around a central thesis: the role of LLMs in mental health is evolving through three distinct, increasingly sophisticated phases. We trace this trajectory from Phase I, in which LLMs act primarily as passive Information Tools and Pattern Recognizers for assessment; through Phase II, where they function as Empathetic Conversationalists for in-the-moment, stateless interactions; to the current frontier, Phase III, which seeks Longitudinal, Personalized Companions implemented as stateful cognitive agents. To support this framework, we systematically review core technologies, agent architectures (Profile, Memory, Reasoning, and Planning), and the critical infrastructure of datasets and benchmarks, highlighting how their evolution underpins this developmental path. Viewing the field through this developmental lens, we provide a comprehensive synthesis of existing work, an insightful narrative of its trajectory, and a clear roadmap for future innovation in responsible, effective, and human-centered AI for mental healthcare. A curated collection of the resources reviewed in this survey is available at our project repository: https://github.com/Emo-gml/Awesome-Mental-Health-LLMs.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.25186